Theory of Representation — Inductive Biases, Gaussian Processes, and the NN–GP Correspondence | MIT 6.7960 Lecture 13
Take a net to infinite width and its random-init output becomes a Gaussian process (NN–GP); its training dynamics freeze into the Neural Tangent Kernel (NTK). This theory analyzes nets and, in reverse, guides us to design the 'right inductive bias'.