Neuroscience × Machine Intelligence

The brain doesn't
just compute.
It predicts.

Cortical Learning is the study of how the neocortex learns, remembers, and understands the world through sparse, predictive representations. Open research. Open source. Open minds.

6
LAYERS OF NEOCORTEX
100ms
PREDICTION CYCLE
~10¹¹
NEURONS IN HUMAN CORTEX
SCROLL TO DISCOVER
EST. 2026

Cortical Learning is how the brain really works.

Inspired by the groundbreaking work of Jeff Hawkins and Numenta, this platform is the open home for research, implementations, and discussion around the neocortex's learning algorithms.

Join 4,872 researchers & engineers
exploring intelligence from first principles

Not just another neural net

Modern deep learning is powerful but fundamentally different from biology. Cortical Learning studies the actual mechanisms the neocortex uses: sparse distributed representations, continuous online learning, and prediction at every level.

01
Hierarchical Temporal Memory
A biologically plausible model of the neocortex that learns sequences and makes predictions in real time.
02
Thousand Brains Theory
Every cortical column builds complete models of objects using reference frames.
03
Cortical Learning Algorithm (CLA)
The original name for HTM's core learning mechanism — still the foundation of modern work.
Core Concepts

How the cortex learns

Sparse Distributed Representations (SDR)

Only ~2% of neurons fire at any time. This sparsity creates robust, high-capacity memory that is fault-tolerant and energy efficient.

BIOLOGICAL
COMPUTATIONAL

Temporal Memory & Prediction

The cortex constantly predicts the next input. When predictions match reality, learning is minimal. When they don't, the brain updates its model.

THE HEART OF INTELLIGENCE

Reference Frames in Columns

Each cortical column maintains a model of the world from its own perspective. Thousands of columns vote to create unified perception.

Cortical columns diagram
Peer-reviewed & Open

Featured Research

Browse full library

From theory to real-world intelligence

Cortical principles are already powering next-generation systems in anomaly detection, robotics, and autonomous agents that learn continuously without catastrophic forgetting.

01
Continuous Learning Systems
Never forget what you learned yesterday
02
Robust Anomaly Detection
Used in production at thousands of companies
03
Sensorimotor Intelligence
Robots that understand their world like animals
04
Explainable AI
Every prediction comes with a clear model

Free Resources & Tools

HTM School Video Series

The best visual introduction to Hierarchical Temporal Memory. 20+ free episodes.

Watch the series

Open Source Implementations

Python, C++, Rust, JavaScript — production-ready HTM libraries maintained by the community.

Explore repos

Community Forums & Discord

Discuss papers, share experiments, and collaborate with researchers worldwide.

Monthly digest • New papers • Code drops • Events

Stay at the frontier of cortical intelligence

Get the latest research summaries, open-source releases, and community calls delivered to your inbox. Zero spam.

We respect your inbox as much as we respect the neocortex.