Allison Whitten

Christopher Kanan is building algorithms that can continuously learn over time — the way we do.

Intelligent beings learn by interacting with the world. Artificial intelligence researchers have adopted a similar strategy to teach their virtual agents new tricks.

Neuroscientists uncovered an energy-saving mode in vision-system neurons that works at the cost of being able to see fine-grained details.

Dopamine, a neurochemical often associated with reward behavior, also seems to help organize precisely when the brain initiates movements. It’s the latest revelation about the power of neuromodulators.

Algorithms that use the brain’s communication signal can now work on analog neuromorphic chips, which closely mimic our energy-efficient brains.

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.

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.

By focusing on relationships between solutions to polynomial equations, rather than the exact solutions themselves, Évariste Galois changed the course of modern mathematics.