English
Related papers

Related papers: Closing the Training/Inference Gap for Deep Attrac…

200 papers

Given an existing trained neural network, it is often desirable to learn new capabilities without hindering performance of those already learned. Existing approaches either learn sub-optimal solutions, require joint training, or incur a…

Computer Vision and Pattern Recognition · Computer Science 2018-02-15 Amir Rosenfeld , John K. Tsotsos

Motivated by the gap between theoretical optimal approximation rates of deep neural networks (DNNs) and the accuracy realized in practice, we seek to improve the training of DNNs. The adoption of an adaptive basis viewpoint of DNNs leads to…

Machine Learning · Computer Science 2019-12-11 Eric C. Cyr , Mamikon A. Gulian , Ravi G. Patel , Mauro Perego , Nathaniel A. Trask

Back-translation is a critical component of Unsupervised Neural Machine Translation (UNMT), which generates pseudo parallel data from target monolingual data. A UNMT model is trained on the pseudo parallel data with translated source, and…

Computation and Language · Computer Science 2022-03-24 Zhiwei He , Xing Wang , Rui Wang , Shuming Shi , Zhaopeng Tu

Materials discovery is crucial for making scientific advances in many domains. Collections of data from experiments and first-principle computations have spurred interest in applying machine learning methods to create predictive models…

This paper introduces deep neural networks (DNNs) as add-on blocks to baseline feedback control systems to enhance tracking performance of arbitrary desired trajectories. The DNNs are trained to adapt the reference signals to the feedback…

Robotics · Computer Science 2017-10-09 Siqi Zhou , Mohamed K. Helwa , Angela P. Schoellig

Miscalibration - a mismatch between a model's confidence and its correctness - of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We show that, as…

Machine Learning · Computer Science 2020-10-27 Jishnu Mukhoti , Viveka Kulharia , Amartya Sanyal , Stuart Golodetz , Philip H. S. Torr , Puneet K. Dokania

A lot of recent work has focused on sparse learned indexes that use deep neural architectures to significantly improve retrieval quality while keeping the efficiency benefits of the inverted index. While such sparse learned structures…

Information Retrieval · Computer Science 2024-07-09 Soyuj Basnet , Jerry Gou , Antonio Mallia , Torsten Suel

Deep learning models offer superior performance compared to other machine learning techniques for a variety of tasks and domains, but pose their own challenges. In particular, deep learning models require larger training times as the depth…

Machine Learning · Computer Science 2023-05-31 Sunitha Basodi , Krishna Pusuluri , Xueli Xiao , Yi Pan

As shown in recent research, deep neural networks can perfectly fit randomly labeled data, but with very poor accuracy on held out data. This phenomenon indicates that loss functions such as cross-entropy are not a reliable indicator of…

Machine Learning · Statistics 2019-06-13 Yiding Jiang , Dilip Krishnan , Hossein Mobahi , Samy Bengio

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

Data-driven techniques for machine vision heavily depend on the training data to sufficiently resemble the data occurring during test and application. However, in practice unknown distortion can lead to a domain gap between training and…

Image and Video Processing · Electrical Eng. & Systems 2022-10-25 Maximiliane Gruber , Fabian Brand , Alina Mosebach , Jürgen Seiler , André Kaup

This paper introduces a meta-learning approach for parameterized pseudo-differential operators with deep neural networks. With the help of the nonstandard wavelet form, the pseudo-differential operators can be approximated in a compressed…

Numerical Analysis · Mathematics 2020-02-26 Jordi Feliu-Faba , Yuwei Fan , Lexing Ying

The recent development of deep learning combined with compressed sensing enables fast reconstruction of undersampled MR images and has achieved state-of-the-art performance for Cartesian k-space trajectories. However, non-Cartesian…

Image and Video Processing · Electrical Eng. & Systems 2022-07-26 Chang Gao , Shu-Fu Shih , J. Paul Finn , Xiaodong Zhong

This thesis aims to invent new approaches for making inferences with the k-means algorithm. k-means is an iterative clustering algorithm that randomly assigns k centroids, then assigns data points to the nearest centroid, and updates…

Machine Learning · Computer Science 2024-10-24 Alfred K. Adzika , Prudence Djagba

While self-attention mechanism has shown promising results for many vision tasks, it only considers the current features at a time. We show that such a manner cannot take full advantage of the attention mechanism. In this paper, we present…

Computer Vision and Pattern Recognition · Computer Science 2020-07-13 Xu Ma , Jingda Guo , Sihai Tang , Zhinan Qiao , Qi Chen , Qing Yang , Song Fu

Deep Neural Networks (DNN) have shown great promise in many classification applications, yet are widely known to have poorly calibrated predictions when they are over-parametrized. Improving DNN calibration without comprising on model…

Machine Learning · Computer Science 2024-05-07 Mikkel Jordahn , Pablo M. Olmos

The task of labeling data for training deep neural networks is daunting and tedious, requiring millions of labels to achieve the current state-of-the-art results. Such reliance on large amounts of labeled data can be relaxed by exploiting…

Machine Learning · Computer Science 2016-02-17 Aysegul Dundar , Jonghoon Jin , Eugenio Culurciello

We present an architecture of a recurrent neural network (RNN) with a fully-connected deep neural network (DNN) as its feature extractor. The RNN is equipped with both causal temporal prediction and non-causal look-ahead, via…

Machine Learning · Computer Science 2014-03-07 Jianshu Chen , Li Deng

While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and…

Machine Learning · Computer Science 2015-03-30 Adriana Romero , Nicolas Ballas , Samira Ebrahimi Kahou , Antoine Chassang , Carlo Gatta , Yoshua Bengio

In supervised learning, understanding an input's proximity to the training data can help a model decide whether it has sufficient evidence for reaching a reliable prediction. While powerful probabilistic models such as Gaussian Processes…

Machine Learning · Computer Science 2024-06-19 Ifigeneia Apostolopoulou , Benjamin Eysenbach , Frank Nielsen , Artur Dubrawski
‹ Prev 1 3 4 5 6 7 10 Next ›