English
Related papers

Related papers: Hybridised Loss Functions for Improved Neural Netw…

200 papers

Nearly all practical neural models for classification are trained using cross-entropy loss. Yet this ubiquitous choice is supported by little theoretical or empirical evidence. Recent work (Hui & Belkin, 2020) suggests that training using…

Machine Learning · Computer Science 2023-02-09 Like Hui , Mikhail Belkin , Stephen Wright

Conventional training methods for artificial neural network (ANN) models never achieve zero error rate systematically for large data. A new training method consists of three steps: first create an auxiliary data from conventionally trained…

Machine Learning · Computer Science 2023-12-27 Bo Deng

In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Shihao Zhang , Linlin Yang , Michael Bi Mi , Xiaoxu Zheng , Angela Yao

Learning with a {\it convex loss} function has been a dominating paradigm for many years. It remains an interesting question how non-convex loss functions help improve the generalization of learning with broad applicability. In this paper,…

Machine Learning · Computer Science 2018-05-22 Yi Xu , Shenghuo Zhu , Sen Yang , Chi Zhang , Rong Jin , Tianbao Yang

Traditionally artificial neural networks (ANNs) are trained by minimizing the cross-entropy between a provided groundtruth delta distribution (encoded as one-hot vector) and the ANN's predictive softmax distribution. It seems, however,…

Computer Vision and Pattern Recognition · Computer Science 2018-12-31 Pooran Singh Negi , David chan , Mohammad Mahoor

Deep Neural Networks, often owing to the overparameterization, are shown to be capable of exactly memorizing even randomly labelled data. Empirical studies have also shown that none of the standard regularization techniques mitigate such…

Machine Learning · Computer Science 2021-07-23 Deep Patel , P. S. Sastry

In most applications of utilizing neural networks for mathematical optimization, a dedicated model is trained for each specific optimization objective. However, in many scenarios, several distinct yet correlated objectives or tasks often…

Machine Learning · Computer Science 2024-04-15 Wei Cui , Wei Yu

Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It has been shown that the commonly used Cross Entropy (CE) loss is not robust to noisy labels. Whilst new…

Machine Learning · Computer Science 2020-06-25 Xingjun Ma , Hanxun Huang , Yisen Wang , Simone Romano , Sarah Erfani , James Bailey

Cross entropy loss has served as the main objective function for classification-based tasks. Widely deployed for learning neural network classifiers, it shows both effectiveness and a probabilistic interpretation. Recently, after the…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Rahaf Aljundi , Yash Patel , Milan Sulc , Daniel Olmeda , Nikolay Chumerin

For classification, neural networks typically learn by minimizing cross-entropy, but are evaluated and compared using accuracy. This disparity suggests neural loss function search (NLFS), the search for a drop-in replacement loss function…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Brandon Morgan , Dean Hougen

This paper is motivated by an open problem around deep networks, namely, the apparent absence of over-fitting despite large over-parametrization which allows perfect fitting of the training data. In this paper, we analyze this phenomenon in…

Machine Learning · Computer Science 2019-08-28 Hrushikesh Mhaskar , Tomaso Poggio

Neural-symbolic approaches have recently gained popularity to inject prior knowledge into a learner without requiring it to induce this knowledge from data. These approaches can potentially learn competitive solutions with a significant…

Artificial Intelligence · Computer Science 2023-02-16 Giuseppe Marra , Francesco Giannini , Michelangelo Diligenti , Marco Maggini , Marco Gori

We introduce two-scale loss functions for use in various gradient descent algorithms applied to classification problems via deep neural networks. This new method is generic in the sense that it can be applied to a wide range of machine…

Numerical Analysis · Mathematics 2021-09-03 Leonid Berlyand , Robert Creese , Pierre-Emmanuel Jabin

Uncertainty quantification of machine learning and deep learning methods plays an important role in enhancing trust to the obtained result. In recent years, a numerous number of uncertainty quantification methods have been introduced. Monte…

Machine Learning · Computer Science 2023-02-07 Afshar Shamsi , Hamzeh Asgharnezhad , AmirReza Tajally , Saeid Nahavandi , Henry Leung

Robust loss functions are essential for training deep neural networks with better generalization power in the presence of noisy labels. Symmetric loss functions are confirmed to be robust to label noise. However, the symmetric condition is…

Machine Learning · Computer Science 2021-06-08 Xiong Zhou , Xianming Liu , Junjun Jiang , Xin Gao , Xiangyang Ji

In supervised machine learning, the choice of loss function implicitly assumes a particular noise distribution over the data. For example, the frequently used mean squared error (MSE) loss assumes a Gaussian noise distribution. The choice…

Machine Learning · Computer Science 2023-02-15 Thamsanqa Mlotshwa , Heinrich van Deventer , Anna Sergeevna Bosman

The generalisation of Neural Networks (NN) to multiple datasets is often overlooked in literature due to NNs typically being optimised for specific data sources. This becomes especially challenging in time-series-based multi-dataset models…

Machine Learning · Computer Science 2024-10-28 Ayman Elhalwagy , Tatiana Kalganova

Artificial neural networks (ANNs) show limited performance with scarce or imbalanced training data and face challenges with continuous learning, such as forgetting previously learned data after new tasks training. In contrast, the human…

Machine Learning · Computer Science 2024-10-22 Anthony Bazhenov , Pahan Dewasurendra , Giri P. Krishnan , Jean Erik Delanois

We propose a new loss function for supervised and physics-informed training of neural networks and operators that incorporates a posteriori error estimate. More specifically, during the training stage, the neural network learns additional…

Numerical Analysis · Mathematics 2024-02-09 Vladimir Fanaskov , Alexander Rudikov , Ivan Oseledets

We propose a generalized formulation of the Huber loss. We show that with a suitable function of choice, specifically the log-exp transform; we can achieve a loss function which combines the desirable properties of both the absolute and the…

Machine Learning · Statistics 2021-08-31 Kaan Gokcesu , Hakan Gokcesu