gokadin/ai-backpropagation
The backpropagation algorithm explained and demonstrated.
This project explains and demonstrates the backpropagation algorithm, a core technique for training neural networks with at least one hidden layer. It takes raw input data and, through a forward pass, produces an output. Then, by calculating the error between the predicted and actual output, it adjusts the network's internal 'weights' in a backward pass to improve accuracy. This is ideal for students, researchers, or anyone seeking a deep theoretical and practical understanding of how neural networks learn.
No commits in the last 6 months.
Use this if you need to understand the fundamental mechanics of how multi-layered neural networks learn from data.
Not ideal if you're looking for a high-level tool to simply apply neural networks without diving into the underlying mathematical principles.
Stars
23
Forks
4
Language
Go
License
—
Category
Last pushed
Feb 14, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gokadin/ai-backpropagation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
digantamisra98/Mish
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
Sentdex/nnfs_book
Sample code from the Neural Networks from Scratch book.
itdxer/neupy
NeuPy is a Tensorflow based python library for prototyping and building neural networks
vzhou842/cnn-from-scratch
A Convolutional Neural Network implemented from scratch (using only numpy) in Python.
nicklashansen/rnn_lstm_from_scratch
How to build RNNs and LSTMs from scratch with NumPy.