convolutional-neural-network deep-learning deep-neural-networks generative-adversarial-network generative-models lstm-neural-networks machine-learning machine-learning-algorithms numpy pytorch pytorch-implementation pytorch-tutorial recurrent-neural-networks scipy supervised-learning tensorflow unsupervised-learning variational-autoencoder

ml-study-guide: Implementing Algorithms from scratch

Purpose

This repository is a set of common machine and deep learning algorithms implementations, with additional implmentation of foundational papers in deep learning. The aim is to get familiar with NumPy, SciPy and Tensorflow V2 APIs. Furthermore, it gives a better intuition of common deep learning architectures and where to use them.

PyTorch Implementations

The PyTorch implementations of the algorithms follow Sebastian Raschka's course: Deep Learning Fundamentals, hence it will updated as new material becomes available

Cheers and Have fun learning!!!

About

Implementing ML Algos using NumPy, SciPy and Tensorflow v2

convolutional-neural-network deep-learning deep-neural-networks generative-adversarial-network generative-models lstm-neural-networks machine-learning machine-learning-algorithms numpy pytorch pytorch-implementation pytorch-tutorial recurrent-neural-networks scipy supervised-learning tensorflow unsupervised-learning variational-autoencoder

MIT License

Languages

Language:Jupyter Notebook 99.9%Language:Python 0.1%