#25 · Primary category： Time Series Machine Learning
nupic-legacy
Numenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strictly on the neuroscience of the neocortex.
Project last updated：12/03/24
GitHub Stars
6.3K
Forks
1.5K
Contributors
126
License
MIT
Why we included this project
Few projects make Hierarchical Temporal Memory approachable enough to try, and NuPIC is one of them. It implements Numenta's theory of neocortical learning as a time-based sequence model that keeps adapting online, which suits anomaly detection and next-value prediction on streaming feeds like sensor telemetry or server metrics. The catch: the codebase has sat in maintenance mode for years, still lists Python 2.7 as a dependency, and is not the current platform. Think of it as a research-grade reference for exploring a different neural-inspired paradigm, not something to build on today.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
netdata
The fastest path to AI-powered full stack observability, even for lean teams.
catboost
A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
sktime
A unified framework for machine learning with time series
darts
A python library for user-friendly forecasting and anomaly detection on time series.
featuretools
An open source python library for automated feature engineering