Build neural networks based only on Numpy
-
Updated
Feb 14, 2023 - Python
Build neural networks based only on Numpy
Classifying the Blur and Clear Images
This code is part of my post on Medium.
RNN architectures trained with Backpropagation and Reservoir Computing (RC) methods for forecasting high-dimensional chaotic dynamical systems.
This resource implements a deep neural network through Numpy, and is equipped with easy-to-understand theoretical derivation, mainly for the in-depth understanding of neural networks. 神经网络模型的理论证明与基于Numpy的实现。
Code base for solving Markov Decision Processes and Reinforcement Learning problems using Recurrent Convolutional Neural Networks.
Computer code collated for use with Artificial Intelligence Engines book by JV Stone
Particle Swarm Optimizer For Neural Network Training
Python library for diffraction tomography with the Born and Rytov approximations
A new lightweight auto-differentation library that directly builds on numpy. Used as a homework for CMU 11785/11685/11485.
Supporting code for "End-to-end optical backpropagation for training neural networks".
Quantization-aware training with spiking neural networks
Back Propagation, Python
Educational Transformer from scratch (no autograd), with forward and backprop.
Model-based Policy Gradients
Implementation of feedback alignment learning in PyTorch
Multilayer perceptron deep neural network with feedforward and back-propagation for MNIST image classification using NumPy
Minimalistic Multiple Layer Neural Network from Scratch in Python.
yet another scalar autograd engine - featuring complex numbers and fixed DAG
A framework for mini neural networks (perceptrons), written from scratch in python. The goal of the project is to demystify the workings of a neural network and various training algorithms by providing code written from scratch for the simplest neural network one could have.
Add a description, image, and links to the backpropagation topic page so that developers can more easily learn about it.
To associate your repository with the backpropagation topic, visit your repo's landing page and select "manage topics."