Interpretable neural networks help reveal the nature of dark matter

A research team from the Xinjiang Astronomical Observatory (XAO) of the Chinese Academy of Sciences has developed an ...

Kolmogorov-Arnold networks bridge AI and scientific discovery by increasing interpretability

AI has successfully been applied in many areas of science, advancing technologies like weather prediction and protein folding ...
eLife

Human EEG and artificial neural networks reveal disentangled representations and processing timelines of object real-world size and depth in natural images

Neural and computational evidence reveals that real-world size is a temporally late, semantically grounded, and hierarchically stable dimension of object representation in both human brains and ...

Neural DSP models John Mayer’s entire amp and effects rig—and it sounds great

So do we really need one amp sim package? Neural DSP thinks we do, because the Finnish company just dropped a major new ...

Designing Reactive AI With Spiking Neural Nets

Wolfram-like attention framing meets spiking networks: event-triggered, energy-thrifty AI that “wakes” to stimuli.
Interesting Engineering

AlphaFold and the architecture that cracked protein structure

AlphaFold didn't accelerate biology by running faster experiments. It changed the engineering assumptions behind protein structure prediction.

Key brain cell 'hubs' found to synchronize the body's internal clock

What makes someone a "morning lark" or a "night owl?" Why does jet lag hit us so hard, and why do some people struggle each ...
eLife

Afadin-deficient mouse retinas exhibit severe neuronal lamination defects but preserve visual functions

Afadin-deficient mice, whose outer-retinal lamination and photoreceptor synapses are severely disrupted, nonetheless partially retain retinal neural circuits and visual function.