English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The recently released AlphaZero algorithm achieves superhuman performance inthe games of chess, shogi and Go, which raises two open questions. Firstly, asthere is a finite number of possibilities in the game, is there a quantifiableintelligence measurement for evaluating intelligent systems, e.g. AlphaZero?Secondly, AlphaZero introduces sophisticated reinforcement learning andself-play to efficiently encode the possible states, is there a simpleinformation-theoretic model to represent the learning process and offer moreinsights in fostering strong AI systems?  This paper explores the above two questions by proposing a simple variance ofShannon's communication model, the concept of intelligence entropy and theUnified Intelligence-Communication Model is proposed, which provide aninformation-theoretic metric for investigating the intelligence level and alsoprovide an bound for intelligent agents in the form of Shannon's capacity,namely, the intelligence capacity. This paper then applies the concept andmodel to AlphaZero as a case study and explains the learning process ofintelligent agent as turbo-like iterative decoding, so that the learningperformance of AlphaZero may be quantitatively evaluated. Finally, conclusionsare provided along with theoretical and practical remarks.

The Entropy of Artificial Intelligence and a Case Study of AlphaZero from Shannon's Perspective