GitHub / msmrexe / numpy-neural-network
A scratch-built NumPy implementation of a Fully Connected Neural Network, with a sequential model API, a variety of layers (Linear, ReLU, BatchNorm), loss functions (MSE, SoftmaxCrossEntropy), and a robust training `Solver` to create and train multi-layer perceptrons for both classification and regression.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msmrexe%2Fnumpy-neural-network
PURL: pkg:github/msmrexe/numpy-neural-network
Stars: 1
Forks: 0
Open issues: 0
License: mit
Language: Python
Size: 51.8 KB
Dependencies parsed at: Pending
Created at: 3 days ago
Updated at: 3 days ago
Pushed at: 3 days ago
Last synced at: 3 days ago
Topics: backpropagation, batch-normalization, course-project, deep-learning, fully-connected-neural-network, neural-networks, nn-from-scratch, numpy, python, university-project