Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference — mentioned by epmaybe

Thu, 09 Nov 2017 17:05:17 GMT

I've read the article :), the author is the same physician who wrote "emperor of all maladies", a book about cancer. Basically what it comes down to is that doctors get really good at bayesian inference at some point in their career, definitely not while we are students. I am however confident that we can build models that learn in a similar manner. I'm actually trying to build a model for a class project that uses bayesian inference in a CNN as per Gal et al (https://arxiv.org/abs/1506.02158) to try and detect diabetic retinopathy. Their paper actually tries to detect different skin cancers.

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

Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference · HackerPapers discussions

Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference — mentioned by epmaybe