Empiricism without Magic: Transformational Abstraction in Deep Convolutional Neural Networks

Synthese (12):1-34 (2018)
  Copy   BIBTEX

Abstract

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.

Other Versions

No versions found

Similar books and articles

Toward biologically plausible artificial vision.Mason Westfall - 2023 - Behavioral and Brain Sciences 46:e290.
Deep learning: A philosophical introduction.Cameron Buckner - 2019 - Philosophy Compass 14 (10):e12625.

Analytics

Added to PP
2018-09-17

Downloads
1,482 (#9,990)

6 months
199 (#14,976)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Cameron Buckner
University of Florida

References found in this work

A treatise of human nature.David Hume & A. D. Lindsay - 1739 - Oxford,: Clarendon press. Edited by L. A. Selby-Bigge.
Doing without concepts.Edouard Machery - 2009 - New York: Oxford University Press.
Thinking about mechanisms.Peter Machamer, Lindley Darden & Carl F. Craver - 2000 - Philosophy of Science 67 (1):1-25.
A Treatise of Human Nature (1739-40).David Hume - 1739 - Mineola, N.Y.: Oxford University Press. Edited by Ernest Campbell Mossner.

View all 47 references / Add more references