General‎ > ‎

[Article] 'Consciousness' in the machine learning (deep learning) perspective

posted Oct 1, 2017, 1:38 PM by Jong-Hwan Lee   [ updated Oct 9, 2017, 9:34 AM ]

The Consciousness Prior

 

Yoshua Bengio

 

Université de Montréal, MILA

 

September 26, 2017

 

Abstract

A new prior is proposed for representation learning, which can be combined with other priors in order to help disentangling abstract factors from each other. It is inspired by the phenomenon of conscious-ness seen as the formation of a low-dimensional combination of a few concepts constituting a conscious thought, i.e., consciousness as awareness at a particular time instant. This provides a powerful constraint on the representation in that such low-dimensional thought vectors can correspond to statements about reality which are either true, highly probable, or very useful for taking decisions. The fact that a few elements of the current state can be combined into such a predictive or useful statement is a strong constraint and deviates considerably from the maximum likelihood approaches to modeling data and how states unfold in the future based on an agent’s actions. Instead of making predictions in the sensory (e.g. pixel) space, the consciousness prior allow the agent to make predictions in the abstract space, with only a few dimensions of that space being involved in each of these predictions. The consciousness prior also makes it natural to map conscious states to natural language utterances or to express classical AI knowledge in the form of facts and rules, although the conscious states may be richer than what can be expressed easily in the form of a sentence, a fact or a rule. 


https://arxiv.org/pdf/1709.08568.pdf

Comments