marktechpost

Apple Researchers Propose Cut Cross-Entropy (CCE): A Machine Learning Method that Computes the Cross-Entropy Loss without Materializing the Logits for all Tokens into Global Memory

Advancements in large language models (LLMs) have revolutionized natural language processing, with applications spanning text generation, translation, and summarization. These models rely on large ...
Scientific Research Publishing

Mao, A., Mohri, M. and Zhong, Y. (2023) Cross-Entropy Loss Functions: Theoretical Analysis and Applications.

ABSTRACT: This study evaluates the performance and reliability of a vision transformer (ViT) compared to convolutional neural networks (CNNs) using the ResNet50 model in classifying lung cancer from ...
GitHub

nn.functional.binary_cross_entropy crashes if invoked with MPS float16

When I tried to fix the issue described by #123715, I found that nn.functional.binary_cross_entropy implementation in the MPS encountered an error, the detailed logs ...
IEEE

Parallel Cross Entropy Policy Gradient Adaptive Dynamic Programming for Optimal Tracking Control of Discrete-Time Nonlinear Systems

Abstract: Policy gradient adaptive dynamic programming (PGADP) is a recently acclaimed control technique for the optimal control design of nonlinear systems. Nevertheless, it demands a substantial ...
Scientific Research Publishing

Using Cross Entropy as a Performance Metric for Quantifying Uncertainty in DNN Image Classifiers: An Application to Classification of Lung Cancer on CT Images ()

1 Faculty of Informatics, University of Fukuchiyama, Kyoto, Japan. 2 Graduate School of Radiological Sciences, International University of Health and Welfare, Tochigi, Japan. 3 School of Health ...
GitHub

cross_entropy_loss.md

The **Cross-Entropy Loss** is actually the only loss we are discussing here. The other losses names written in the title are other names or variations of it. The CE ...
IEEE

Efficient Levenberg-Marquardt minimization of the cross-entropy error function

Abstract: The Levenberg-Marquardt algorithm is one of the most common choices for training medium-size artificial neural networks. Since it was designed to solve nonlinear least-squares problems, its ...