We take a closer look at some theoretical challenges of Machine Learning as a function approximation, gradient descent as the default optimization algorithm, limitations of fixed length and width networks and a different approach to RNNs from a mathematical perspective.
Paper
References (5)
02Only recently Fourier series were used in the new design of recurrent neural network called "Transformers
03Neural Networks and Lookup Tables for Identification Identification of Dynamic Systems2011
04Neural Networks and Lookup Tables for Identification Identification of Dynamic Systems Springer2011
05Protein Folding J2021 · Jumper et al.