Deep learning

Two researchers show that for neural networks to be able to remember better, they need far more parameters than previously thought.

By using hypernetworks, researchers can now preemptively fine-tune artificial neural networks, saving some of the time and expense of training.

It’s simple enough for AI to seem to comprehend data, but devising a true test of a machine’s knowledge has proved difficult.

Tiny amounts of artificial noise can fool neural networks, but not humans. Some researchers are looking to neuroscience for a fix.

A new model of learning centers on bursts of neural activity that act as teaching signals — approximating backpropagation, the algorithm behind learning in AI.

To help them explain the shocking success of deep neural networks, researchers are turning to older but better-understood models of machine learning.

Computational neuroscientists taught an artificial neural network to imitate a biological neuron. The result offers a new way to think about the complexity of single brain cells.

Melanie Mitchell has worked on digital minds for decades. She says they’ll never truly be like ours until they can make analogies.

For all their triumphs, AI systems can’t seem to generalize the concepts of “same” and “different.” Without that, researchers worry, the quest to create truly intelligent machines may be hopeless.