MICrONS

MACHINE INTELLIGENCE FROM CORTICAL NETWORKS
MICrONS

Intelligence Value

The human brain has the remarkable ability to learn patterns from small amounts of data and then recognize novel instances of those patterns despite distortion and noise. Although advances in machine learning algorithms have been weakly informed by the brain since the 1940’s, they do not yet rival human performance.

The MICrONS program aims to close the performance gap between human analysts and automated pattern recognition systems by reverse-engineering the algorithms of the brain.

Summary

MICrONS seeks to close this performance gap by reverse-engineering the algorithms of the brain. The research is leveraging the latest generation of brain mapping tools to reveal and exploit the structure and function of cortical circuits. This will allow the design of algorithms based on biologically inspired data representations, transformations, and learning rules. These algorithms are expected to achieve human-like performance on challenging inference tasks. This will be achieved by using sparse data that allows automated recognition of objects in imagery, even when few training examples exist, or when the objects appear different enough from the training examples that a human would have to infer their similarity. In mid-2019, MICrONS demonstrated the first proof-of-concept that a neurally informed algorithm can outperform the state of the art.

MICrONS has assembled the largest (multi-petabyte) extant dataset of co-registered neurophysiological and neuroanatomical data from the mammalian brain, spanning 1 mm3 and encompassing 100,000 neurons. Performers have densely mapped synaptic connectivity in this imaging volume and are studying how network structure constrains function. At the conclusion of the program, performers will deliver pattern recognition algorithms informed by neuroscience that are expected to meet or exceed human performance on challenging visual scene analysis problems.

Related Article(s)

An automated pipeline for understanding how the brain is wired

Johns Hopkins APL and University Students Join Forces to Map the Brain

Inside the Moonshot Effort to Finally Figure Out the Brain

The Boss: A Petascale Database for Large-Scale Neuroscience Powered by Serverless Technologies

IARPA Project Targets Hidden Algorithms for the Brain

ReadCoor Joins The Wyss Institute’s IARPA MICrONS Brain Mapping Consortium

Artificial intelligence project could yield clues about autism

Mapping the Brain to Build Better Machines

IARPA awards $18.7M contract to Allen Institute to reconstruct neuronal connections

US Bets $100 Million on Machines That Think More Like Humans

Unlocking the secrets of the brain's intelligence to develop smarter technologies

Allen Institute for Brain Science receives $18.7M to help reconstruct the complex wiring of the brain

Allen Institute joins in IARPA’s massive MICrONS project to create a tiny bit of virtual brain tissue

Research on mouse's brain could lead to smarter machines

The U.S. Government Launches a $100-Million "Apollo Project of the Brain"

IARPA Wants Smarter Algorithms -- Not More of Them

AWS Public Sector Blog: The Boss: A Petascale Database for Large-Scale Neuroscience Powered by Serverless Technologies

IEEE Spectrum: AI Designers Find Inspiration in Rat Brains

Harvard Gazette: An open-source AI tool for studying movement across behaviors and species

BrainFacts.org: Teasing Out the Mysteries of the Brain to Enhance Artificial Intelligence

Popular Mechanics: The Heroes of Science Who Are Unlocking the Brain

BrainInitiative.org: The BRAIN Initiative® Pioneers the Future through Open Science Technology

Cold Spring Harbor Laboratory News Release: Diagramming the brain with colorful connections

Open Access Government: Next Generation Sequencing: The analysis of synthetic biology signatures in brain tissue

Related Publications

To access MICrONS program-related publications, please visit Google Scholar.


Contact Information

Program Manager

Dr. David Markowitz

Contracting Office Address

Office of the Director of National Intelligence

Intelligence Advanced Research Projects Activity

Washington, DC 20511

Research Area(s)

Computational neuroscience, Machine learning , Neurophysiology, Connectomics, Data Science

Related Program(s)

Broad Agency Announcement (BAA)

Link(s) to BAA

IARPA-BAA-14-06

Solicitation Status

CLOSED

Proposers' Day Date

July 17, 2014

BAA Release Date

January 8, 2015

BAA Question Period

January 8, 2015 — February 9, 2015

Proposal Due Date

Friday, 13 March 2015

Program Summary

Testing and Evaluation Partners

  • Sandia National Laboratories
  • Johns Hopkins University Applied Physics Laboratory

Prime Performers

  • Baylor College of Medicine
  • Allen Institute for Brain Science
  • Princeton University