What's up in
neural networks
artificial intelligence
AI Researchers Fight Noise by Turning to Biology
Tiny amounts of artificial noise can fool neural networks, but not humans. Some researchers are looking to neuroscience for a fix.
neuroscience
To Be Energy-Efficient, Brains Predict Their Perceptions
Results from neural networks support the idea that brains are “prediction machines” — and that they work that way to conserve energy.
Q&A
Her Machine Learning Tools Pull Insights From Cell Images
The computational biologist Anne Carpenter creates software that brings the power of machine learning to researchers seeking answers in mountains of cell images.
neural networks
Neuron Bursts Can Mimic Famous AI Learning Strategy
A new model of learning centers on bursts of neural activity that act as teaching signals — approximating backpropagation, the algorithm behind learning in AI.
neural networks
A New Link to an Old Model Could Crack the Mystery of Deep Learning
To help them explain the shocking success of deep neural networks, researchers are turning to older but better-understood models of machine learning.
neurons
How Computationally Complex Is a Single Neuron?
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.
graph theory
How Big Data Carried Graph Theory Into New Dimensions
Researchers are turning to the mathematics of higher-order interactions to better model the complex connections within their data.
Q&A
The Computer Scientist Training AI to Think With Analogies
Melanie Mitchell has worked on digital minds for decades. She says they’ll never truly be like ours until they can make analogies.
neuroscience
Neurons Unexpectedly Encode Information in the Timing of Their Firing
A temporal pattern of activity observed in human brains may explain how we can learn so quickly.