Daniel del Castillo's repositories
ai-safety-gridworlds
This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
auto-news-rss-to-tts-podcast
Automatically converts text RSS news feeds into audio files through TTS engines; from them it creates a podcast RSS feed that can be imported (through its integrated web server) into any podcast app!
Awesome-Inverse-Reinforcement-Learning
Literature and code for inverse reinforcement leanring research
faiss
A library for efficient similarity search and clustering of dense vectors.
GANGogh
Using GANs to create Art
Inverse-Reinforcement-Learning
Implementations of selected inverse reinforcement learning algorithms.
jibjib-model
Machine learning model for bird songs recognition
lets-do-irl
Inverse RL algorithms (APP, MaxEnt, GAIL, VAIL)
libfreenect
Drivers and libraries for the Xbox Kinect device on WIndows, Linux, and OS X
LSenTiMent
A sentence-level LSTM baseline model for Sentiment Analysis
mad-twinnet
The code for the MaD TwinNet. Demo page:
Minecraft
Simple Minecraft-inspired program using Python and Pyglet
myMusicBender
A Real-Time gestual interface for musical expression
pg-is-all-you-need
Policy Gradient is all you need! A step-by-step tutorial for well-known PG methods.
pytorch-rl
This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch
samplernn-pytorch
PyTorch implementation of SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
small-text
Active Learning for Text Classification in Python
spleeter
Deezer source separation library including pretrained models.
tensorflow-recommendation-wals
An end-to-end solution for website article recommendations based on Google Analytics data. Uses WALS matrix-factorization in TensorFlow, trained on Cloud ML Engine. Recommendations served with App Engine Flex and Cloud Endpoints. Orchestration is performed using Airflow on Cloud Composer. See the solution tutorials at:
TruthfulQA
TruthfulQA: Measuring How Models Imitate Human Falsehoods
VocalSeparation
Using Deep Learning for singing voice separation - Project for the course DT2119 Speech and Speaker Recognition offered by KTH in 2018