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/

Zendy Plus

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

Zendy Tools

Zendy Open

Associative memory has been a prominent candidate for the computationperformed by the massively recurrent neocortical networks. Attractor networksimplementing associative memory have offered mechanistic explanation for manycognitive phenomena. However, attractor memory models are typically trainedusing orthogonal or random patterns to avoid interference between memories,which makes them unfeasible for naturally occurring complex correlated stimulilike images. We approach this problem by combining a recurrent attractornetwork with a feedforward network that learns distributed representationsusing an unsupervised Hebbian-Bayesian learning rule. The resulting networkmodel incorporates many known biological properties: unsupervised learning,Hebbian plasticity, sparse distributed activations, sparse connectivity,columnar and laminar cortical architecture, etc. We evaluate the synergisticeffects of the feedforward and recurrent network components in complex patternrecognition tasks on the MNIST handwritten digits dataset. We demonstrate thatthe recurrent attractor component implements associative memory when trained onthe feedforward-driven internal (hidden) representations. The associativememory is also shown to perform prototype extraction from the training data andmake the representations robust to severely distorted input. We argue thatseveral aspects of the proposed integration of feedforward and recurrentcomputations are particularly attractive from a machine learning perspective.

Brain-like combination of feedforward and recurrent network components achieves prototype extraction and robust pattern recognition