Tag: neural networks

Researchers in Morocco have developed IACAN, a deep learning architecture that dynamically balances convolutional and attention branches using KL divergence ...

Researchers have developed a hypernetwork-based framework that lets continually learning AI systems erase specific tasks without access to the original ...

Researchers in China have developed a deep learning model that analyzes complete, variable-length opcode sequences from blockchain transactions, detecting seven ...

Researchers highlight reconfigurable transistor hardware that filters task-relevant visual inputs before computation, cutting wasted activations in neuromorphic AI systems.

A combined monkey, human, and neural network study reveals that feature interference in the visual cortex explains why uncertain tasks ...

Researchers have combined quantum-mechanical simulations, neural networks, and Bayesian statistics to cut the voltage prediction error of a physics-based lithium-ion ...

A new Nature Machine Intelligence study provides causal evidence that language models actively use internal confidence signals to shape their ...

A new unsupervised framework transfers part-of-speech annotations to low-resource languages using machine-generated pseudo-parallel data instead of real parallel corpora.

Researchers have introduced NB-Net, a biologically inspired neural network that expands in width through parallel multi-scale branches and staged feature ...

A new cloud-edge collaborative framework adapts speech-to-speech translation to any device's compute budget while preserving speaker identity through a privacy-preserving ...