Michael KissnerinTowards Data ScienceNetwork of Networks — A Neural-Symbolic Approach to Inverse-GraphicsOne of the first ideas many people have once they get acquainted with deep learning and neural networks is, “what if we make a network of…12 min read·Jul 23, 2019--2--2
Michael KissnerinTowards Data ScienceAn Easy Guide to Gauge Equivariant Convolutional NetworksGeometric deep learning is a very exciting new field, but its mathematics is slowly drifting into the territory of algebraic topology and…12 min read·May 24, 2019--10--10
Michael KissnerWriting down the weights and biases of a universal Neural Network without training itRecently, well a day ago, Lee et al. uploaded a paper that talks about the learning dynamics of wide Neural Networks (NN), which sparked a…4 min read·Feb 20, 2019----