On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “wavelet-like”

On learning with shift-invariant structurescs.LG

New algorithms for learning shift-invariant components and aligning signals.

problem Learning shift-invariant components and aligning signals.

method Formulated optimization problems using circulant and convolutional matrices, proposed efficient solutions.

result Effective algorithms for learning shift-invariant components and aligning signals.

shift-invariant circulant matrices dictionary learning signal alignment wavelet-like

2018-12-03abs ↗pdf ↗

Parallel Transport Convolution: A New Tool for Convolutional Neural Networks on Manifoldscs.LG

Convolution has been playing a prominent role in various applications in science and engineering for many years. It is the most important operation in convolutional neural networks. There has been a recent growth of interests of research in generalizing convolutions on curved domains such as manifolds and graphs. Howev…

2018-05-21abs ↗pdf ↗

End-to-End Auditory Object Recognition via Inception Nucleuscs.SD

End-to-end audio recognition system improves accuracy.

problem Improving accuracy in auditory object recognition.

method Proposes an end-to-end deep neural network with an 'inception nucleus' to learn features from raw waveforms.

result Bests current state-of-the-art approaches by 10.4 percentage points on Urbansound8k dataset.

auditory object recognition end-to-end learning inception nucleus deep neural network waveform inputs

2020-05-25abs ↗pdf ↗

Ridge Regression with Over-Parametrized Two-Layer Networks Converge to Ridgelet Spectrumcs.LG

Study shows neural network parameters converge to ridgelet spectrum.

problem Characterization of local minima in over-parametrized neural networks.

method Developed ridgelet transform to analyze neural network parameters.

result Distribution of parameters converges to ridgelet spectrum.

ridge regression neural networks wavelet transform local minima over-parametrization

2020-07-07abs ↗pdf ↗

Express Wavenet -- a low parameter optical neural network with random shift wavelet patterncs.LG

Express Wavenet reduces neural network parameters to 1% of standard networks.

problem Optical neural networks with high parameter count.

method Wavelet modulation, random shift wavelets, expressway structure.

result Express Wavenet achieves high accuracy with significantly fewer parameters.

Optical neural networks Wavelet modulation Parameter reduction Random shift wavelets Expressway structure

2020-01-06abs ↗pdf ↗

Wavelet Networks: Scale-Translation Equivariant Learning From Raw Time-Seriescs.LG

Wavelet Networks learn from raw time-series data, outperforming conventional CNNs.

problem Learning from raw time-series data efficiently and effectively.

method Constructing scale-translation equivariant neural networks based on wavelet symmetries.

result Wavelet Networks outperform conventional CNNs on raw waveforms and spectrograms.

Wavelet Networks Time-series Equivariant Wavelet Transform CNN

2020-06-09abs ↗pdf ↗

Kernel based analysis of massive datacs.LG

Develops a new theory for approximating functions on massive data.

problem Challenges in machine learning with massive data.

method eignets theory for local, stratified approximation.

result Solves inverse problems like finding data probability law and function smoothness.

machine learning approximation theory inverse problems wavelets metric measure space

2020-03-30abs ↗pdf ↗

Inducing Hierarchical Compositional Model by Sparsifying Generator Networkcs.CV

This paper learns hierarchical compositional models for image synthesis.

problem Creating interpretable and hierarchical image representations.

method Sparsifying a generator network to induce an AND-OR hierarchy.

result The method learns meaningful and interpretable hierarchical representations.

image synthesis hierarchical model interpretability sparsity convolutional neural networks

2019-09-10abs ↗pdf ↗