Tuesday, July 29, 2025
LBNN
  • Business
  • Markets
  • Politics
  • Crypto
  • Finance
  • Energy
  • Technology
  • Taxes
  • Creator Economy
  • Wealth Management
  • Documentaries
No Result
View All Result
LBNN

Data from macaque monkeys reveals flaws in deep neural networks

Simon Osuji by Simon Osuji
January 9, 2025
in Artificial Intelligence
0
Data from macaque monkeys reveals flaws in deep neural networks
0
SHARES
0
VIEWS
Share on FacebookShare on Twitter


Evaluating how brains generalize
Deep neural network-based models of the visual cortex employ a linear model to map image features extracted from pre-trained networks to neuronal responses from the macaque IT cortex. Credit: Harvard John A. Paulson School of Engineering and Applied Sciences

Among the marvels of the human brain is its ability to generalize. We see an object, like a chair, and we know it’s a chair, even when it’s a slightly different shape, or it’s found in an unexpected place or in a dimly lit environment.

Related posts

Scientists use AI-powered robot to assemble cyborg insects for use in search and rescue efforts

Scientists use AI-powered robot to assemble cyborg insects for use in search and rescue efforts

July 29, 2025
AI can see clearly now, when it comes to energy storage

AI can see clearly now, when it comes to energy storage

July 28, 2025

Deep neural networks, brain-inspired machines often used to study how actual brains function, are much worse at image generalization than we are. But why? How can such models be improved? And how does the brain generalize so effortlessly? Computer science graduate student Spandan Madan in the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) has long been fascinated by these questions.

In research presented at the Neural Information Processing Systems conference in December, Madan and colleagues used brain data collected from monkeys to show that widely accepted ways of modeling the brain may be fundamentally flawed, particularly when it comes to generalizing across conditions not present in training data. This is known as “out-of-distribution” data. The findings are also published on the arXiv preprint server.

“We showed that if you build a model of the brain, which uses deep neural networks, it works very well for the data you train it on, but the moment you test that data under novel conditions, it doesn’t work well. It breaks down completely,” said Madan, who is co-advised by Hanspeter Pfister, the An Wang Professor of Computer Science at SEAS, and Gabriel Kreiman, HMS Professor of Ophthalmology.

Madan likened this breakdown to Newton’s laws of motion only working for planets, but not for small objects falling off one’s desk. “It’s not a satisfying model of the brain if it cannot generalize,” he said.






Credit: MIT

The interdisciplinary team of researchers, which included co-authors Will Xiao and Professor Margaret Livingstone of HMS, and Mingran Cao of the Francis Crick Institute, investigated how well deep neural networks, trained on brain data from macaque monkeys, could predict neuronal responses to out-of-distribution images.

Showing seven monkeys thousands of images over 109 experimental sessions, the team recorded neural firing rates in the animals’ brains in response to each image. In all, the researchers collected 300,000 image-response pairs, making it one of the largest-ever datasets of neural firing rates.

Madan and team then showed those same images to their model, but they introduced new conditions in the form of things like image contrast, hue, saturation, intensity, and temperature.

The model passed with flying colors on predicting correct neural activity on the familiar data but failed miserably on the unfamiliar data, performing only about 20% as well. In the paper, the researchers describe being able to rate the performance of a model’s generalization with a relatively simple metric, which could then be used as a strong gauge for neural predictivity under different types of data shifts.

The problem of generalization in the field of artificial intelligence has long been known, and the paper is one of the first to show that those problems cross over into neuroscience too, Madan said. “As AI and neuroscience become increasingly intertwined, we hope that this problem also becomes of importance to neuroscience researchers … We hope that we can bring the two fields together and work on this problem together.”

HMS’ Xiao added, “As AI researchers, we must recognize how our tools shape other fields. AI models’ poor generalization to distribution shifts doesn’t just affect practical applications; this study shows it can fundamentally limit our ability to use AI for understanding biological intelligence, highlighting the broader scientific consequences of this well-known AI challenge.”

More information:
Spandan Madan et al, Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex, arXiv (2024). DOI: 10.48550/arxiv.2406.16935

Journal information:
arXiv

Provided by
Harvard John A. Paulson School of Engineering and Applied Sciences

Citation:
Evaluating how brains generalize: Data from macaque monkeys reveals flaws in deep neural networks (2025, January 8)
retrieved 8 January 2025
from https://techxplore.com/news/2025-01-brains-generalize-macaque-monkeys-reveals.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.





Source link

Previous Post

No let-up for soldiers on border protection duty in December

Next Post

On ECCB official administrator for FICS

Next Post
On ECCB official administrator for FICS

On ECCB official administrator for FICS

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

RECOMMENDED NEWS

India & China To Trade With Maldives In Local Currency

India & China To Trade With Maldives In Local Currency

1 year ago
‘Urgent debate’ scheduled to discuss SANDF casualties in the DRC

‘Urgent debate’ scheduled to discuss SANDF casualties in the DRC

6 months ago
US Begins Ground Tests for Collaborative Combat Aircraft Drones

US Begins Ground Tests for Collaborative Combat Aircraft Drones

3 months ago
Former US IRS agent among Binance staff detained in Nigeria

Former US IRS agent among Binance staff detained in Nigeria

1 year ago

POPULAR NEWS

  • Ghana to build three oil refineries, five petrochemical plants in energy sector overhaul

    Ghana to build three oil refineries, five petrochemical plants in energy sector overhaul

    0 shares
    Share 0 Tweet 0
  • The world’s top 10 most valuable car brands in 2025

    0 shares
    Share 0 Tweet 0
  • When Will SHIB Reach $1? Here’s What ChatGPT Says

    0 shares
    Share 0 Tweet 0
  • Top 10 African countries with the highest GDP per capita in 2025

    0 shares
    Share 0 Tweet 0
  • Global ranking of Top 5 smartphone brands in Q3, 2024

    0 shares
    Share 0 Tweet 0
  • Privacy Policy
  • Contact

© 2023 LBNN - All rights reserved.

No Result
View All Result
  • Home
  • Business
  • Politics
  • Markets
  • Crypto
  • Economics
    • Manufacturing
    • Real Estate
    • Infrastructure
  • Finance
  • Energy
  • Creator Economy
  • Wealth Management
  • Taxes
  • Telecoms
  • Military & Defense
  • Careers
  • Technology
  • Artificial Intelligence
  • Investigative journalism
  • Art & Culture
  • Documentaries
  • Quizzes
    • Enneagram quiz
  • Newsletters
    • LBNN Newsletter
    • Divergent Capitalist

© 2023 LBNN - All rights reserved.