https://github.com/sophiaas/simple-neural-nets

Learn to build neural networks from scratch, simply. No autograd, no deep learning libraries - just numpy.
https://github.com/sophiaas/simple-neural-nets

convolutional-neural-networks deep-learning deep-neural-networks neural-networks neural-networks-from-scratch numpy recurrent-neural-networks

Last synced: about 7 hours ago
JSON representation

Learn to build neural networks from scratch, simply. No autograd, no deep learning libraries - just numpy.

• Host: GitHub
• URL: https://github.com/sophiaas/simple-neural-nets
• Owner: sophiaas
• Created: 2020-04-29T18:18:20.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2022-08-10T19:58:08.000Z (over 2 years ago)
• Last Synced: 2023-08-14T20:03:39.209Z (over 1 year ago)
• Topics: convolutional-neural-networks, deep-learning, deep-neural-networks, neural-networks, neural-networks-from-scratch, numpy, recurrent-neural-networks
• Language: Python
• Homepage:
• Size: 1.46 MB
• Stars: 6
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Simple Neural Nets

This codebase provides the skeletal structure for implementing neural networks from scratch, exclusively in numpy. Fill in the blanks to implement three fundamental neural network architectures: feedforward, recurrent, and convolutional. See `instructions.pdf` for a walkthrough of how to complete the repo and test your models!

*I wrote this codebase while a Graduate Student Instructor for UC Berkeley's Machine Learning course, CS189/289A. It was used as the 6th homework assignment in the Spring 2020 semester. [sagnibak](https://github.com/sagnibak) is a contributor.*