Moving beyond content-specific computation in artificial neural networks

Journal article

A basic deep neural network (DNN) is trained to exhibit a large set of input–output dispositions. While being a good model of the way humans perform some tasks automatically, without deliberative reasoning, more is needed to approach human-like artificial intelligence. Analysing recent additions brings to light a distinction between two fundamentally different styles of computation: content-specific and non-content-specific computation (as first defined here). For example, deep episodic RL networks draw on both. So does human conceptual reasoning. Combining the two takes advantage of the complementary costs and benefits of each. It also offers a better model of human cognitive competence.

Authors: Shea, N

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Wiley
• Journal: Mind and Language
• Volume: 38
• Issue: 1
• Pages: 156-177
• Publication date: 2021-10-05
• Acceptance date: 2021-05-14
• DOI: 10.1111/mila.12387
• EISSN: 1468-0017
• ISSN: 0268-1064
• Language: English
• Keywords: distributed representation; deep neural networks; explicit memory; FFR; computation; content-specific; concepts