training-algorithms

There are 0 repository under training-algorithms topic.

evanbernard / MiniNeuralNets
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.
neural-network backpropagation genetic-algorithm perceptrons weight-adjustment training-algorithms
Language:Python 21
Emperor-WS / PyEmber
An Educational Framework Based on PyTorch for Deep Learning Education and Exploration
adam-optimizer artificial-intelligence autograd backpropagation convolutional-neural-networks cupy deep-learning deep-learning-framework deep-learning-library deep-neural-networks feedforward-neural-network genetic-algorithm gradient-descent neural-network numpy optimizer perceptrons python pytorch training-algorithms
Language:Python 10
GishB / GeneralAlgorithms
Personal algorithmic task solutions saved from platforms like Yandex.Context, CodeWars and Karpov.Courses / Решене олимпиадных задач на платформе Яндекс.Контекст, CodeWars, Karpov.Courses
algorithm-challenges training-algorithms
Language:Jupyter Notebook 3
ATHAANGGORO10 / BearPython
python-script create-games pygame training-algorithms
Language:Python 2
ATHAANGGORO10 / ShowingFace
create-showingface python-script library-venv training-algorithms
Language:Python 2
bharathsudharsan / ECML-Tutorial-ML-Meets-IoT
Repository of the ECML PKDD 2021 tutorial title 'Machine Learning Meets Internet of Things: From Theory to Practice'
tinyml edge-computing iot-devices self-learning optimization training-algorithms efficient-inference machine-learning arm-cortex-m4 arm-cortex-m0 quantization pruning tflite graph-optimization cmsis-nn
Language:Jupyter Notebook 1
laat
davor10105 / laat
Use LLMs as training regularizers for small, differentiable models and significantly improve their generalization ability when trained on few-shot and skewed datasets.
ai large-language-models tabular-data training-algorithms few-shot-learning
Language:Python 1
fxckillua / random-training-algorithm
Implementação de um algoritmo de treinamento aleatório para redes neurais. Este projeto explora abordagens alternativas para otimização de modelos em aprendizado de máquina.
artificial-intelligence artificial-intelligence-algorithms cpp deep-learning machine-learning machine-learning-algorithms model-optimization neural-networks open-source random-algorithm random-algorithms training-algorithm training-algorithms
Language:C++ 0
arashsajjadi / Stockfish-DQN-Agent
♟️ Optimized Chess RL Trainer using DQN vs Stockfish. Built with PyTorch and python-chess, it learns using per-move rewards from Stockfish evaluations. Implements Prioritized Experience Replay (PER) and parallel CPU/GPU execution for faster training. The agent dynamically adjusts Stockfish skill level based on performance.
artificial-intelligence chess-engine deep-learning dqn dqn-pytorch pytorch reinforcement-learning stockfish training-algorithms rl-machine-learning
Language:Python
CJHJ / pfn-intern-ml-task-2019
My take on PFN Internship ML Task 2019
adam evaluation graphs numpy reproduction training-algorithms
Language:Python

training-algorithms

evanbernard / MiniNeuralNets

Emperor-WS / PyEmber

GishB / GeneralAlgorithms

ATHAANGGORO10 / BearPython

ATHAANGGORO10 / ShowingFace

bharathsudharsan / ECML-Tutorial-ML-Meets-IoT

davor10105 / laat

fxckillua / random-training-algorithm

arashsajjadi / Stockfish-DQN-Agent

CJHJ / pfn-intern-ml-task-2019