search

tensorflow / playground

Play with neural networks!
http://playground.tensorflow.org
Apache License 2.0
11.97k stars 2.55k forks source link

Feature Suggestion - Drop out and use different activation function in each layer. #50

Open goldflower opened 7 years ago

goldflower commented 7 years ago

I thought add these features are needed for all types of neuron networks, so it would be nice to add them.

In addition, maybe we could switch between feedforward and backpropagation mode?

emmanuelrouxfr commented 2 years ago

Dear @goldflower, by reading your issue it seems that you may appreciate the fork we've been working on !

https://coolearning.github.io/playground/

The Coolearning interface allows real-time network interaction during training, and much more ! Like individual learning rate, activation functions and regularization for each neuron... you can achieve your request by selecting the neurons of a layer and apply them a specific activation function !

See you there :)