jiwoongim Goto Github PK

alphago-zero-gobang

Meta-Zeta is a Gobang model based on reinforcement learning. It is mainly used to understand the demo of the operating principle of AlphaGo Zero, that is, how the neural network guides MCTS to make decisions, and how to learn by itself. Source code + tutorial

appagent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

avb-pytorch-

Adversarial Variational Bayes

baller2vec

A multi-entity Transformer for multi-agent spatiotemporal modeling.

bitstamp-python-client

Python package to communicate with bitstamp.net

causal-inference-tutorial

ccml

char-rnn

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

conservative_autoencoder

crypto_alert

Cryptocurrency Pump & Dump, Trading Signal alert

dcgan_code

Deep Convolutional Generative Adversarial Networks

diwae-pytorch-

Denoising Importance Weighted Autoencoder

dotfiles

dtp

dvae

dvae-pytorch-

Denoising Variational Autoencoder

ft-sne

f-divergence based t-SNE

geco

Gnosis Ecosystem Fund

gemini-python

A python client for the Gemini API and Websocket

gran

imsml

jiwoongim.github.io

minimum_probability_flow_learning

For more information, see http://arxiv.org/abs/1412.6617

ml_demo

Demo for ML tools

oho

Online Hyperparameter Optimization

old_ml_scrap

tensorflow

Computation using data flow graphs for scalable machine learning

uoro-demo