This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
structured_factorization [2018/10/27 12:03]
structured_factorization [2018/10/27 12:07] (current)
Line 346: Line 346:
 https://​arxiv.org/​pdf/​1810.10531.pdf A mathematical theory of semantic development https://​arxiv.org/​pdf/​1810.10531.pdf A mathematical theory of semantic development
 in deep neural networks in deep neural networks
 +The synaptic weights of the neural
 +network extract from the statistical structure of the environment
 +a set of paired object analyzers and feature synthesizers associated
 +with every categorical distinction. The bootstrapped,​ simultaneous
 +learning of each pair solves the apparent Gordian knot of knowing
 +both which items belong to a category, and which features are important
 +for that category: the object analyzers determine category
 +membership, while the feature synthesizers determine feature importance,
 +and the set of extracted categories are uniquely determined
 +by the statistics of the environment.