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 ability to abstract, count, and use System~2 reasoning are well-knownmanifestations of intelligence and understanding. In this paper, we argue,using the example of the ``Look and Say" puzzle, that although deep neuralnetworks can exhibit high `competence' (as measured by accuracy) when trainedon large data sets (2 million examples in our case), they do not show any signon the deeper understanding of the problem, or what D. Dennett calls`comprehension'. We report on two sets experiments: first, computing the nextelement of the sequence, and ,then, the previous element. We view both problemsas building a translator from one set of tokens to another. We apply bothstandard LSTMs and Transformer/Attention-based neural networks, using publiclyavailable machine translation software. We observe that despite the amazingaccuracy, the performance of the trained programs on the actual L\&S sequenceis bad, and shows no understanding of the principles behind the sequences. Theramifications of this finding include: (1) from the cognitive scienceperspective, we argue that we need better mathematical models of abstraction;(2) the universality of neural networks should be re-examined for functionsacting on discrete data sets; (3) we hypothesize topology can provide adefinition of without the reference to the concept of distance.

Abstraction, Reasoning and Deep Learning: A Study of the "Look and Say" Sequence