Evaluating the visualization of what a Deep Neural Network has learned — mentioned by rickdeveloper

Mon, 08 Feb 2021 16:59:04 GMT

This is an interesting idea. I wonder if we could then use something like [0] to trace back "gay-ness" as well as other "personality features" (I'm not sure what the correct term is here) to the exact genes. One potential issue I see is that the DNA of any person has an arbitrary length, which poses some challenges in the design of a neural network. Traditionally, this has been solved with LSTMs or RNNs, but as far I know these are designed for data with a temporal dimension (such as text or speech, which progress with time). I'm not sure if that's true for DNA. [0]…

Paper and discussion history. A mention is not an endorsement.

Evaluating the visualization of what a Deep Neural Network has learned · HackerPapers discussions

Evaluating the visualization of what a Deep Neural Network has learned — mentioned by rickdeveloper