In this paper an Artificial Neural Network (ANN) model was used to help cars dealers recognize the many characteristics of cars, including manufacturers, their location and classification of cars according to several categories including: Make, Model, Type, Origin, DriveTrain, MSRP, Invoice, EngineSize, Cylinders, Horsepower, MPG_Highway, Weight, Wheelbase, Length. ANN was used in prediction of the number of miles per gallon when the car is driven in the city(MPG_City). The results showed that ANN model was able to predict MPG_City (...) with 97.50 % accuracy. The factor of DriveTrain has the most influence on MPG_City evaluation. Similar studies can be carried out for the evaluation of other characteristics of cars. (shrink)

In this paper an Artificial Neural Network (ANN) model, for predicting the category of a tumor was developed and tested. Taking patients’ tests, a number of information gained that influence the classification of the tumor. Such information as age, sex, histologic-type, degree-of-diffe, status of bone, bone-marrow, lung, pleura, peritoneum, liver, brain, skin, neck, supraclavicular, axillar, mediastinum, and abdominal. They were used as input variables for the ANN model. A model based on the Multilayer Perceptron Topology was established and (...) trained using data set which its title is “primary tumor” and was obtained from the University Medical Centre, Institute of Oncology, Ljubljana, Yugoslavia Test data evaluation shows that the ANN model is able to correctly predict the tumor category with 76.67 % accuracy. (shrink)

In this paper an Artificial Neural Network (ANN) model was used to help cars dealers recognize the many characteristics of cars, including manufacturers, their location and classification of cars according to several categories including: Buying, Maint, Doors, Persons, Lug_boot, Safety, and Overall. ANN was used in forecasting car acceptability. The results showed that ANN model was able to predict the car acceptability with 99.12 %. The factor of Safety has the most influence on car acceptability evaluation. Comparative study (...) method is suitable for the evaluation of car acceptability forecasting, can also be extended to all other areas. (shrink)

In this research, an Artificial Neural Network (ANN) model was developed and tested to predict Birth Weight. A number of factors were identified that may affect birth weight. Factors such as smoke, race, age, weight (lbs) at last menstrual period, hypertension, uterine irritability, number of physician visits in 1st trimester, among others, as input variables for the ANN model. A model based on multi-layer concept topology was developed and trained using the data from some birth cases in hospitals. (...) The evaluation of testing the dataset shows that the ANN model is capable of correctly predicting the birth weight with 100% accuracy. (shrink)

Diabetes is one of the most common diseases worldwide where a cure is not found for it yet. Annually it cost a lot of money to care for people with diabetes. Thus the most important issue is the prediction to be very accurate and to use a reliable method for that. One of these methods is using artificial intelligence systems and in particular is the use of Artificial Neural Networks (ANN). So in this paper, we used (...) artificial neural networks to predict whether a person is diabetic or not. The criterion was to minimize the error function in neural network training using a neural network model. After training the ANN model, the average error function of the neural network was equal to 0.01 and the accuracy of the prediction of whether a person is diabetics or not was 87.3%. (shrink)

Abstract: The emergence of the novel coronavirus (COVID-19) in 2019 has presented the world with an unprecedented global health crisis. The rapid and widespread transmission of the virus has strained healthcare systems, disrupted economies, and challenged societies. In response to this monumental challenge, the intersection of technology and healthcare has become a focal point for innovation. This research endeavors to leverage the capabilities of Artificial Neural Networks (ANNs) to develop an advanced predictive model for forecasting the spread (...) of COVID-19. It involves the collection, analysis, and integration of diverse datasets encompassing epidemiological, clinical, and social factors that influence the virus's dissemination. (shrink)

As a type of evidence glass can be very useful contact trace material in a wide range of offences including burglaries and robberies, hit-and-run accidents, murders, assaults, ram-raids, criminal damage and thefts of and from motor vehicles. All of that offer the potential for glass fragments to be transferred from anything made of glass which breaks, to whoever or whatever was responsible. Variation in manufacture of glass allows considerable discrimination even with tiny fragments. In this study, we worked glass classification (...) and testing of artificial neural network model created by the JustNN. The aim of the study is help investigator in identifying the type of glass found in arena of the crime. The Neural Network model was trained and validated using the type of glass dataset. The accuracy of model in predicting the type of glass reached 96.7%. Thus neural network is suitable for predicating type of glasses. (shrink)

Buildings energy consumption is growing gradually and put away around 40% of total energy use. Predicting heating and cooling loads of a building in the initial phase of the design to find out optimal solutions amongst different designs is very important, as ell as in the operating phase after the building has been finished for efficient energy. In this study, an artificial neural network model was designed and developed for predicting heating and cooling loads of a building based (...) on a dataset for building energy performance. The main factors for input variables are: relative compactness, roof area, overall height, surface area, glazing are a, wall area, glazing area distribution of a building, orientation, and the output variables: heating and cooling loads of the building. The dataset used for training are the data published in the literature for various 768 residential buildings. The model was trained and validated, most important factors affecting heating load and cooling load are identified, and the accuracy for the validation was 99.60%. (shrink)

Accurate assessment and comprehension of smoking behavior are pivotal for elucidating associated health risks and formulating effective public health strategies. In this study, we introduce an innovative approach to predict and analyze smoking prevalence using an artificial neural network (ANN) model. Leveraging a comprehensive dataset spanning multiple years and geographic regions, our model incorporates various features, including demographic data, economic indicators, and tobacco control policies. This research investigates smoking trends with a specific focus on gender-based analyses. These findings (...) are pivotal for enhancing public health initiatives aimed at mitigating tobacco use, assessing associated health risks, and mitigating smoking-related diseases. (shrink)

This paper adopts two modeling tools, namely, multiple linear regression (MLR) and artificial neural networks (ANNs), to predict the concentrations of heavy metals (zinc, boron, and manganese) in surface waters of the Oued Inaouen watershed flowing towards Inaouen, using a set of physical-chemical parameters. XLStat was employed to perform multiple linear and nonlinear regressions, and Statista 10 was chosen to construct neural networks for modeling and prediction. The effectiveness of the ANN- and MLR-based stochastic models (...) was assessed by the determination coefficient (R²), the sum squared error (SSE) and a review of fit graphs. The results demonstrate the value of ANNs for prediction modeling. Drawing on supervised learning and back propagation, the ANN-based prediction models adopt an architecture of [18-15-1] for zinc, [18-11-1] for manganese, and [18-8-1] for boron, and perform effectively with a single cached layer. It was found that the MLR-based prediction models are substantially less accurate than those based on the ANNs. In addition, the physical-chemical parameters being investigated are nonlinearly correlated with the levels of heavy metals in the surface waters of the Oued Inaouen watershed flowing towards Inaouen. (shrink)

Computer assisted theorem proving is an increasingly important part of mathematical methodology, as well as a long-standing topic in artificial intelligence (AI) research. However, the current generation of theorem proving software have limited functioning in terms of providing new proofs. Importantly, they are not able to discriminate interesting theorems and proofs from trivial ones. In order for computers to develop further in theorem proving, there would need to be a radical change in how the software functions. Recently, machine learning (...) results in solving mathematical tasks have shown early promise that deep artificial neural networks could learn symbolic mathematical processing. In this paper, I analyze the theoretical prospects of such neural networks in proving mathematical theorems. In particular, I focus on the question how such AI systems could be incorporated in practice to theorem proving and what consequences that could have. In the most optimistic scenario, this includes the possibility of autonomous automated theorem provers (AATP). Here I discuss whether such AI systems could, or should, become accepted as active agents in mathematical communities. (shrink)

Abstract: This research explores the application of artificial neural networks (ANNs) in predicting cancer using a synthetically generated dataset designed for research purposes. The dataset comprises 10,000 pseudo-patient records, each characterized by gender, age, smoking history, fatigue, and allergy status, along with a binary indicator for the presence or absence of cancer. The 'Gender,' 'Smoking,' 'Fatigue,' and 'Allergy' attributes are binary, while 'Age' spans a range from 18 to 100 years. The study employs a three-layer ANN architecture (...) to develop a predictive model. The achieved accuracy of 97.24% and a low loss value of 0.02 indicate promising performance. Further analysis involves a comprehensive examination of the confusion matrix, precision, recall, and F1 score metrics, along with the ROC curve and AUC score, to provide a detailed understanding of the model's strengths and weaknesses. Additionally, considerations for cross-validation, hyperparameter tuning, and interpretability are discussed. It is emphasized that while the synthetic nature of the dataset allows for controlled experimentation, results should be cautiously interpreted and validated on authentic clinical data before extrapolation to real-world medical scenarios. This research serves as a valuable contribution to the exploration of predictive models for cancer detection, encouraging continued investigation and development in the field. (shrink)

Heart failure is a major cause of death worldwide. Early detection and intervention are essential for improving the chances of a positive outcome. This study presents a novel approach to predicting the likelihood of a person having heart failure using a neural network model. The dataset comprises 918 samples with 11 features, such as age, sex, chest pain type, resting blood pressure, cholesterol, fasting blood sugar, resting electrocardiogram results, maximum heart rate achieved, exercise-induced angina, oldpeak, ST_Slope, and HeartDisease. A (...) neural network model with four layers (1 input and 1 output) was trained on the dataset and achieved an accuracy of 90% and an average error of 0.009. The most influential factors in heart failure prediction were found to be oldpeak, ST_Slope, sex, fastingBS, chestPainType, exerciseAngina, cholesterol, restingBP, maxHR, restingBP, and age. This study provides a valuable tool for early detection and intervention of heart failure, thereby contributing to the field of health and medicine. (shrink)

Abstract Heart Attack is the Cardiovascular Disease (CVD) which causes the most deaths among CVDs. We collected a dataset from Kaggle website. In this paper, we propose an ANN model for the predicting whether a patient has a heart attack or not that. The dataset set consists of 9 features with 1000 samples. We split the dataset into training, validation, and testing. After training and validating the proposed model, we tested it with testing dataset. The proposed model reached an accuracy (...) of 98.01% on the Heart Disease Dataset. (shrink)

Throughout this research, imposing the training of an Artificial Neural Network (ANN) to play tic-tac-toe bored game, by training the ANN to play the tic-tac-toe logic using the set of mathematical combination of the sequences that could be played by the system and using both the Gradient Descent Algorithm explicitly and the Elimination theory rules implicitly. And so on the system should be able to produce imunate amalgamations to solve every state within the game course to make better (...) of results of winnings or getting draw. (shrink)

In this paper, we developed an Artificial Neural Network (ANN) for detect the absence or presence of lung cancer in human body. Symptoms were used to diagnose the lung cancer, these symptoms such as Yellow fingers, Anxiety, Chronic Disease, Fatigue, Allergy, Wheezing, Coughing, Shortness of Breath, Swallowing Difficulty and Chest pain. They were used and other information about the person as input variables for our ANN. Our ANN established, trained, and validated using data set, which its title is (...) “survey lung cancer”. Model evaluation showed that the ANN model is able to detect the absence or presence of lung cancer with 96.67 % accuracy. (shrink)

Parkinson's Disease (PD) is a long-term degenerative disorder of the central nervous system that mainly affects the motor system. The symptoms generally come on slowly over time. Early in the disease, the most obvious are shaking, rigidity, slowness of movement, and difficulty with walking. Doctors do not know what causes it and finds difficulty in early diagnosing the presence of Parkinson’s disease. An artificial neural network system with back propagation algorithm is presented in this paper for helping doctors (...) in identifying PD. Previous research with regards to predict the presence of the PD has shown accuracy rates up to 93% [1]; however, accuracy of prediction for small classes is reduced. The proposed design of the neural network system causes a significant increase of robustness. It is also has shown that networks recognition rates reached 100%. (shrink)

Abstract: Accurate stock price prediction is essential for informed investment decisions and financial planning. In this research, we introduce an innovative approach to forecast stock prices using an Artificial Neural Network (ANN). Our dataset, consisting of 5582 samples and 6 features, including historical price data and technical indicators, was sourced from Yahoo Finance. The proposed ANN model, composed of four layers (1 input, 1 hidden, 1 output), underwent rigorous training and validation, yielding remarkable results with an accuracy of (...) 99.84% and an average error of 0.005. Additionally, we conducted a feature importance analysis, identifying the key drivers of stock price prediction, such as "High," "Low," "Open," "Volume"," and "Date." This study not only offers a highly accurate stock price prediction model but also contributes valuable insights into the influential factors affecting stock prices, enhancing the field of financial analysis and investment decision-making that are suitable for the task. (shrink)

The grammatical forms and material of the book of Revelation suggest a complex interplay of Old Testament and 1st century literature and language. As well, the book does not lack its own peculiarity and character that is unparalleled in the literate world. Various analytical tools including historical-comparative methodologies have been employed to reconstruct the linguistic paradigm of the book. Artificial intelligence and its derivatives provide alternate methods of probing this paradigm.

In this paper, an artificial neural network (ANN) model was developed and validated to predict whether a couple is going to get divorced or not. Prediction is done based on some questions that the couple answered, answers of those questions were used as the input to the ANN. The model went through multiple learning-validation cycles until it got 100% accuracy.

Purpose – The internet creates ample opportunities to start a mobile social commerce business. The literature confirms the issue of customer trust for social commerce businesses is a challenge that must be addressed. Hence, this study aims to examine the antecedents of trust in mobile social commerce by applying linear and non-linear relationships based on partial least squares structural equation modeling and an artificial neural network model. -/- Design/methodology/approach – This study applied a non-linear artificial neural (...) network approach to provide a further understanding of the determinants of trust in mobile social commerce based on a non-linear and non-compensatory model. Besides, a questionnaire was distributed to 340 social commerce customers in Malaysia. -/- Findings – The conceptual framework for investigating trust in mobile social commerce has various advantages and contributions to predicting consumer behaviour. The results of the study showed there is a positive and significant relationship between social support, presence and unified theory of acceptance and use of technology2 (UTAUT2). In addition, UTAUT2 has fully mediated the relationship between social support, presence and trust in social commerce. Finally, the results concluded the relationship between UTAUT2 and trust in social commerce would be stronger when the diffusion of innovation and innovation resistance is high and low, respectively. -/- Research limitations/implications – The current study provides a novel perspective on how customers can trust social m-commerce to provide real solutions to managers of encouraging e-marketing among consumers. -/- Practical implications – This paper shows how businesses can develop trust in social m-commerce in Malaysian markets. The findings of this study probably could be extended to other businesses in Asia or other countries. Because trust in social e-commerce has a dynamic role in consumer behaviour and intention to purchase. -/- Originality/value – This study provided a new perspective on mobile social commerce and paid more attention to an investigation of such emerging commerce. The originality of this study is embodied by investigating an integrated model that included different theories that presented new directions of trust in mobile social commerce through social and behavioural determinants. (shrink)

Water quality assessment is critical for environmental sustainability and public health. This research employs neural networks to predict water quality, utilizing a dataset of 21 diverse features, including metals, chemicals, and biological indicators. With 8000 samples, our neural network model, consisting of four layers, achieved an impressive 94.22% accuracy with an average error of 0.031. Feature importance analysis revealed arsenic, perchlorate, cadmium, and others as pivotal factors in water quality prediction. This study offers a valuable contribution to (...) enhancing water quality monitoring and decision-making for stakeholders and policymakers. (shrink)

Abstract: This research focuses on utilizing Artificial Neural Networks (ANNs) to predict Audit Risk accurately, a critical aspect of ensuring financial system integrity and preventing fraud. Our dataset, gathered from Kaggle, comprises 18 diverse features, including financial and historical parameters, offering a comprehensive view of audit-related factors. These features encompass 'Sector_score,' 'PARA_A,' 'SCORE_A,' 'PARA_B,' 'SCORE_B,' 'TOTAL,' 'numbers,' 'marks,' 'Money_Value,' 'District,' 'Loss,' 'Loss_SCORE,' 'History,' 'History_score,' 'score,' and 'Risk,' with a total of 774 samples. Our proposed neural network (...) architecture, consisting of three layers (1 input, 1 hidden, and 1 output), forms the core of this study. While it may seem simple, the power of ANNs lies not in complexity but in their ability to uncover intricate data patterns. The model underwent rigorous training and validation, resulting in remarkable outcomes—an accuracy of 100% and an average error rate of 0.000015. In addition to performance metrics, our research investigates feature importance, revealing the key contributors to Audit Risk prediction. Notably, 'Sector_score,' 'PARA_A,' 'SCORE_A,' 'PARA_B,' 'SCORE_B,' 'TOTAL,' 'numbers,' 'marks,' 'Money_Value,' 'District,' 'Loss,' 'Loss_SCORE,' 'History,' and 'History_score' emerged as the most influential factors, shedding light on the elements crucial for precise risk assessment. This study advances Audit Risk prediction models and highlights the potential of ANNs in strengthening financial system integrity and fraud prevention. The insights gained from our findings offer practical guidance for stakeholders in the audit and financial sectors. (shrink)

Abstract: The aim behind analyzing Google Stock Prices dataset is to get a fair idea about the relationships between the multiple attributes a day might have, such as: the opening price for each day, the volume of trading for each day. With over a hundred thousand days of trading data, there are some patterns that can help in predicting the future prices. We proposed an Artificial Neural Network (ANN) model for predicting the closing prices for future days. The (...) prediction is based on these features (date, opening price, highest price, lowest price, volume), which were used as input variables and (closing price) as output variable for our ANN model. Our model was created, trained, and validated using data set in JNN environment, which its title is “Google-Stock-Prices”. The model evaluation showed that the ANN model is able to predict correctly 99.48% of the validation samples. (shrink)

The paper outlines an analysis of two types of information - ordinary and subjective, consideration is given to the difference between the concepts of intelligence and perceiving mind. It also provides description of some logical functional features of consciousness. A technical approach is proposed to technical obtaining of subjective information by changing the signal’s time degree of freedom to the spatial one in order to obtain the "observer" function in the system and information signals appearing in relation to it, that (...) serve as subjective sensations. The solution to this problem may give a new approach to designing a strong artificial intelligence and shed light on the difficult problem of the mind. (shrink)

This is the proceedings of the "1st Turkish Conference on AI and ANNs," K. Oflazer, V. Akman, H. A. Guvenir, and U. Halici (editors). The conference was held at Bilkent University, Bilkent, Ankara on 25-26 June 1992. -/- Language of contributions: English and Turkish.

Kidney stones pose a significant health concern, and early detection can lead to timely intervention and improved patient outcomes. This research endeavours to predict the presence of kidney stones based on urine analysis, utilizing a neural network model. A dataset of 552 urine specimens, comprising six essential physical characteristics (specific gravity, pH, osmolarity, conductivity, urea concentration, and calcium concentration), was collected and prepared. Our proposed neural network architecture, featuring three layers (input, hidden, output), was trained and validated, achieving (...) an impressive accuracy of 98.67% and an average error of 0.012. In addition to model performance, feature importance analysis was conducted to determine the most influential factors in predicting kidney stone presence. The findings underscore the significance of urea concentration, specific gravity, calcium concentration, conductivity, osmolarity, and pH as key indicators. This research contributes to the early diagnosis of kidney stones and demonstrates the potential of neural networks in medical diagnostics. The clinical implications of these findings are discussed, emphasizing the importance of timely intervention in managing kidney stone-related health issues. (shrink)

Objective. Study of the validity and reliability of the discourse approach for the psycholinguistic understanding of the nature, structure, and features of the linguistic consciousness functioning. -/- Materials & Methods. This paper analyzes artificial neural network models built on the corpus of texts, which were obtained in the process of experimental research of the coronavirus quarantine concept as a new category of linguistic consciousness. The methodology of feedforward artificial neural networks (multilayer perceptron) was used in (...) order to assess the possibility of predicting the leading texts semantics based on the discourses ranks and their place in the respective linear sequence. Same baseline parameters were used to predict respondents' self-assessments of changes in their psychological well-being and in daily life routine during the quarantine, as well as to predict their preferences of the quarantine strategies. The study relied on basic ideas about discourse as a meaning constituted by the dispersion of other meanings (Foucault). The same dispersion mechanism realizes itself in interdiscourse interaction, forming a discursive formation at a higher level. The method of T-units (Hunt) was used to identify and count discourses in the texts. The ranking of discourses was provided based on the criterion of their semantic-syntactic autonomy. -/- Results. The conducted neural network modeling revealed a high accuracy in predicting the work of the linguistic consciousness functions associated with retrospective self-assessment and anticipatory imagination of the respondents. Another result of this modeling is a partial confirmation of the assumption concerning existence a relationship between the structural parameters of the discursive field (the rank of the discourses and their place in the respective linear sequence) and the leading semantics of the text. -/- Conclusions. A discourse approach to the study of linguistic consciousness, understanding of its structure and functioning features seems to be reasonably appropriate. The implementation of the approach presupposes the need to form a base of linguistic corpora with the inclusion in each text markup of such parameters as: the presence of specific discourses, their ranks, positions in the linear sequence of discourses. (shrink)

Abstract: In this study, we explore the possibility of classifying the plant species. We collected the plant species from Kaggle website. This dataset encompasses 544 samples, encompassing 136 distinct plant species. Recent advancements in machine learning, particularly Artificial Neural Networks (ANNs), offer promise in enhancing plant Species classification accuracy and efficiency. This research explores plant Species classification, harnessing neural networks' power. Utilizing a rich dataset from Kaggle, containing 544 entries, we develop and evaluate a (...) class='Hi'>neural network model. Our neural network, featuring a single hidden layer, achieves remarkable results—a staggering 100% accuracy and a minute average error rate of 0.002. Beyond performance metrics, we delve into the intricacies of plant Species classification through feature importance analysis. The most influential features— Vegsout, durflow, semiros, pdias, begflow, wind, leafy, autopoll and insects— uncover the physiological traits underpinning accurate rice classification. This research contributes to advancing rice classification methods and highlights the potential of ANNs in optimizing agricultural practices, ensuring plant safety, and bolstering global trade. (shrink)

Over 1.5 million living animal species have been described—of which around 1 million are insects—but it has been estimated there are over 7 million animal species in total. Animals range in length from 8.5 micrometres to 33.6 metres. In this paper an Artificial Neural Network (ANN) model, was developed and tested to predict animal species. There are a number of features that influence the classification of animal species. Such as the existence of hair/ feather, if the animal gives (...) birth or spawns, it is airborne, aquatic, predator, toothed, backboned, venomous, has –fins, has-tail, cat-sized, and domestic. A model based on the Multilayer Perceptron Topology was proposed and trained, using data set what was collected from UCI Machine Learning Repository. Evaluation of the proposed model shows that the ANN model is able to correctly predict the animal category with 100% accuracy. (shrink)

Abstract: This research delves into the utilization of Artificial Neural Networks (ANNs) as a powerful tool for predicting the overall ratings of books by leveraging a diverse set of attributes. To achieve this, we employ a comprehensive dataset sourced from Goodreads, enabling us to thoroughly examine the intricate connections between the different attributes of books and the ratings they receive from readers. In our investigation, we meticulously scrutinize how attributes such as genre, author, page count, publication year, (...) and reader reviews influence a book's overall rating. Through rigorous analysis and experimentation, we construct an advanced ANN model tailored for predictive analysis in the realm of book ratings. The outcomes of our study reveal the remarkable potential of ANNs in this domain. The ANN model exhibits an impressive level of accuracy when it comes to forecasting book ratings, underlining the efficacy and promise of artificial neural networks in enhancing our understanding and prediction of book evaluations. This research opens up new avenues for leveraging machine learning techniques to gain deeper insights into the dynamics of book ratings and reader preferences. (shrink)

Abstract: The aim behind analyzing the Goodreads dataset is to get a fair idea about the relationships between the multiple attributes a book might have, such as: the aggregate rating of each book, the trend of the authors over the years and books with numerous languages. With over a hundred thousand ratings, there are books which just tend to become popular as each day seems to pass. We proposed an Artificial Neural Network (ANN) model for predicting the overall (...) rating of books. The prediction is based on these features (bookID, title, authors, isbn, language_code, isbn13, # num_pages, ratings_count, text_reviews_count), which were used as input variables and (average_rating) as output variable for our ANN model. Our model were created, trained, and validated using data set in JNN environment, which its title is “Goodreads-books”. Model evaluation showed that the ANN model is able to predict correctly 99.78% of the validation samples. (shrink)

We describe and try to motivate our project to build systems using both a knowledge based and a neural network approach. These two approaches are used at different stages in the solution of a problem, instead of using knowledge bases exclusively on some problems, and neural nets exclusively on others. The knowledge base (KB) is defined first in a declarative, symbolic language that is easy to use. It is then compiled into an efficient neural network (NN) representation, (...) run, and the results from run time and (eventually) from learning are decompiled to a symbolic description of the knowledge contained in the network. After inspecting this recovered knowledge, a designer would be able to modify the KB and go through the whole cycle of compiling, running, and decompiling again. The central question with which this project is concerned is, therefore, How do we go from a KB to an NN, and back again? We are investigating this question by building tools consisting of a repertoire of language/translation/network types, and trying them on problems in a variety of domains. (shrink)

In artificial intelligence, recent research has demonstrated the remarkable potential of Deep Convolutional Neural Networks (DCNNs), which seem to exceed state-of-the-art performance in new domains weekly, especially on the sorts of very difficult perceptual discrimination tasks that skeptics thought would remain beyond the reach of artificial intelligence. However, it has proven difficult to explain why DCNNs perform so well. In philosophy of mind, empiricists have long suggested that complex cognition is based on information derived from sensory (...) experience, often appealing to a faculty of abstraction. Rationalists have frequently complained, however, that empiricists never adequately explained how this faculty of abstraction actually works. In this paper, I tie these two questions together, to the mutual benefit of both disciplines. I argue that the architectural features that distinguish DCNNs from earlier neural networks allow them to implement a form of hierarchical processing that I call “transformational abstraction”. Transformational abstraction iteratively converts sensory-based representations of category exemplars into new formats that are increasingly tolerant to “nuisance variation” in input. Reflecting upon the way that DCNNs leverage a combination of linear and non-linear processing to efficiently accomplish this feat allows us to understand how the brain is capable of bi-directional travel between exemplars and abstractions, addressing longstanding problems in empiricist philosophy of mind. I end by considering the prospects for future research on DCNNs, arguing that rather than simply implementing 80s connectionism with more brute-force computation, transformational abstraction counts as a qualitatively distinct form of processing ripe with philosophical and psychological significance, because it is significantly better suited to depict the generic mechanism responsible for this important kind of psychological processing in the brain. (shrink)

Symmetry in biological and physical systems is a product of self-organization driven by evolutionary processes, or mechanical systems under constraints. Symmetry-based feature extraction or representation by neural networks may unravel the most informative contents in large image databases. Despite significant achievements of artificial intelligence in recognition and classification of regular patterns, the problem of uncertainty remains a major challenge in ambiguous data. In this study, we present an artificial neural network that detects symmetry uncertainty states (...) in human observers. To this end, we exploit a neural network metric in the output of a biologically inspired Self- Organizing Map Quantization Error (SOM-QE). Shape pairs with perfect geometry mirror symmetry but a non-homogenous appearance, caused by local variations in hue, saturation, or lightness within and/or across the shapes in a given pair produce, as shown here, a longer choice response time (RT) for “yes” responses relative to symmetry. These data are consistently mirrored by the variations in the SOM-QE from unsupervised neural network analysis of the same stimulus images. The neural network metric is thus capable of detecting and scaling human symmetry uncertainty in response to patterns. Such capacity is tightly linked to the metric’s proven selectivity to local contrast and color variations in large and highly complex image data. (shrink)

Climate change temperature prediction plays a crucial role in effective environmental planning. This study introduces an innovative approach that harnesses the power of Artificial Neural Networks (ANNs) within the Just Neural Network (JustNN) framework to enhance temperature forecasting in the context of climate change. By leveraging historical climate data, our model achieves exceptional accuracy, redefining the landscape of temperature prediction without intricate preprocessing. This model sets a new standard for precise temperature forecasting in the context of (...) climate change. Moreover, our research provides valuable insights into the pivotal factors influencing temperature variations, making significant contributions to environmental science and climate mitigation strategies. (shrink)

Recent breakthroughs in artificial intelligence have primarily resulted from training deep neural networks (DNNs) with vast numbers of adjustable parameters on enormous datasets. Due to their complex internal structure, DNNs are frequently characterized as inscrutable ``black boxes,'' making it challenging to interpret the mechanisms underlying their impressive performance. This opacity creates difficulties for explanation, safety assurance, trustworthiness, and comparisons to human cognition, leading to divergent perspectives on these systems. This chapter examines recent developments in interpretability methods for (...) DNNs, with a focus on interventionist approaches inspired by causal explanation in philosophy of science. We argue that these methods offer a promising avenue for understanding how DNNs process information compared to merely behavioral benchmarking and correlational probing. We review key interventionist methods and illustrate their application through practical case studies. These methods allow researchers to identify and manipulate specific computational components within DNNs, providing insights into their causal structure and internal representations. We situate these approaches within the broader framework of causal abstraction, which aims to align low-level neural computations with high-level interpretable models. While acknowledging current limitations, we contend that interventionist methods offer a path towards more rigorous and theoretically grounded interpretability research, potentially informing both AI development and computational cognitive neuroscience. (shrink)

The article considers the problem of images and the role they play in our reflection turning to evidence provided by two seemingly very distant theories of mind together with two sorts of corresponding visions: dreams as analyzed by Freud who claimed that they are pictures of our thoughts, and their mechanical counterparts produced by neural networks designed for object recognition and classification. Freud’s theory of dreams has largely been ignored by philosophers interested in cognition, most of whom focused (...) solely on the linguistic incarnation of thoughts, but even though commonly neglected by respectable theories of thinking, dream images may prove to be the key to the black box of thought. As argued in this article, when seen from the right perspective and approached with the right set of questions, oneiric visions yield groundbreaking insights into the mechanism of how concepts and judgments are formed. Support for this conclusion comes from a tradition seemingly remote, if not opposed to psychoanalysis: the mechanical model of the mind conceived by information sciences and embodied in the form of artificial neural nets which mirror the activity of human visual cortex producing visions strikingly similar to those created by the sleeping mind. These purely mechanical, artificial ‘dreams’ constitute byproducts of algorithms designed for object recognition and classification, which, as I shall argue, reveals the true purpose of our own oneiric visual formations. Just like their mechanical counterparts produced by neural networks, condensations and displacements encountered in dreams are in fact visual universals. (shrink)

In this paper I discuss one of the key issuesin the philosophy of neuroscience:neurosemantics. The project of neurosemanticsinvolves explaining what it means for states ofneurons and neural systems to haverepresentational contents. Neurosemantics thusinvolves issues of common concern between thephilosophy of neuroscience and philosophy ofmind. I discuss a problem that arises foraccounts of representational content that Icall ``the economy problem'': the problem ofshowing that a candidate theory of mentalrepresentation can bear the work requiredwithin in the causal economy of a mind (...) and anorganism. My approach in the current paper isto explore this and other key themes inneurosemantics through the use of computermodels of neural networks embodied and evolvedin virtual organisms. The models allow for thelaying bare of the causal economies of entireyet simple artificial organisms so that therelations between the neural bases of, forinstance, representation in perception andmemory can be regarded in the context of anentire organism. On the basis of thesesimulations, I argue for an account ofneurosemantics adequate for the solution of theeconomy problem. (shrink)

The book is thought-provoking and informative, wide in scope while also being technically detailed, and still relevant to modem AI [at least as of 1998, the time of writing this review, but probably also at the time of posting this entry here, 2023] even though it was published in 1989. This relevance lies mainly in the book’s advocacy of distributed computation at multiple levels of description, its combining of neural networks and other techniques, its emphasis on the interplay (...) between action and perception, and its particular approach to natural language processing. The criticisms I have occasionally made above are relatively minor, and one of the major shortcomings of schema theory at least at the time of the book’s publication -- namely the lack of a detailed, preferably neural, mechanism for schema instantiation -- is one of which Arbib is well aware. The book is well produced, for the most part clearly written, and has useful summaries at the beginning of each chapter. Both general readers and AI researchers (mainly but not exclusively those working on robotics, vision and neural networks) could benefit from reading the book. (shrink)

In this research, an Artificial Neural Network (ANN) model was developed and tested to predict Birth Weight. A number of factors were identified that may affect birth weight. Factors such as smoke, race, age, weight (lbs) at last menstrual period, hypertension, uterine irritability, number of physician visits in 1st trimester, among others, as input variables for the ANN model. A model based on multi-layer concept topology was developed and trained using the data from some birth cases in hospitals. (...) The evaluation of testing the dataset shows that the ANN model is capable of correctly predicting the birth weight with 100% accuracy. (shrink)

In this paper an Artificial Neural Network (ANN) model was used to help cars dealers recognize the many characteristics of cars, including manufacturers, their location and classification of cars according to several categories including: Make, Model, Type, Origin, DriveTrain, MSRP, Invoice, EngineSize, Cylinders, Horsepower, MPG_Highway, Weight, Wheelbase, Length. ANN was used in prediction of the number of miles per gallon when the car is driven in the city(MPG_City). The results showed that ANN model was able to predict MPG_City (...) with 97.50 % accuracy. The factor of DriveTrain has the most influence on MPG_City evaluation. Similar studies can be carried out for the evaluation of other characteristics of cars. (shrink)

Endowing artificial systems with explanatory capacities about the reasons guiding their decisions, represents a crucial challenge and research objective in the current fields of Artificial Intelligence (AI) and Computational Cognitive Science [Langley et al., 2017]. Current mainstream AI systems, in fact, despite the enormous progresses reached in specific tasks, mostly fail to provide a transparent account of the reasons determining their behavior (both in cases of a successful or unsuccessful output). This is due to the fact that the (...) classical problem of opacity in artificial neural networks (ANNs) explodes with the adoption of current Deep Learning techniques [LeCun, Bengio, Hinton, 2015]. In this paper we argue that the explanatory deficit of such techniques represents an important problem, that limits their adoption in the cognitive modelling and computational cognitive science arena. In particular we will show how the current attempts of providing explanations of the deep nets behaviour (see e.g. [Ritter et al. 2017] are not satisfactory. As a possibile way out to this problem, we present two different research strategies. The first strategy aims at dealing with the opacity problem by providing a more abstract interpretation of neural mechanisms and representations. This approach is adopted, for example, by the biologically inspired SPAUN architecture [Eliasmith et al., 2012] and by other proposals suggesting, for example, the interpretation of neural networks in terms of the Conceptual Spaces framework [Gärdenfors 2000, Lieto, Chella and Frixione, 2017]. All such proposals presuppose that the neural level of representation can be considered somehow irrelevant for attacking the problem of explanation [Lieto, Lebiere and Oltramari, 2017]. In our opinion, pursuing this research direction can still preserve the use of deep learning techniques in artificial cognitive models provided that novel and additional results in terms of “transparency” are obtained. The second strategy is somehow at odds with respect to the previous one and tries to address the explanatory issue by avoiding to directly solve the “opacity” problem. In this case, the idea is that one of resorting to pre-compiled plausible explanatory models of the word used in combination with deep-nets (see e.g. [Augello et al. 2017]). We argue that this research agenda, even if does not directly fits the explanatory needs of Computational Cognitive Science, can still be useful to provide results in the area of applied AI aiming at shedding light on the models of interaction between low level and high level tasks (e.g. between perceptual categorization and explanantion) in artificial systems. (shrink)

Abstract: In this research, the Artificial Neural Network (ANN) model was developed and tested to predict the rate of treatment expenditure on an individual or family in a country. A number of factors have been identified that may affect treatment expenses. Factors such as age, grade level such as primary, preparatory, secondary or college, sex, size of disability, social status, and annual medical expenses in fixed dollars excluding dental and outpatient clinics among others, as input variables for the (...) ANN model. A model based on the multi-layer Perceptron topology was developed and trained using data on 5574 cases. The evaluation of the test data shows that the ANN model is capable of predicting correctly Medical Expenses. (shrink)

Abstract: In this research, an Artificial Neural Network (ANN) model was developed and tested to predict efficiency of antibiotics in treating various bacteria types. Attributes that were taken in account are: organism name, specimen type, and antibiotic name as input and susceptibility as an output. A model based on one input, one hidden, and one output layers concept topology was developed and trained using a data from Queensland government's website. The evaluation shows that the ANN model is capable (...) of correctly predicting the susceptibility of organisms to the antibiotics with 98% accuracy. -/- . (shrink)

Why would we want to develop artificial human-like arithmetical intelligence, when computers already outperform humans in arithmetical calculations? Aside from arithmetic consisting of much more than mere calculations, one suggested reason is that AI research can help us explain the development of human arithmetical cognition. Here I argue that this question needs to be studied already in the context of basic, non-symbolic, numerical cognition. Analyzing recent machine learning research on artificial neural networks, I show how AI (...) studies could potentially shed light on the development of human numerical abilities, from the proto-arithmetical abilities of subitizing and estimating to counting procedures. Although the current results are far from conclusive and much more work is needed, I argue that AI research should be included in the interdisciplinary toolbox when we try to explain the development and character of numerical cognition and arithmetical intelligence. This makes it relevant also for the epistemology of mathematics. (shrink)

Abstract: Rice, as a paramount staple crop worldwide, sustains billions of lives. Precise classification of rice types holds immense agricultural, nutritional, and economic significance. Recent advancements in machine learning, particularly Artificial Neural Networks (ANNs), offer promise in enhancing rice type classification accuracy and efficiency. This research explores rice type classification, harnessing neural networks' power. Utilizing a rich dataset from Kaggle, containing 18,188 entries and key rice grain attributes, we develop and evaluate a neural network (...) model. Our neural network, featuring a single hidden layer, achieves remarkable results—a staggering 100% accuracy and a minute average error rate of 0.000001. Beyond performance metrics, we delve into the intricacies of rice type classification through feature importance analysis. The most influential features—'id,' 'Area,' 'MajorAxisLength,' 'MinorAxisLength,' 'Eccentricity,' 'ConvexArea,' 'EquivDiameter,' 'Extent,' 'Perimeter,' 'Roundness,' and 'AspectRatio'—uncover the physiological traits underpinning accurate rice classification. This research contributes to advancing rice classification methods and highlights the potential of ANNs in optimizing agricultural practices, ensuring food safety, and bolstering global trade. (shrink)

In a recent reply to our article, “What is Interpretability?,” Prasetya argues against our position that artificial neural networks are explainable. It is claimed that our indefeasibility thesis—that adding complexity to an explanation of a phenomenon does not make the phenomenon any less explainable—is false. More precisely, Prasetya argues that unificationist explanations are defeasible to increasing complexity, and thus, we may not be able to provide such explanations of highly complex AI models. The reply highlights an important (...) lacuna in our original paper, the omission of the unificationist account of explanation, and affords us the opportunity to respond. Here, we argue that artificial neural networks are explainable in a way that should satisfy unificationists and that interpretability methods present ways in which ML theories can achieve unification. (shrink)

Abstract: This paper presents an artificial neural network based approach for the diagnosis of hepatitis virus. A number of factors that may possibly influence the performance of patients were outlined. Such factors as age, sex, Steroid, Antivirals, Fatigue, Malaise, Anorexia, Liver Big, Liver Firm Splean Palpable, Spiders, Ascites, Varices, Bilirubin, Alk Phosphate, SGOT, Albumin, Protine and Histology, were then used as input variables for the ANN model . Test data evaluation shows that the ANN model is able to (...) correctly predict the diagnosis of more than 93% of prospective Patients. (shrink)

Abstract: In this paper an Artificial Neural Network (ANN) model, for predicting the Letters from twenty dissimilar fonts for each letter. The character images were, initially, based on twenty dissimilar fonts and each letter inside these twenty fonts was arbitrarily distorted to yield a file of 20,000 distinctive stimuli. Every stimulus was transformed into 16 simple numerical attributes (arithmetical moments and edge amounts) which were then ascended to be suitable into a range of numeral values from 0 to (...) 15. We naturally chose, arbitrarily, 1,000 distinctive stimuli for this research. We made certain that the scattering remnants the similar after selecting the one thousand stimuli. In this research, a neural network tool (Just NN) was used for the purpose of predicting to classify every of a huge number of black and white four-sided pixel displays as one of the 26 capital letters in the English language. (shrink)