Skip to content

Implementation of Machine Learning Algorithms in Pure Numpy Only

Notifications You must be signed in to change notification settings

apoorvreddy/numpy_ml

Repository files navigation

numpy_ml

Implementation of Neural Networks in Pure Numpy Only

mlp-npy-20.ipynb notebook contains the implementation of a 1 hidden layer neural network in pure Numpy. I have implemented the gradient computations as matrix multiplications of the Flattened Jacobian Matrices, the way it is (probably) implemented in popular libraries such as TensorFlow in the sense of computational graphs.

About

Implementation of Machine Learning Algorithms in Pure Numpy Only

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published