paper-with-me

Papers

Learning to Adaptively Scale Recurrent Neural Networks

2019-02-15 · Hao Hu, Liqiang Wang, Guo-Jun Qi

Recent advancements in recurrent neural network (RNN) research have demonstrated the superiority of utilizing multiscale structures in learning temporal representations of time series. Currently, most of multiscale RNNs use fixed scales, which do not comply with the nature of dynamical temporal patterns among sequences. In this paper, we propose Adaptively Scaled Recurrent Neural Networks (ASRNN), a simple but efficient way to handle this problem. Instead of using predefined scales, ASRNNs are able to learn and adjust scales based on different temporal contexts, making them more flexible in modeling multiscale patterns. Compared with other multiscale RNNs, ASRNNs are bestowed upon dynamical scaling capabilities with much simpler structures, and are easy to be integrated with various RNN cells. The experiments on multiple sequence modeling tasks indicate ASRNNs can efficiently adapt scales based on different sequence contexts and yield better performances than baselines without dynamical scaling abilities.

📄 PDF Abstract BibTeX arXiv:1902.05696

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

Gated Feedback Recurrent Neural Networks

2015-02-09 · Junyoung Chung, Caglar Gulcehre, Kyunghyun Cho, Yoshua Bengio

In this work, we propose a novel recurrent neural network (RNN) architecture. The proposed RNN, gated-feedback RNN (GF-RNN), extends the existing approach of stacking multiple recurrent layers by allowing and controlling…

Language ModelingLanguage Modelling

Recurrent Model Predictive Control: Learning an Explicit Recurrent Controller for Nonlinear Systems

2021-02-20 · Zhengyu Liu, Jingliang Duan, Wenxuan Wang, Shengbo Eben Li 외

This paper proposes an offline control algorithm, called Recurrent Model Predictive Control (RMPC), to solve large-scale nonlinear finite-horizon optimal control problems. It can be regarded as an explicit solver of trad…

Model Predictive Control

Crowd Counting using Deep Recurrent Spatial-Aware Network

2018-07-02 · Lingbo Liu, Hongjun Wang, Guanbin Li, Wanli Ouyang 외

Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera's perspective that causes huge appearanc…

Crowd CountingManagement

Recurrent Scene Parsing with Perspective Understanding in the Loop

2017-05-20 · CVPR 2018 6 · Shu Kong, Charless Fowlkes

Objects may appear at arbitrary scales in perspective images of a scene, posing a challenge for recognition systems that process images at a fixed resolution. We propose a depth-aware gating module that adaptively select…

Depth EstimationMonocular Depth EstimationScene ParsingSegmentation+1

Recurrent Attention Unit

2018-10-30 · Guoqiang Zhong, Guohua Yue, Xiao Ling

Recurrent Neural Network (RNN) has been successfully applied in many sequence learning problems. Such as handwriting recognition, image description, natural language processing and video motion analysis. After years of d…

General ClassificationHandwriting Recognitionimage-classificationImage Classification+5