IntroDLPython
TicTacToe
IntroDLPython | TicTacToe | |
---|---|---|
1 | 3 | |
31 | 3 | |
- | - | |
1.2 | 2.0 | |
about 1 year ago | 9 months ago | |
Python | Python | |
- | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
IntroDLPython
-
A Comprehensive Guide to the Backpropagation Algorithm in Neural Networks
Also, we’ll discuss how to implement a backpropagation neural network in Python from scratch using NumPy, based on this GitHub project. The project builds a generic backpropagation neural network that can work with any architecture.
TicTacToe
-
Neural networks fundamentals with Python – a guide to implementing your first neural network from scratch
I have a similar ML library for a generic NN made from scratch, with many parameters to customize it, I just finished it last week, I also mostly based myself in the 3b1b videos.
-
I created an AI for Super Hexagon based on Distributional RL. And I dare to call it superhuman :D
Also, does this have a particular reason? I've seen this in GAE-implementations but never for DQL.
-
HELP! Stuck with a reinforcement learning experiment.
I built a general purpose basic ML library that creates a Neural Network (only DENSE layers), saves and loads the weights into a file, does forward propagation and training (optimization of weights and biases) using SGD (code here). I tested the ML library with the XOR problem to make sure it worked fine (code here).
What are some alternatives?
DeepNeuralNetworksFromScratch - Different kinds of deep neural networks (DNNs) implemented from scratch using Python and NumPy, with a TensorFlow-like object-oriented API.
Connect-4 - Connect 4 is a token game created with Python and module Numpy. Place 4 tokens in a row (vertically, horizontally, or diagonally) before your opponent wins. Single-player against Artificial Intelligence and multiplayer also available.
DiffMorph - Image morphing without reference points by applying warp maps and optimizing over them.
Tic-Tac-Toe - Tic-Tac-Toe in terminal
robo-vln - Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"
AI.NeuralNetwork - Neural Network
Neupy - NeuPy is a Tensorflow based python library for prototyping and building neural networks
TensorLayer - Deep Learning and Reinforcement Learning Library for Scientists and Engineers
MAGIST-Algorithm - Multi-Agent Generally Intelligent Simultaneous Training Algorithm for Project Zeta
py-Tic-Tac-Toe - An implementation of Tic Tac Toe in the console, with AI opponents.
neuro-symbolic-sudoku-solver - ⚙️ Solving sudoku using Deep Reinforcement learning in combination with powerful symbolic representations.
boardgame2 - Extension of OpenAI Gym that implements multiple two-player zero-sum 2-dimension board games