Aaron Hosford's repositories
interpret
Fit interpretable models. Explain blackbox machine learning.
hosford42.github.io
Personal front page
PheKnowLator
PheKnowLator: Heterogeneous Biomedical Knowledge Graphs and Benchmarks Constructed Under Alternative Semantic Models
LNB
Less Naive Bayes
JSONConfig
Framework for JSON serialization/deserialization of arbitrary Python objects
VectorFace
Vector interface library for convenient backend swapping and library interoperability
awesome-rag
A curated list of retrieval-augmented generation (RAG) in large language models
UBINotebook
A notebook and articles on the advantages of Universal Basic Income
xcsf
XCSF learning classifier system: rule-based online evolutionary machine learning
LCS-From-Scratch
Learning Classifier Systems from Scratch
evennia
Python MUD/MUX/MUSH/MU* development system
XCS-IMG
XCS-IMG is the adaptation of accuracy based learning classifier system (XCS) for images supporting visualization of learned features.
DeepSpeech
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
gym
A toolkit for developing and comparing reinforcement learning algorithms.
ProMP
ProMP: Proximal Meta-Policy Search
Sophia
Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
rasa_core
machine learning based dialogue engine for conversational software
TensorFlowUtilities
Assorted useful tensorflow functions and keras layers
Flask-SocketIO-Chat
A simple chat application that demonstrates how to structure a Flask-SocketIO application.
torchhd
Torchhd is a Python library for Hyperdimensional Computing and Vector Symbolic Architectures
popgym
Partially Observable Process Gym
logotron
Maybe someday a bot that runs Logo programs and shares the result as a video
RustPython
A Python Interpreter written in Rust
antioch
A next-generation MUD/MOO-like virtual world engine in Python
PPO
Reinforcement Learning
dreamer
Dream to Control: Learning Behaviors by Latent Imagination
ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.