PhilSci Archive

Throwing light on black boxes: emergence of visual categories from deep learning

López-Rubio, Ezequiel (2020) Throwing light on black boxes: emergence of visual categories from deep learning. [Preprint]

[img]
Preview
Text
UnderstandingDeepLearning_Synthese_Preprint.pdf

Download (202kB) | Preview

Abstract

One of the best known arguments against the connectionist approach to artificial intelligence and cognitive science is that neural networks are black boxes, i.e., there is no understandable account of their operation. This difficulty has impeded efforts to explain how categories arise from raw sensory data. Moreover, it has complicated investigation about the role of symbols and language in cognition. This state of things has been radically changed by recent experimental findings in artificial deep learning research. Two kinds of artificial deep learning networks, namely the Convolutional Neural Network (CNN) and the Generative Adversarial Network (GAN) have been found to possess the capability to build internal states that are interpreted by humans as complex visual categories, without any specific hints or any grammatical processing. This emergent ability suggests that those categories do not depend on human knowledge or the syntactic structure of language, while they do rely on their visual context. This supports a mild form of empiricism, while it does not assume that computational functionalism is true. Some consequences are extracted regarding the debate about amodal and grounded representations in the human brain. Furthermore, new avenues for research on cognitive science are open.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
López-Rubio, Ezequielezeqlr@lcc.uma.es0000-0001-8231-5687
Keywords: deep learning, visual categories, machine learning, cognitive science
Subjects: Specific Sciences > Neuroscience > Cognitive Neuroscience
Specific Sciences > Cognitive Science > Computation
Specific Sciences > Artificial Intelligence > Machine Learning
Specific Sciences > Cognitive Science > Perception
General Issues > Technology
Depositing User: Prof. Ezequiel López-Rubio
Date Deposited: 15 May 2020 03:38
Last Modified: 15 May 2020 03:38
Item ID: 17182
Official URL: https://doi.org/10.1007/s11229-020-02700-5
DOI or Unique Handle: 10.1007/s11229-020-02700-5
Subjects: Specific Sciences > Neuroscience > Cognitive Neuroscience
Specific Sciences > Cognitive Science > Computation
Specific Sciences > Artificial Intelligence > Machine Learning
Specific Sciences > Cognitive Science > Perception
General Issues > Technology
Date: May 2020
URI: https://philsci-archive.pitt.edu/id/eprint/17182

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Altmetric.com

Actions (login required)

View Item View Item