Tag
A 2014 blog post explaining how to create hybrid images — pictures that change depending on viewing distance — by combining the 2006 Oliva/Torralba/Schyns technique with intuitive Fourier analysis and code.
The article explains how Fourier analysis can be used to draw complex shapes like llamas using rotating circles, demonstrating the Fourier transform through visual examples.
This paper uses Transition Games to study the transition from memorization to generalization in Transformers, revealing distributed utility gain with attention bias and Fourier recoding rather than a module switch.
FM-LLM propose a frequency-enhanced mixture-of-experts framework that adapts frozen LLMs to time series forecasting without textual prompts, achieving state-of-the-art results by injecting spectral representations and separating periodic/non-periodic decoding.
This paper develops a Fourier analysis framework to study data augmentation under group invariances, showing that partial augmentation can achieve the same minimax rates as full augmentation up to a vanishing approximation error, while also proving that exact invariance requires full group averaging.
Introduces SpikF-GO, a spiking neural network model for multivariate time series forecasting that combines graph-based inter-variable dependency modeling with spike-driven spectral processing, achieving state-of-the-art results among SNN methods with reduced energy consumption.
This paper provides a theoretical analysis of how neural networks learn structured representations during group composition tasks, proving that training dynamics drive neurons to converge to irreducible group representations with exponential convergence rates. The work establishes a representation-theoretic account of feature learning and characterizes a low-rank compression phenomenon for matrix-valued group representations.