2 papers
cs.LG2024
Neural Fourier Modelling: A Highly Compact Approach to Time-Series Analysis
Minjung Kim, Yusuke Hioka, Michael Witbrock
Neural time-series analysis has traditionally focused on modeling data in the time domain, often with some approaches incorporating equivalent Fourier domain representations as aux…
cs.AI2024
Transformers As Approximations of Solomonoff Induction
Nathan Young, Michael Witbrock
Solomonoff Induction is an optimal-in-the-limit unbounded algorithm for sequence prediction, representing a Bayesian mixture of every computable probability distribution and perfor…