English
Related papers

Related papers: Effect of the regularization hyperparameter on dee…

200 papers

It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations. Is there a theoretical basis for this?…

Machine Learning · Statistics 2018-09-19 Andrew R. Barron , Jason M. Klusowski

In this paper, we focus on three problems in deep learning based medical image segmentation. Firstly, U-net, as a popular model for medical image segmentation, is difficult to train when convolutional layers increase even though a deeper…

Computer Vision and Pattern Recognition · Computer Science 2018-10-17 Wanli Chen , Yue Zhang , Junjun He , Yu Qiao , Yifan Chen , Hongjian Shi , Xiaoying Tang

This paper demonstrates dynamic hyper-parameter setting, for deep neural network training, using Mutual Information (MI). The specific hyper-parameter studied in this paper is the learning rate. MI between the output layer and true outcomes…

Machine Learning · Computer Science 2018-06-27 Shrihari Vasudevan

We identify an implicit under-parameterization phenomenon in value-based deep RL methods that use bootstrapping: when value functions, approximated using deep neural networks, are trained with gradient descent using iterated regression onto…

Machine Learning · Computer Science 2021-10-26 Aviral Kumar , Rishabh Agarwal , Dibya Ghosh , Sergey Levine

Deep neural networks have proved very successful on archetypal tasks for which large training sets are available, but when the training data are scarce, their performance suffers from overfitting. Many existing methods of reducing…

Computer Vision and Pattern Recognition · Computer Science 2017-11-17 Wei Zhu , Qiang Qiu , Jiaji Huang , Robert Calderbank , Guillermo Sapiro , Ingrid Daubechies

We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sensitivity to…

Machine Learning · Statistics 2017-06-01 Yuichi Yoshida , Takeru Miyato

Training a deep neural model for semantic segmentation requires collecting a large amount of pixel-level labeled data. To alleviate the data scarcity problem presented in the real world, one could utilize synthetic data whose label is easy…

Computer Vision and Pattern Recognition · Computer Science 2021-11-10 Yiren Jian , Chongyang Gao

Meta-learning that uses implicit gradient have provided an exciting alternative to standard techniques which depend on the trajectory of the inner loop training. Implicit meta-learning (IML), however, require computing $2^{nd}$ order…

Machine Learning · Computer Science 2023-10-31 Fady Rezk

We derive a new margin-based regularization formulation, termed multi-margin regularization (MMR), for deep neural networks (DNNs). The MMR is inspired by principles that were applied in margin analysis of shallow linear classifiers, e.g.,…

Machine Learning · Computer Science 2020-09-15 Berry Weinstein , Shai Fine , Yacov Hel-Or

Deep metrics have been shown effective as similarity measures in multi-modal image registration; however, the metrics are currently constructed from aligned image pairs in the training data. In this paper, we propose a strategy for learning…

Computer Vision and Pattern Recognition · Computer Science 2018-04-06 Alireza Sedghi , Jie Luo , Alireza Mehrtash , Steve Pieper , Clare M. Tempany , Tina Kapur , Parvin Mousavi , William M. Wells

For compression fracture detection and evaluation, an automatic X-ray image segmentation technique that combines deep-learning and level-set methods is proposed. Automatic segmentation is much more difficult for X-ray images than for CT or…

Medical Physics · Physics 2019-04-17 Kang Cheol Kim , Hyun Cheol Cho , Tae Jun Jang , Jong Mun Choi , Jin Keun Seo

The analysis of neural network training beyond their linearization regime remains an outstanding open question, even in the simplest setup of a single hidden-layer. The limit of infinitely wide networks provides an appealing route forward…

Machine Learning · Computer Science 2020-06-19 Jaume de Dios , Joan Bruna

We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations. In training low-precision networks, gradient descent in the backward pass is performed…

Computer Vision and Pattern Recognition · Computer Science 2020-05-26 Yoojin Choi , Mostafa El-Khamy , Jungwon Lee

Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…

Machine Learning · Computer Science 2025-07-30 Andrii Balashov

Automated segmentation of anatomical structures is a crucial step in image analysis. For lung segmentation in computed tomography, a variety of approaches exist, involving sophisticated pipelines trained and validated on different datasets.…

Image and Video Processing · Electrical Eng. & Systems 2020-08-21 Johannes Hofmanninger , Florian Prayer , Jeanny Pan , Sebastian Rohrich , Helmut Prosch , Georg Langs

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we…

Computer Vision and Pattern Recognition · Computer Science 2020-05-07 Yi Zhu , Zhongyue Zhang , Chongruo Wu , Zhi Zhang , Tong He , Hang Zhang , R. Manmatha , Mu Li , Alexander Smola

Classical statistical learning theory predicts that overparameterized models should exhibit severe overfitting, yet modern deep neural networks with far more parameters than training samples consistently generalize well. This contradiction…

Machine Learning · Computer Science 2026-04-10 Zeran Johannsen

Deep learning based methods have achieved remarkable success in image restoration and enhancement, but most such methods rely on RGB input images. These methods fail to take into account the rich spectral distribution of natural images. We…

Image and Video Processing · Electrical Eng. & Systems 2021-02-11 Harsh Sinha , Aditya Mehta , Murari Mandal , Pratik Narang

Hyperparameters in machine learning (ML) have received a fair amount of attention, and hyperparameter tuning has come to be regarded as an important step in the ML pipeline. But just how useful is said tuning? While smaller-scale…

Machine Learning · Computer Science 2022-09-05 Moshe Sipper

Parametric approaches to Learning, such as deep learning (DL), are highly popular in nonlinear regression, in spite of their extremely difficult training with their increasing complexity (e.g. number of layers in DL). In this paper, we…

Machine Learning · Computer Science 2018-03-23 Ashkan Panahi , Hamid Krim , Liyi Dai