Advances in Artificial Intelligence and Machine Learning最新文献

Exoskeleton-Based Multimodal Action and Movement Recognition: Identifying and Developing the Optimal Boosted Learning Approach 基于外骨骼的多模态动作和运动识别:识别和开发最佳的增强学习方法

Advances in Artificial Intelligence and Machine Learning Pub Date : 1900-01-01 DOI: 10.54364/aaiml

Nirmalya Thakur, C. Han

引用次数: 0

An Experimental Study of Dimension Reduction Methods on Machine Learning Algorithms with Applications to Psychometrics 机器学习算法降维方法在心理测量学中的应用实验研究

Advances in Artificial Intelligence and Machine Learning Pub Date : 1900-01-01 DOI: 10.54364/aaiml.2023.1149

Sean H. Merritt, Alexander P. Christensen

引用次数: 0

A Comparison of Methods for Neural Network Aggregation 神经网络聚合方法的比较

Advances in Artificial Intelligence and Machine Learning Pub Date : 1900-01-01 DOI: 10.54364/aaiml.2023.1160

John Pomerat Aviv Segev

{"title":"A Comparison of Methods for Neural Network Aggregation","authors":"John Pomerat Aviv Segev","doi":"10.54364/aaiml.2023.1160","DOIUrl":"https://doi.org/10.54364/aaiml.2023.1160","url":null,"abstract":"Deep learning has been successful in the theoretical aspect. For deep learning to succeed in industry, we need to have algorithms capable of handling many inconsistencies appearing in real data. These inconsistencies can have large effects on the implementation of a deep learning algorithm. Artificial Intelligence is currently changing the medical industry. However, receiving authorization to use medical data for training machine learning algorithms is a huge hurdle. A possible solution is sharing the data without sharing the patient information. We propose a multi-party computation protocol for the deep learning algorithm. The protocol enables to conserve both the privacy and the security of the training data. Three approaches of neural networks assembly are analyzed: transfer learning, average ensemble learning, and series network learning. The results are compared to approaches based on data-sharing in different experiments. We analyze the security issues of the proposed protocol. Although the analysis is based on medical data, the results of multi-party computation of machine learning training are theoretical and can be implemented in multiple research areas.","PeriodicalId":319545,"journal":{"name":"Advances in Artificial Intelligence and Machine Learning","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131328201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

General Cyclical Training of Neural Networks 神经网络的一般循环训练

Advances in Artificial Intelligence and Machine Learning Pub Date : 1900-01-01 DOI: 10.54364/aaiml.2023.1157

Leslie N. Smith

{"title":"General Cyclical Training of Neural Networks","authors":"Leslie N. Smith","doi":"10.54364/aaiml.2023.1157","DOIUrl":"https://doi.org/10.54364/aaiml.2023.1157","url":null,"abstract":"This position paper describes the principle of “General Cyclical Training” in machine learning, where training starts and ends with “easy training” and the “hard training” happens during the middle epochs. We propose several manifestations for training neural networks, including algorithmic examples (via hyper-parameters and loss functions), data-based examples, and model-based examples. Specifically, we introduce several novel techniques: cyclical weight decay, cyclical batch size, cyclical focal loss, cyclical softmax temperature, cyclical data augmentation, cyclical gradient clipping, and cyclical semi-supervised learning. In addition, we demonstrate that cyclical weight decay, cyclical softmax temperature, and cyclical gradient clipping (as three examples of this principle) are beneficial in the test accuracy performance of a trained model. Furthermore, we discuss model-based examples (such as pretraining and knowledge distillation) from the perspective of general cyclical training and recommend some changes to the typical training methodology. In summary, this paper defines the general cyclical training concept and discusses several specific ways in which this concept can be applied to training neural networks. In the spirit of reproducibility, the code used in our experiments is available at https://github.com/lnsmith54/CFL.","PeriodicalId":319545,"journal":{"name":"Advances in Artificial Intelligence and Machine Learning","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115581762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4