amassivek/signalpropagation
Forward Pass Learning and Inference Library, for neural networks and general intelligence, Signal Propagation (sigprop)
This is a Python package for machine learning engineers and researchers to train neural networks more efficiently. It allows you to train different parts of a neural network (or other parameterized models) in a continuous and asynchronous way, using the same computational pass for both training and making predictions. This helps streamline the development and deployment of complex AI models, especially for applications requiring ongoing learning or running on specialized hardware.
No commits in the last 6 months.
Use this if you are a machine learning engineer building and deploying neural networks that need to learn continuously, asynchronously, or in parallel, especially on diverse hardware like neuromorphic chips or edge devices.
Not ideal if you are a data scientist primarily using off-the-shelf models or focusing on traditional batch training methods for standard machine learning tasks.
Stars
57
Forks
8
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/amassivek/signalpropagation"
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.