# ReSet: Learning Recurrent Dynamic Routing in ResNet-like Neural Networks

Source: [ReSet: Learning Recurrent Dynamic Routing in ResNet-like Neural Networks](<https://www.sota2.com/research/paper/68fa65161e209131cea082f9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:37.349Z

Authors: Iurii Kemaev, Daniil Polykovskiy, Dmitry Vetrov

Published: 2018-11-11T09:45:41.000Z

## Abstract

Neural Network is a powerful Machine Learning tool that shows outstanding performance in Computer Vision, Natural Language Processing, and Artificial Intelligence. In particular, recently proposed ResNet architecture and its modifications produce state-of-the-art results in image classification problems. ResNet and most of the previously proposed architectures have a fixed structure and apply the same transformation to all input images. In this work, we develop a ResNet-based model that dynamically selects Computational Units (CU) for each input object from a learned set of transformations. Dynamic selection allows the network to learn a sequence of useful transformations and apply only required units to predict the image label. We compare our model to ResNet-38 architecture and achieve better results than the original ResNet on CIFAR-10.1 test set. While examining the produced paths, we discovered that the network learned different routes for images from different classes and similar routes for similar images.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1811.04380>)

[PDF](<https://arxiv.org/pdf/1811.04380.pdf>)
