Philosophy of Connectionism, Foundational Empirical Issues

The rapid advancements in artificial intelligence, particularly in natural language processing, have brought to light a critical challenge, i.e., the semantic grounding problem. This article explores the root causes of this issue, focusing on the limitations of connectionist models that dominate current AI research. By examining Noam Chomsky's theory of Universal Grammar and his critiques of connectionism, I highlight the fundamental differences between human language understanding and AI language generation. Introducing the concept of semantic grounding, I emphasise the need for (...) AI to connect language with real-world experiences and context to achieve true understanding. While multi-modal models represent a step forward, they fall short of addressing the core issue. The article concludes with a call for a course correction in AI development, advocating for the integration of embodied cognition, dynamic learning, hybrid models, and ethical practices. This shift is essential for creating AI systems that can meaningfully interact with the world, reducing the incidence of hallucinations and enhancing their reliability and utility. (shrink)

This paper aims to offer a new view of the role of connectionist models in the study of human cognition through the conceptualization of the history of connectionism – from the simplest perceptrons to convolutional neural nets based on deep learning techniques, as well as through the interpretation of criticism coming from symbolic cognitive science. Namely, the connectionist approach in cognitive science was the target of sharp criticism from the symbolists, which on several occasions caused its marginalization and almost complete (...) abandonment of its assumptions in the study of cognition. Criticisms have mostly pointed to its explanatory inadequacy as a theory of cognition or to its biological implausibility as a theory of implementation, and critics often focused on specific shortcomings of some connectionist models and argued that they apply to connectionism in general. In this paper, we want to show that both types of critique are based on the assumption that the only valid explanations in cognitive science are instances of homuncular functionalism and that by removing this assumption and by adopting an alternative methodology – exploratory mechanistic strategy, we can reject most objections to connectionism as irrelevant, explain the progress of connectionist models despite their shortcomings and sketch the trajectory of their future development. By adopting mechanistic explanations and by criticizing functionalism, we will reject the objections of explanatory inadequacy, by characterizing connectionist models as generic rather than concrete mechanisms, we will reject the objections of biological implausibility, and by attributing the exploratory character to connectionist models we will show that practice of generalizing current to general failures of connectionism is unjustified. (shrink)

Computational complexity is a discipline of computer science and mathematics which classifies computational problems depending on their inherent difficulty, i.e. categorizes algorithms according to their performance, and relates these classes to each other. P problems are a class of computational problems that can be solved in polynomial time using a deterministic Turing machine while solutions to NP problems can be verified in polynomial time, but we still do not know whether they can be solved in polynomial time as well. A (...) solution for the so-called NP-complete problems will also be a solution for any other such problems. Its artificial-intelligence analogue is the class of AI-complete problems, for which a complete mathematical formalization still does not exist. In this chapter we will focus on analysing computational classes to better understand possible formalizations of AI-complete problems, and to see whether a universal algorithm, such as a Turing test, could exist for all AI-complete problems. In order to better observe how modern computer science tries to deal with computational complexity issues, we present several different deep-learning strategies involving optimization methods to see that the inability to exactly solve a problem from a higher order computational class does not mean there is not a satisfactory solution using state-of-the-art machine-learning techniques. Such methods are compared to philosophical issues and psychological research regarding human abilities of solving analogous NP-complete problems, to fortify the claim that we do not need to have an exact and correct way of solving AI-complete problems to nevertheless possibly achieve the notion of strong AI. (shrink)

Abstract (for the combined three Parts) This paper presents the simplest known theory of processes involved in a person’s unconscious and conscious achievements such as intending, perceiving, reacting and thinking. The basic principle is that an individual has mental states which possess quantitative causal powers and are susceptible to influences from other mental states. Mental performance discriminates the present level of a situational feature from its level in an individually acquired, multiple featured norm (exemplar, template, standard). The effect on output (...) of a moderate disparity between input and norm is scaled in a universal unit of discrimination (Weber’s fraction), with the norm’s level being zero. When one process converts separate sources of input into an output, their discriminative distances from norm are summated. Distinct processes converging on an output combine their discriminations from norm orthogonally. An output may be influenced by the constructs of other outputs as well as by inputs. Descriptive performance is the influence of one category of input on a verbal output. Reasoning is minimally the effect of one verbal process on another. In deeper mental processing, the influence on a response comes from a response construct modulating a description: this process gives the meaning to an emotion or a motive. Descriptive modulation of stimulation corresponds to a bodily sensation or other conceptualized percept. When an output is explained solely by sources of input, that response to the stimulation may be mediated unconsciously. Development of a person within physical and communal environments embodies such mental causation within material causation and acculturates that mind to social causation. (shrink)

Brains, unlike artificial neural nets, use symbols to summarise and reason about perceptual input. But unlike symbolic AI, they “ground” the symbols in the data: the symbols have meaning in terms of data, not just meaning imposed by the outside user. If neural nets could be made to grow their own symbols in the way that brains do, there would be a good prospect of combining neural networks and symbolic AI, in such a way as to combine the good features (...) of each. The article argues the cluster analysis provides algorithms to perform the task, and that any solution to the task must be a form of cluster analysis. (shrink)