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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “filter-sharing”

ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networkscs.LG

ALF reduces network parameters and operations by 70% and 61%, respectively, on embedded hardware.

problem Efficient deployment of deep learning models on resource-constrained hardware.

method Autoencoder-based low-rank filter-sharing technique.

result ALF achieves significant compression with minimal accuracy loss.

model compression convolutional neural networks embedded hardware autoencoder filter-sharing

2020-07-27abs ↗pdf ↗

FSNet: Compression of Deep Convolutional Neural Networks by Filter Summarycs.LG

We present a novel method of compression of deep Convolutional Neural Networks (CNNs) by weight sharing through a new representation of convolutional filters. The proposed method reduces the number of parameters of each convolutional layer by learning a 1D vector termed Filter Summary (FS). The convolutional filters ar…

2019-02-08abs ↗pdf ↗