playground
playground copied to clipboard
tensorflow
Play with neural networks!
Dear Developers, I would like to freeze the weights and the biases in some given layers (at some given initial values). Do you have any suggestions how I could do...
Fix the Software Grant and Corporate Contributor License Agreement Link. Formatting was not correct.
Hello. I can't get the hot reload to work. I get the following: [1] [2] npm run watch-html exited with code 0 [1] [1] npm run watch-css exited with code...
The heatmap is currently counter-intuitive with cold blue showing positive values and warm orange showing negatives. Swaping them would make visualization easier to perceive.
Can anybody tell me what are the Training Loss and Test Loss given by the program when there is regularisation? Are they the mismatch at the data (as they should...
It would be nice to lift some of the limits: 1. Max layers 2. Max neurons per layer 3. Smaller regularization rates 4. Bigger batch sizes 5. More noise At...
This PR adds a dataset to exhibit the concept of overfitting. The dataset is linearly separable along the main diagonal, but its positive training samples only span a subset of...
