中文
相关论文

相关论文: A Study on the Uncertainty of Convolutional Layers…

200 篇论文

Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the robustness of…

机器学习 · 计算机科学 2017-03-27 Nicholas Cheney , Martin Schrimpf , Gabriel Kreiman

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning…

机器学习 · 计算机科学 2022-06-24 Haojing Shen , Sihong Chen , Ran Wang , Xizhao Wang

Loss functions play a key role in training superior deep neural networks. In convolutional neural networks (CNNs), the popular cross entropy loss together with softmax does not explicitly guarantee minimization of intra-class variance or…

计算机视觉与模式识别 · 计算机科学 2019-04-26 XiaoBin Li , WeiQiang Wang

Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for better training regimens. We investigate learning in Deep…

机器学习 · 计算机科学 2020-12-02 Ayush Manish Agrawal , Atharva Tendle , Harshvardhan Sikka , Sahib Singh , Amr Kayid

The highly non-linear nature of deep neural networks causes them to be susceptible to adversarial examples and have unstable gradients which hinders interpretability. However, existing methods to solve these issues, such as adversarial…

机器学习 · 计算机科学 2023-01-11 Suraj Srinivas , Kyle Matoba , Himabindu Lakkaraju , Francois Fleuret

A convolutional layer in a Convolutional Neural Network (CNN) consists of many filters which apply convolution operation to the input, capture some special patterns and pass the result to the next layer. If the same patterns also occur at…

计算机视觉与模式识别 · 计算机科学 2019-02-04 Okan Köpüklü , Maryam Babaee , Stefan Hörmann , Gerhard Rigoll

In this work, we build a generic architecture of Convolutional Neural Networks to discover empirical properties of neural networks. Our first contribution is to introduce a state-of-the-art framework that depends upon few hyper parameters…

计算机视觉与模式识别 · 计算机科学 2017-03-07 Edouard Oyallon

In this paper we discuss the stability properties of convolutional neural networks. Convolutional neural networks are widely used in machine learning. In classification they are mainly used as feature extractors. Ideally, we expect similar…

机器学习 · 计算机科学 2017-01-20 Radu Balan , Maneesh Singh , Dongmian Zou

Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme…

机器学习 · 计算机科学 2018-02-06 Amir Rosenfeld , John K. Tsotsos

Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by adversarial attacks. These attacks add a small perturbation to the…

机器学习 · 计算机科学 2018-03-26 Rajeev Ranjan , Swami Sankaranarayanan , Carlos D. Castillo , Rama Chellappa

Previous work has proposed many new loss functions and regularizers that improve test accuracy on image classification tasks. However, it is not clear whether these loss functions learn better representations for downstream tasks. This…

计算机视觉与模式识别 · 计算机科学 2021-11-05 Simon Kornblith , Ting Chen , Honglak Lee , Mohammad Norouzi

It is well known that (stochastic) gradient descent has an implicit bias towards flat minima. In deep neural network training, this mechanism serves to screen out minima. However, the precise effect that this has on the trained network is…

机器学习 · 计算机科学 2020-08-11 Rotem Mulayoff , Tomer Michaeli

Deep convolutional neural networks (CNN) brought revolution without any doubt to various challenging tasks, mainly in computer vision. However, their model designing still requires attention to reduce number of learnable parameters, with no…

计算机视觉与模式识别 · 计算机科学 2016-08-16 Ihsan Ullah , Alfredo Petrosino

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we…

机器学习 · 计算机科学 2020-01-09 Gao Huang , Zhuang Liu , Geoff Pleiss , Laurens van der Maaten , Kilian Q. Weinberger

This paper focuses on improving the mathematical interpretability of convolutional neural networks (CNNs) in the context of image classification. Specifically, we tackle the instability issue arising in their first layer, which tends to…

计算机视觉与模式识别 · 计算机科学 2025-04-21 Hubert Leterme , Kévin Polisano , Valérie Perrier , Karteek Alahari

Deep neural networks trained on a wide range of datasets demonstrate impressive transferability. Deep features appear general in that they are applicable to many datasets and tasks. Such property is in prevalent use in real-world…

机器学习 · 计算机科学 2019-09-27 Hong Liu , Mingsheng Long , Jianmin Wang , Michael I. Jordan

Modern neural network architectures for large-scale learning tasks have substantially higher model complexities, which makes understanding, visualizing and training these architectures difficult. Recent contributions to deep learning…

机器学习 · 计算机科学 2024-10-30 Jayadeva , Himanshu Pant , Mayank Sharma , Abhimanyu Dubey , Sumit Soman , Suraj Tripathi , Sai Guruju , Nihal Goalla

We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…

机器学习 · 统计学 2019-03-11 Konstantin Posch , Jan Steinbrener , Jürgen Pilz

Neural Networks have high accuracy in solving problems where it is difficult to detect patterns or create a logical model. However, these algorithms sometimes return wrong solutions, which become problematic in high-risk domains like…

机器学习 · 计算机科学 2025-06-26 Miguel N. Font , José L. Jorro-Aragoneses , Carlos M. Alaíz

Deep neural network models have a complex architecture and are overparameterized. The number of parameters is more than the whole dataset, which is highly resource-consuming. This complicates their application and limits its usage on…

计算机视觉与模式识别 · 计算机科学 2024-08-15 Vasiliy Alekseev , Ilya Lukashevich , Ilia Zharikov , Ilya Vasiliev
‹ 上一页 1 2 3 10 下一页 ›