This is a small enhanced version of the playground appilcation created by Daniel Smilkov and Shan Carter. https://github.com/tensorflow/playground https://playground.tensorflow.org/#activation=tanh&batchSize=10&dataset=circle&regDataset=reg-plane&learningRate=0.03&regularizationRate=0&noise=0&networkShape=4,2&seed=0.14647&showTestData=false&discretize=false&percTrainData=50&x=true&y=true&xTimesY=false&xSquared=false&ySquared=false&cosX=false&sinX=false&cosY=false&sinY=false&collectStats=false&problem=classification&initZero=false&hideText=false

It was build for a study-project and added following features to the original playground:

• Save function
• Fix seed-value
• New data-sets
• New input-features
• Extend the gradient descent algorithm with an momentum part

Feel free to clone the repository and play around with it!