Tech Times on MSN

Brain-like learning rule cracks convolutional networks: Sakana AI measures the biology tax

Biologically plausible learning now reaches 96.7% on MNIST and 61.7% on CIFAR-10 without backpropagation, as Sakana AI demonstrates brain-faithful training on convolutional networks for the first time ...
AlphaGalileo

Transfer learning for subject-independent motor imagery EEG classification using convolutional relational networks

Researchers from Nazarbayev University and Astana IT University have developed a transfer-learning framework that improves ...