Sign In

Communications of the ACM

ACM TechNews

Study Urges Caution When Comparing Neural Networks to the Brain

View as: Print Mobile App Share:
Neural networks are loosely modeled on the organization of the human brain.

Neural networks form the basis of many artificial intelligence systems for applications such as speech recognition, computer vision, and medical image analysis.

Credit: MIT News

A study by Massachusetts Institute of Technology (MIT) researchers revealed the difficulty of comparing neural networks to the brain.

The researchers studied over 11,000 neural networks trained to simulate the function of grid cells (part of the brain's navigation system) and found that very specific constraints not found in biological systems are needed for neural networks to generate grid-cell-like activity.

Researcher Rylan Schaeffer said, "What this suggests is that in order to obtain a result with grid cells, the researchers training the models needed to bake in those results with specific, biologically implausible implementation choices."

The analysis showed that close to 90% of the neural networks successfully learned path integration (a prediction of an animal's next location based on a given starting point and velocity), but grid-cell-like activity patterns were produced by just 10% of the networks.

From MIT News
View Full Article


Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account