Is Information in the Brain Represented in Continuous or Discrete Form?

Re:Is Information in the Brain Represented in Continuous or ... by bitL on Monday May 21, 2018 @10:42PM (#17123389)

Is there any abstraction of Deep Learning on discrete domains? Using discrete calculus from Concrete Mathematics perhaps? Or better a mixed discrete/continuous one? I guess optimization there would be killer...

[ Parent | on HN ]

Re:Is Information in the Brain Represented in Continuous or ... by pests on Tuesday May 22, 2018 @07:20AM (#17125116)

There are many different ways to represent discrete domains in deep learning. One example is entity embeddings such as word2vec which turns a finite list of entities (words in word2vec) into a number of continuous variables.

[ Parent | on HN ]

Re:Is Information in the Brain Represented in Continuous or ... by bitL on Tuesday May 22, 2018 @09:33AM (#17125780)

I know. Though if you want to represent complex DAGs or do some inner combinatorics, it doesn't generalize that well. DeepWalk and its variations are only for toy-sized graphs.

[ Parent | on HN ]