Why you should use wide neural networks

4 years 5 months ago #5 by Robinson

You may be interested in a couple papers that study how deep networks may compress information (lose mutual information between the input and the hidden layers, while gaining mutual information between the hidden layers and the output) during training. I find that line of work very interesting.

For more details
Brand Video Marketing

Please Log in or Create an account to join the conversation.

Time to create page: 0.241 seconds


Neither the owner nor the website operator nor the authors of the content can be responsible for any possible losses (especilly the economical or financial ones) caused by application of the information published on these web sites. There is absolutely no warranty of the accuracy, completeness of information, text, graphics, links etc of the content of these web sites.

Trading of stocks, CFD's and forex is highly risky and can lead to high losses.