LaunchPlatform/marketplace
Marketplace ML experiment - training without backprop
This project offers an experimental way for machine learning developers to train models without relying on traditional backpropagation. It processes model layers in groups, testing various parameter combinations and then refining the best ones. The primary users are machine learning engineers and researchers looking for alternative, potentially more efficient training methods on GPUs.
No commits in the last 6 months.
Use this if you are a machine learning developer interested in exploring novel, non-backpropagation-based training algorithms that might offer efficiency gains on GPU.
Not ideal if you are a practitioner looking for a stable, production-ready machine learning framework or if you are unfamiliar with deep learning internals.
Stars
27
Forks
5
Language
Python
License
MIT
Category
Last pushed
Sep 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LaunchPlatform/marketplace"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
quantylab/rltrader
파이썬과 케라스를 이용한 딥러닝/강화학습 주식투자 - 퀀트 투자, 알고리즘 트레이딩을 위한 최첨단 해법 입문 (개정판)
matlab-deep-learning/reinforcement_learning_financial_trading
MATLAB example on how to use Reinforcement Learning for developing a financial trading model
erhardtconsulting/tensortrade-ng
TensorTrade-NG is an open source Python framework for building, training, evaluating, and...
TradeMaster-NTU/TradeMaster
TradeMaster is an open-source platform for quantitative trading empowered by reinforcement...
LeonardoBerti00/DeepMarket
DeepMarket is a framework for performing Limit Order Book simulation with Deep Learning. This is...