From 0a97778b69ac1a72939a268b1be1ab37ca3617a4 Mon Sep 17 00:00:00 2001 From: Daniel Shiffman Date: Sun, 11 Feb 2018 12:50:37 -0500 Subject: [PATCH] Update README.md --- README.md | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 4b7d930..866f45c 100644 --- a/README.md +++ b/README.md @@ -13,15 +13,18 @@ Here are some demos running directly in the browser: * [x] Delta weight formulas, connect to "mathematics of gradient" video * [x] Implement gradient descent in library / with code * [x] XOR coding challenge [live example](https://codingtrain.github.io/Toy-Neural-Network-JS/examples/xor/) -* [x] MNIST coding challenge [live example](https://codingtrain.github.io/Toy-Neural-Network-JS/examples/mnist/) +* [ ] MNIST coding challenge [live example](https://codingtrain.github.io/Toy-Neural-Network-JS/examples/mnist/) + * redo this challenge + * cover softmax activation, cross-entropy + * graph cost function? + * only use testing data * [ ] Support for saving / restoring network (see #50) * [ ] Support for different activation functions (see #45) -* [ ] softmax activation, cross-entropy +* [ ] Support for multiple hidden layers (see #61) * [ ] Support for neuro-evolution * [ ] play flappy bird (many players at once). * [ ] play pong (many game simulations at once) * [ ] steering sensors (a la Jabril's forrest project!) -* [ ] Support for multiple hidden layers * [ ] Combine with ml5 / deeplearnjs ## Getting Started