English
Related papers

Related papers: Feature Incay for Representation Regularization

200 papers

Softmax function is widely used in artificial neural networks for multiclass classification, multilabel classification, attention mechanisms, etc. However, its efficacy is often questioned in literature. The log-softmax loss has been shown…

Machine Learning · Computer Science 2020-11-24 Kunal Banerjee , Vishak Prasad C , Rishi Raj Gupta , Karthik Vyas , Anushree H , Biswajit Mishra

Maximizing the separation between classes constitutes a well-known inductive bias in machine learning and a pillar of many traditional algorithms. By default, deep networks are not equipped with this inductive bias and therefore many…

Machine Learning · Computer Science 2022-10-25 Tejaswi Kasarla , Gertjan J. Burghouts , Max van Spengler , Elise van der Pol , Rita Cucchiara , Pascal Mettes

Weight decay is a widely used technique for training Deep Neural Networks(DNN). It greatly affects generalization performance but the underlying mechanisms are not fully understood. Recent works show that for layers followed by…

Machine Learning · Computer Science 2021-03-30 Yucong Zhou , Yunxiao Sun , Zhao Zhong

Designing robust loss functions is popular in learning with noisy labels while existing designs did not explicitly consider the overfitting property of deep neural networks (DNNs). As a result, applying these losses may still suffer from…

Machine Learning · Computer Science 2022-05-27 Hao Cheng , Zhaowei Zhu , Xing Sun , Yang Liu

Deep learning models have become an increasingly preferred option for biometric recognition systems, such as speaker recognition. SincNet, a deep neural network architecture, gained popularity in speaker recognition tasks due to its…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-13 Labib Chowdhury , Mustafa Kamal , Najia Hasan , Nabeel Mohammed

While numerous machine unlearning (MU) methods have recently been developed with promising results in erasing the influence of forgotten data, classes, or concepts, they are also highly vulnerable-for example, simple fine-tuning can…

Machine Learning · Computer Science 2026-04-10 Yichen Gao , Altay Unal , Akshay Rangamani , Zhihui Zhu

Regularization is essential when training large neural networks. As deep neural networks can be mathematically interpreted as universal function approximators, they are effective at memorizing sampling noise in the training data. This…

Machine Learning · Computer Science 2015-01-06 Jan Rudy , Weiguang Ding , Daniel Jiwoong Im , Graham W. Taylor

Deep networks learn internal representations whose geometry--how features bend, rotate, and evolve--affects both generalization and robustness. Existing similarity measures such as CKA or SVCCA capture pointwise overlap between activation…

Machine Learning · Computer Science 2026-01-30 Vasileios Sevetlidis , George Pavlidis

Despite the success of deep-learning models in many tasks, there have been concerns about such models learning shortcuts, and their lack of robustness to irrelevant confounders. When it comes to models directly trained on human faces, a…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Qi Qi , Shervin Ardeshir

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

In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation,…

Machine Learning · Statistics 2019-09-19 Ugo Tanielian , Flavian Vasile

In this paper we propose integrating a priori knowledge into both design and training of convolutional neural networks (CNNs) to learn object representations that are invariant to affine transformations (i.e., translation, scale, rotation).…

Computer Vision and Pattern Recognition · Computer Science 2019-09-04 Xenju Xu , Guanghui Wang , Alan Sullivan , Ziming Zhang

Replicated Softmax model, a well-known undirected topic model, is powerful in extracting semantic representations of documents. Traditional learning strategies such as Contrastive Divergence are very inefficient. This paper provides a novel…

Machine Learning · Computer Science 2015-06-25 Jiatao Gu , Victor O. K. Li

Current deep learning classifiers, carry out supervised learning and store class discriminatory information in a set of shared network weights. These weights cannot be easily altered to incrementally learn additional classes, since the…

Computer Vision and Pattern Recognition · Computer Science 2022-12-02 Penny Johnston , Keiller Nogueira , Kevin Swingler

Artificial and biological agents cannon learn given completely random and unstructured data. The structure of data is encoded in the metric relationships between data points. In the context of neural networks, neuronal activity within a…

Machine Learning · Computer Science 2022-11-03 Kosio Beshkov , Jonas Verhellen , Mikkel Elle Lepperød

We propose a novel approach which exploits chaos to enhance classification accuracy. Specifically, the available data that need to be classified are treated as vectors that are first lifted into a higher-dimensional space and then used as…

Machine Learning · Computer Science 2026-04-21 Panos Stinis

In this paper, we focus on the separability of classes with the cross-entropy loss function for classification problems by theoretically analyzing the intra-class distance and inter-class distance (i.e. the distance between any two points…

Machine Learning · Computer Science 2019-09-17 Rudrajit Das , Subhasis Chaudhuri

Nonnegative matrix factorization (NMF) has been widely used to dimensionality reduction in machine learning. However, the traditional NMF does not properly handle outliers, so that it is sensitive to noise. In order to improve the…

Machine Learning · Computer Science 2022-06-08 Tingting Shen , Junhang Li , Can Tong , Qiang He , Chen Li , Yudong Yao , Yueyang Teng

End-to-end speaker verification systems have received increasing interests. The traditional i-vector approach trains a generative model (basically a factor-analysis model) to extract i-vectors as speaker embeddings. In contrast, the…

Audio and Speech Processing · Electrical Eng. & Systems 2018-12-13 Yutian Li , Feng Gao , Zhijian Ou , Jiasong Sun

We propose a deep learning-based solution for the problem of feature learning in one-class classification. The proposed method operates on top of a Convolutional Neural Network (CNN) of choice and produces descriptive features while…

Computer Vision and Pattern Recognition · Computer Science 2019-10-02 Pramuditha Perera , Vishal M. Patel