Neural Computing cs.NE

The ocean resembles a giant web, where each thread connects distant points of water. When one spot warms, winds and currents change thousands of kilometers away. The neural network in this study wove such a web for the first time on its own to predict El Niño.

A neuron in the brain is like a person handing out business cards at a crowded conference. At first, making acquaintances is easy, but as the address book fills up, each new contact requires more effort: there's little room left. The authors based their model on this 'crowding' rule: the more incoming connections a neuron already has, the harder it is to form another one.

Engineers improving neural networks act like breeders: they try a variant, check the result, and keep the best. They collected 935 such trials from 161 papers and measured how often a code tweak turns out beneficial, harmful, or neutral. The picture is familiar to any biologist: 68% of changes degrade performance, 19% do nothing, and only 13% yield a gain.

An orchestra where each musician plays their own part but hears only the neighbor. One wrong note, and a wave of errors rolls through the hall. That's how Ising machines work — special devices for solving problems where you need to find the best option among many.

An orchestra at its first rehearsal without a conductor. Violins come in at the wrong time, brass is late, and instead of a symphony, you get cacophony. That's roughly how a computer model of the brain behaves when you remove special cells — von Economo neurons.

A robot in a maze walks into a dead end. A minute later, it’s the first to find the exit. This illogical maneuver is exploration, not a mistake. Like a cartographer circling a mountain to see its slopes. Evolutionary algorithms in silico have long mimicked selection and mutation to search for the best solutions.

Chatting with living neurons is like tuning an old radio: it's not enough to find the right frequency: you've got to aim the antenna too.

Holding in mind the exact position of a pen as it's slowly moved is a routine task for the brain. For artificial neural networks, it's nearly impossible. Standard recurrent networks like GRU and LSTM tend to break continuous motion into rigid steps: the pen doesn't glide smoothly but jumps from point to point.

A beam of light enters a glass cell filled with cesium vapor and changes the internal state of the atoms: this is how information is recorded. A moment later, another beam reads it out by how the atoms absorb light. It's not a hard drive, but rather a notebook that turns its own pages. Eight such "pages" are created by an acousto-optic deflector — a device that bends light with sound.

Getting lost in a hall of mirrors is easy: every wall reflects another, and you feel like you've been here before. The brain gets similarly confused when surrounded by many similar places. Neurons responsible for the spatial map can fire the same signal for two different corners of a room. This is called spatial ambiguity.