no code implementations • 12 Sep 2023 • Ng Shyh-Chang, A-Li Luo, Bo Qiu
We further show that using the Eckart-Young theorem for truncated singular value decomposition of the weight matrix for every NN layer, we can illuminate the nature of the latent space manifold of the training dataset encoded and represented by every NN layer, and the geometric nature of the mathematical operations performed by each NN layer.