English
Related papers

Related papers: Learning Wake-Sleep Recurrent Attention Models

200 papers

Research on continual learning has led to a variety of approaches to mitigating catastrophic forgetting in feed-forward classification networks. Until now surprisingly little attention has been focused on continual learning of recurrent…

Computer Vision and Pattern Recognition · Computer Science 2020-10-30 Riccardo Del Chiaro , Bartłomiej Twardowski , Andrew D. Bagdanov , Joost van de Weijer

Despite deep convolutional neural networks' great success in object classification, it suffers from severe generalization performance drop under occlusion due to the inconsistency between training and testing data. Because of the large…

Computer Vision and Pattern Recognition · Computer Science 2019-11-15 Mingqing Xiao , Adam Kortylewski , Ruihai Wu , Siyuan Qiao , Wei Shen , Alan Yuille

Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph for all instances, adaptive networks can dynamically adjust…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Hao Li , Hong Zhang , Xiaojuan Qi , Ruigang Yang , Gao Huang

Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance. Toward a…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Xizhou Zhu , Dazhi Cheng , Zheng Zhang , Stephen Lin , Jifeng Dai

Deep neural network training spends most of the computation on examples that are properly handled, and could be ignored. We propose to mitigate this phenomenon with a principled importance sampling scheme that focuses computation on…

Machine Learning · Computer Science 2019-10-29 Angelos Katharopoulos , François Fleuret

Stochastic nonlinear dynamical systems are ubiquitous in modern, real-world applications. Yet, estimating the unknown parameters of stochastic, nonlinear dynamical models remains a challenging problem. The majority of existing methods…

Machine Learning · Statistics 2022-05-06 Anubhab Ghosh , Mohamed Abdalmoaty , Saikat Chatterjee , Håkan Hjalmarsson

The transduction of sequence has been mostly done by recurrent networks, which are computationally demanding and often underestimate uncertainty severely. We propose a computationally efficient attention-based network combined with the…

Machine Learning · Computer Science 2021-02-11 Kuilin Chen , Chi-Guhn Lee

Established recurrent neural networks are well-suited to solve a wide variety of prediction tasks involving discrete sequences. However, they do not perform as well in the task of dynamical system identification, when dealing with…

Machine Learning · Computer Science 2019-11-22 Thomas Demeester

Inference in Gaussian process (GP) models is computationally challenging for large data, and often difficult to approximate with a small number of inducing points. We explore an alternative approximation that employs stochastic inference…

Machine Learning · Statistics 2019-05-28 Jiaxin Shi , Mohammad Emtiyaz Khan , Jun Zhu

Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study a sleep-like consolidation mechanism in which a model…

Computation and Language · Computer Science 2026-05-28 Sangyun Lee , Sean McLeish , Tom Goldstein , Giulia Fanti

In this work, we propose Retentive Network (RetNet) as a foundation architecture for large language models, simultaneously achieving training parallelism, low-cost inference, and good performance. We theoretically derive the connection…

Computation and Language · Computer Science 2023-08-10 Yutao Sun , Li Dong , Shaohan Huang , Shuming Ma , Yuqing Xia , Jilong Xue , Jianyong Wang , Furu Wei

Over the long history of machine learning, which dates back several decades, recurrent neural networks (RNNs) have been used mainly for sequential data and time series and generally with 1D information. Even in some rare studies on 2D…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Nguyen Huu Phong , Bernardete Ribeiro

A popular theory of perceptual processing holds that the brain learns both a generative model of the world and a paired recognition model using variational Bayesian inference. Most hypotheses of how the brain might learn these models assume…

Neurons and Cognition · Quantitative Biology 2021-06-01 Ari S. Benjamin , Konrad P. Kording

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output…

Machine Learning · Statistics 2017-11-01 Yihao Feng , Dilin Wang , Qiang Liu

Stochastic gradient descent (SGD) with stochastic momentum is popular in nonconvex stochastic optimization and particularly for the training of deep neural networks. In standard SGD, parameters are updated by improving along the path of the…

Machine Learning · Computer Science 2021-06-08 Jun-Kun Wang , Chi-Heng Lin , Jacob Abernethy

Asynchronous distributed algorithms are a popular way to reduce synchronization costs in large-scale optimization, and in particular for neural network training. However, for nonsmooth and nonconvex objectives, few convergence guarantees…

Optimization and Control · Mathematics 2020-07-14 Vyacheslav Kungurtsev , Malcolm Egan , Bapi Chatterjee , Dan Alistarh

Generative models based on neural networks present a substantial challenge within deep learning. As it stands, such models are primarily limited to the domain of artificial neural networks. Spiking neural networks, as the third generation…

Neural and Evolutionary Computing · Computer Science 2023-05-22 Linghao Feng , Dongcheng Zhao , Yi Zeng

In this paper, an orthogonal stochastic gradient descent (O-SGD) based learning approach is proposed to tackle the wireless channel over-training problem inherent in artificial neural network (ANN)-assisted MIMO signal detection. Our basic…

Signal Processing · Electrical Eng. & Systems 2020-02-26 Songyan Xue , Yi Ma , Rahim Tafazolli

Deep neural networks are a powerful tool for feature learning and extraction given their ability to model high-level abstractions in highly complex data. One area worth exploring in feature learning and extraction using deep neural networks…

Machine Learning · Computer Science 2015-12-15 Mohammad Javad Shafiee , Parthipan Siva , Paul Fieguth , Alexander Wong

Dense prediction models are widely used for image segmentation. One important challenge is to sufficiently train these models to yield good generalizations for hard-to-learn pixels. A typical group of such hard-to-learn pixels are…

Computer Vision and Pattern Recognition · Computer Science 2019-08-07 Gozde Nur Gunesli , Cenk Sokmensuer , Cigdem Gunduz-Demir