Tag: CIFAR-10

Researchers have developed SLAW, a training framework that adapts label smoothing to the sharpness of the loss landscape and reweights ...

A new reinforcement learning framework called FLASH-DRM selects the most valuable devices for each federated learning round, improving accuracy, latency ...

A controlled comparison finds quaternion-valued neural networks match or exceed shallow variational quantum circuits on MNIST, FashionMNIST, and CIFAR-10 at ...

Researchers have unveiled FakeMark, an attack that fabricates convincing neural network watermark evidence without ever accessing the victim model, exposing ...

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

A new tensor decomposition framework dynamically compresses and decompresses neural network layers during training, achieving 95.81 percent accuracy in 12 ...

Researchers at Harbin Engineering University have developed a dual-stream semantic communication framework that lets embodied AI agents preserve both visual ...