Sakana AI - SkrewAI

Sakana AI

Sakana AI Trains Neural Nets Without Backpropagation

Sakana AI's error diffusion method trains Dale-compliant dual-stream networks without backpropagation, hitting 96.7% on MNIST and 61.7% on CIFAR-10, pointing toward more biologically plausible learning.

Sakana AI

Sakana AI's DiffusionBlocks Rethinks Neural Net Training

Sakana AI's DiffusionBlocks reframes residual network training as independent denoising tasks, eliminating end-to-end backprop and slashing memory costs for large generative models.

Sakana AI

Sakana AI's KAME Injects LLM Smarts Into Speech-to-Speech

Sakana AI's KAME is a tandem speech-to-speech architecture that injects LLM knowledge into voice models in real time, aiming to fix the latency-versus-intelligence tradeoff in conversational AI.