Extended Data Fig. 2: The complete MLR architecture that consists of the mVAE, binding pool, tokens, and classifiers for extracting labels (SVMss and SVMcc). | Nature Human Behaviour

Extended Data Fig. 2: The complete MLR architecture that consists of the mVAE, binding pool, tokens, and classifiers for extracting labels (SVMss and SVMcc).

From: A model of working memory for latent representations

Extended Data Fig. 2

Information flows in only one direction through the mVAE but can flow bidirectionally between the latent representations and the binding pool. Tokens are used to differentiate individual items. Note that three tokens are shown here but there is no limit to the number of tokens that can be allocated.

Back to article page