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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Animals are known to make efficient probabilistic inferences based onuncertain and noisy information from the outside world. Although it is knownthat generic neural networks can perform near-optimal point estimation byprobabilistic population codes which has been proposed as a neural basis forencoding of probability distribution, the mechanisms of sampling-basedinference has not been clarified. In this study, we trained two types ofartificial neural networks: feedforward neural networks (FFNNs) and recurrentneural networks (RNNs) to perform sampling based probabilistic inference. Then,we analyzed and compared the mechanisms of sampling in the RNN with those inthe FFNN. As a result, it was found that sampling in RNN is performed by amechanism that efficiently utilizes the properties of dynamical systems, unlikeFFNN. It was also found that sampling in RNNs acts as an inductive bias,enabling more accurate estimation than in MAP estimation. These results willprovide important implications for the discussion of the relationship betweendynamical systems and information processing in neural networks.

Dynamical Mechanism of Sampling-based Stochastic Inference under Probabilistic Population Codes