Sign In

Communications of the ACM

ACM Opinion

Can Neural Networks Learn Better than Human Neurons?

View as: Print Mobile App Share:
Neural network concept illustrated.

Many engineers think that, with enough computer power and fancy tweaks, neural networks will become as smart as people.

Credit: Adobe Stock.

The modern neural network is a better learning algorithm than the brain. The brain neuron is limited by an all-or-nothing principle that makes rapid learning impossible.

By contrast, the differentiable "hotter" or "colder" function used by neural networks enables programmers to algorithmically train networks with trillions of parameters. Which raises the question: What if the human mind can learn better than a neural network?

From Mind Matters News
View Full Article


No entries found

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