Tag
This paper evaluates the biological plausibility and representational alignment of feedback alignment algorithms in convolutional networks, comparing them to standard backpropagation on CIFAR-10. The authors find that modified feedback alignment methods converge on internal representations similar to those produced by backpropagation, suggesting functional success through mimicking representational geometry.
Andrej Karpathy's 'Neural Networks: Zero to Hero' is a free course covering neural networks from basics to modern architectures like transformers, with YouTube lectures and Jupyter notebooks. It includes hands-on implementations of micrograd and makemore.