As the name suggests this repo tries to include some very simple and basic state of the art Neural Networks implemented in Keras and Tensorflow.
Deep learning. Neural networks. Backpropagation. Over the past year or two, I've heard these buzz words being tossed around a lot, and it's something that has definitely seized my curiosity recently. Deep learning is an area of active research these days, and if you've kept up with the field of computer science, I'm sure you've come across at least some of these terms at least once or tried to learn or code these concepts. So to make learning Deep Learning and Neural Networks easy for the beginners I have collected some simple Neural Network Models on MNIST Dataset. I used Keras and Tensorflow because they are quite easy for beginner to learn and understand.
I have also included a Feed Forward Neural Network program for approximate function of a2 + b2 with an error range of about 0.1% to 150% on very very small numbers and around 1-4% on large numbers. Play with the hyperparameters and update this file if you have less than 60 as loss.