Miguel Angel Mancheño's Projects
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
Bringing Characters to Life with Computer Brains in Unity
Self-study on Larry Wasserman's "All of Statistics"
Solutions for All of Statistics by Wasserman
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
🔊 Text-Prompted Generative Audio Model
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Creator for making CYOA adventures for Spectrum +3
Couchbase on Kubernetes
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Image restoration with neural networks but without learning.
Udacity's Deep Learning Nano Foundation program.
Deeplearning4j, ND4J, DataVec and more - deep learning & linear algebra for Java/Scala with GPUs + Spark - From Skymind
Modularized Implementation of Deep RL Algorithms in PyTorch
Code for the paper Music Source Separation in the Waveform Domain
The state-of-the-art in multi-agent Reinforcement Learning is the MADDPG algorithm which utilises DDPG actor-critic neural networks where each agent uses centralized critic training but decentralized actor execution, and is capable of learning either cooperative or competitive environments. This is demonstrated on the Unity Tennis Environment.
Lua/Torch implementation of DQN (Nature, 2015)
Official Code for DragGAN (SIGGRAPH 2023)
elastic stack with a couple of microservices alongside
Deploys the elastic stack on k8s using terraform. Showcases elastic stack 6.8.0 features
Online decorrelation of humidity and temperature in chemical sensors for continuous monitoring
A MNIST-like fashion product database. Benchmark :point_down:
Demo application for the 'Jenkins: The Definitive Guide' book
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
The official gpt4free repository | various collection of powerful language models
A toolkit for developing and comparing reinforcement learning algorithms.
Kubernetes Helm Charts and Tools to run Elastic Stack(ELK) on Azure Container Service(AKS)