dream-faster Goto Github PK

.github

This is a repo for our public profile.

applied-exploration.github.io

🗞 Official Newsletter. Take a journey with us creating a next-gen Machine Learning Research Studio. Deep insights into projects translating state-of-the-art algorithms into practical use-cases. Occasional opinion pieces on on the state of the ML community and tooling.

arfs

All Relevant Feature Selection, with Time Series CV

benchmarks

📐 Time series Benchmarks ran on public Datasets with Fold and Krisi across multiple domains.

datasets

Example dataset for the walkthroughs and examples of Dream Faster's libraries

finml-utils

Utility functions of all of our Financial Machine Learning projects

fold

🪁 A fast Adaptive Machine Learning library for Time-Series, that lets you build, deploy and update composite models easily. An order of magnitude speed-up, combined with flexibility and rigour. This is an internal project - documentation is not updated anymore and substantially differ from the current API.

fold-models

⚙️ Speedy implementations of TS Models, built specifically for Fold (https://github.com/dream-faster/fold)

fold-wrappers

🧱 Wrappers for 3rd party models to be used with fold (https://github.com/dream-faster/fold)

krisi

⏳ Evaluation of Time-Series Predictions with powerful pdf and web Reporting. Tailored for evaluation of metrics over time!

laplace-gnn-recommendation

⛓️ laplace is an end-to-end ML framework to train and predict on neurally-enhanced graphs for recommendation. The pipeline is designed for self-supervised edge prediction on heterogenous graphs.

licenseheaders

Simple python script to add/replace license headers in a directory tree of source files

modular-pipelines

🐾 A lightweight & extensible library to create complex multi-model and multi-modal pipelines, including ``Ensembles`` and ``Meta-Models``

research-hate-speech-api

🎙 Hate-speech detection Demo API built with Modular Pipelines: https://github.com/applied-exploration/modular-pipelines

research-multi-drl

↺ Environment to test system level convergence of local decision making by Deep Reinforcement Learning Agents (DDPG)

research-neural-symbolic-regression