How do I set up Clortex for a basic demo?

Since Clortex is pre-alpha, start by checking the documentation on Fergal Byrne's blog and the GitHub project, but be prepared for unstable setup processes and consider contributing rather than relying on it for stable demos.

What's the main difference between Clortex and Numenta's NuPIC?

Clortex is a modern reimplementation of NuPIC using updated software techniques, while NuPIC is the original, more mature platform. Clortex aims to be more accessible but is still in early development compared to NuPIC's stability.

Is Clortex good for anomaly detection in time series data?

HTM theory excels at temporal data tasks like anomaly detection, and Clortex implements the Cortical Learning Algorithm for this. However, its pre-alpha status means you may encounter bugs and lack of polished examples.

Can I use Clortex in a closed-source commercial product?

No, because Clortex is licensed under GPLv3, which requires derivative works to be open source. For proprietary use, you'd need to seek alternative licensing or use NuPIC's dual-license options.

How does HTM in Clortex compare to deep learning frameworks like TensorFlow?

HTM is brain-inspired and specializes in temporal pattern recognition with less data, while deep learning is more versatile but data-hungry. Clortex offers a unique approach but has far less ecosystem support than TensorFlow.

What programming language is Clortex built with?

Based on the EuroClojure talk and integration with Comportex, Clortex is implemented in Clojure, targeting the JVM ecosystem for brain-inspired intelligence applications.

Open-Awesome

clortex

GPL-3.0Clojure

An open-source implementation of Jeff Hawkins' Hierarchical Temporal Memory and Cortical Learning Algorithm for machine intelligence.

Visit Website GitHub

182 stars18 forks0 contributors

What is clortex?

Clortex is an open-source implementation of Jeff Hawkins' Hierarchical Temporal Memory (HTM) and Cortical Learning Algorithm (CLA) for building machine intelligence systems. It reimagines and reimplements the Numenta Platform for Intelligent Computing (NuPIC) with modern software development approaches. The project aims to create brain-inspired intelligent systems that can solve real-world problems.

Target Audience

Researchers, developers, and entrepreneurs interested in brain-inspired machine intelligence and those working with or looking for alternatives to Numenta's NuPIC platform.

Value Proposition

Clortex offers an open-source, GPLv3 licensed alternative to NuPIC with a modern implementation approach, building upon eight years of NuPIC research while applying contemporary software development techniques to make brain-inspired intelligence more accessible.

Overview

(pre-alpha) Implementation of Jeff Hawkins' Hierarchical Temporal Memory & Cortical Learning Algorithm

Use Cases

Best For

Implementing Hierarchical Temporal Memory theory in practical applications
Building brain-inspired machine intelligence systems
Researching cortical learning algorithms and neural computation
Developing alternatives to Numenta's NuPIC platform
Creating intelligent systems based on neuroscience principles
Exploring open-source implementations of HTM/CLA technology

Not Ideal For

Production systems requiring stable, versioned APIs and long-term support
Teams without prior expertise in Hierarchical Temporal Memory theory or cortical learning algorithms
Commercial projects needing permissive licensing for proprietary redistribution
Applications demanding immediate, out-of-the-box machine learning with extensive tutorials

Pros & Cons

Pros

Neuroscience-Based Intelligence

Implements Jeff Hawkins' HTM and CLA, offering a brain-inspired alternative to traditional AI, as emphasized in the project's philosophy of building systems based on human brain principles.

Modern Reimplementation

Applies contemporary software development techniques to NuPIC's foundation, potentially improving code quality and accessibility compared to the original platform.

Strong Research Heritage

Builds on eight years of NuPIC research and development, ensuring alignment with established HTM theory and leveraging a mature community, as noted in the description.

Open Source Collaboration

Released under GPLv3 and integrated with the NuPIC community and sister project Comportex, fostering open development and knowledge sharing.

Cons

Unstable Pre-Alpha State

Explicitly warned as pre-alpha with APIs subject to drastic change without notice, making it unreliable for any serious or production development.

Incomplete Architecture

Currently being repositioned with Comportex for core algorithms, leading to uncertainty in design and delayed release-worthy code, as admitted in the README.

Sparse Documentation

Documentation is hosted on personal blogs and GitHub pages, with no comprehensive guides, hindering onboarding and practical use despite the project's ambitions.

Open Source Alternative To

clortex is an open-source alternative to the following products:

Numenta Platform for Intelligent Computing (NuPIC)

Frequently Asked Questions

Related Projects

PyTorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Stars101,899

Forks28,473

Last commit15 hours ago

keras

Deep Learning for humans

Streamlit — A faster way to build and share data apps.

Stars45,326

Forks4,331

Last commit20 hours ago

gradio

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

Stars43,191

Forks3,557

Last commit18 hours ago

Community-curated · Updated weekly · 100% open source

Found a gem we're missing?

Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.

Submit a project Star on GitHub