karlhigley
I build recommender systems. I'm into ML, cross-functional teams, and iterative software development.
New York, NY
Pinned Repositories
poprox-recommender
This repository contains the POPROX recommender code — the end-to-end logic for producing recommendations using article data, user histories and profiles, and trained models.
calibrator
An implementation of Harald Steck's Calibrated Recommendations approach to re-ranking
latus
Nearest neighbor search with integrated filtering
lexrank-summarizer
A Spark-based LexRank extractive summarizer for text documents
practicalrecs-examples
Example code for practicalrecs.com blog posts
ranking-metrics-torch
Simple ranking metrics for PyTorch on CPU or GPU
spark-neighbors
Spark-based approximate nearest neighbor search using locality-sensitive hashing
torch-optim-sparse
PyTorch optimizers with sparse momentum and weight decay
NVTabular
NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.
systems
Merlin Systems provides tools for combining recommendation models with other elements of production recommender systems (like feature stores, nearest neighbor search, and exploration strategies) into end-to-end recommendation pipelines that can be served with Triton Inference Server.
karlhigley's Repositories
karlhigley/ranking-metrics-torch
Simple ranking metrics for PyTorch on CPU or GPU
karlhigley/torch-optim-sparse
PyTorch optimizers with sparse momentum and weight decay
karlhigley/practicalrecs-examples
Example code for practicalrecs.com blog posts
karlhigley/latus
Nearest neighbor search with integrated filtering
karlhigley/torch-factorization-models
Factorization-based models for recommender systems with PyTorch
karlhigley/py-pkg-template
A template for Python packages with poetry, pytest, Black, flake8, pylint, and pre-commit hooks
karlhigley/recommender_datasets
A common format and repository for various recommender datasets.
karlhigley/tensorflow
An Open Source Machine Learning Framework for Everyone
karlhigley/conda
OS-agnostic, system-level binary package manager and ecosystem
karlhigley/core
Core Utilities for NVIDIA Merlin
karlhigley/dataloader
The merlin dataloader lets you rapidly load tabular data for training deep leaning models with TensorFlow, PyTorch or JAX
karlhigley/DeepMatch
A deep matching model library for recommendations & advertising. It's easy to train models and to export representation vectors which can be used for ANN search.
karlhigley/docs
Milvus web documents and contents
karlhigley/feast
Feature Store for Machine Learning
karlhigley/janusgraph-movielens
An ETL pipeline to augment the Movielens dataset and ingest it into Janusgraph
karlhigley/keras
Deep Learning for humans
karlhigley/milvus
An open source vector database powered by Faiss, NMSLIB and Annoy
karlhigley/models
Merlin Models is a collection of deep learning recommender system model reference implementations
karlhigley/mtg
Collection of data science and machine learning projects for Magic: the Gathering
karlhigley/NVTabular
NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.
karlhigley/PySyft
A library for encrypted, privacy preserving deep learning
karlhigley/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
karlhigley/readme-md-rst-test
karlhigley/recodex
karlhigley/syft-proto
The JSON proto file which defines types for all Serde encoding across languages
karlhigley/systems
Merlin Systems provides tools for combining recommendation models with other elements of production recommender systems (like feature stores, nearest neighbor search, and exploration strategies) into end-to-end recommendation pipelines that can be served with Triton Inference Server.
karlhigley/Transformers4Rec
Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation, available for both PyTorch and Tensorflow.
karlhigley/triton-inference-core
The core library and APIs implementing the Triton Inference Server.
karlhigley/triton-inference-server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
karlhigley/witchhunt
A Python library for Approximate Nearest Necromancer (ANN) search