thousandbrainsproject/tbp.monty

Monty is a sensorimotor learning framework based on the thousand brains theory of the neocortex.

What it solves

Monty provides a way to implement sensorimotor learning, moving away from traditional deep learning toward a system that mimics the functional organization of the neocortex to achieve more rapid and robust learning and inference.

How it works

It is an implementation of the Thousand Brains Project's theory of intelligence, which treats cortical columns as repeating functional units. The system focuses on sensorimotor intelligence, integrating sensory input with motor movement to learn about the environment.

Who it’s for

Researchers and developers interested in neuroscience-inspired AI, sensorimotor learning, and alternatives to standard deep learning architectures.

Highlights

  • Based on the principles of the neocortex and cortical columns.
  • Open-source implementation of the Thousand Brains Project.
  • Regularly evaluated against a set of sensorimotor benchmark tasks.
  • Designed for rapid and robust learning and inference.

Related

  • Project
    Project-MONAI/MONAI

    A PyTorch-based open-source framework for deep learning in healthcare imaging that provides standardized workflows and domain-specific tools for medical data.

  • Project
    fastai/fastai

    A deep learning library built on PyTorch that provides high-level components for rapid productivity and low-level components for research flexibility.

  • Project
    scikit-learn/scikit-learn

    A Python module for machine learning built on top of SciPy, providing a wide range of tools and algorithms for ML practitioners.

  • Project
    pyt-team/TopoModelX

    A Python module for building topological neural networks that enables deep learning on topological domains like simplicial complexes for science and engineering.