人工智能与机器人研究最新文献

Multi-Modal Multi-Channel American Sign Language Recognition 多模态多通道美国手语识别

人工智能与机器人研究 Pub Date : 2023-11-10 DOI: 10.1142/s2972335324500017

Elahe Vahdani, Longlong Jing, Matt Huenerfauth, Yingli Tian

引用次数: 0

Asymptotic Edge of Chaos as Guiding Principle for Neural Network Training 混沌的渐近边作为神经网络训练的指导原则

人工智能与机器人研究 Pub Date : 2023-10-27 DOI: 10.1142/s2972335323500011

Lin Zhang, Ling Feng, Kan Chen, Choy Heng Lai

{"title":"Asymptotic Edge of Chaos as Guiding Principle for Neural Network Training","authors":"Lin Zhang, Ling Feng, Kan Chen, Choy Heng Lai","doi":"10.1142/s2972335323500011","DOIUrl":"https://doi.org/10.1142/s2972335323500011","url":null,"abstract":"It has been recently demonstrated that optimal neural networks operate near the asymptotic edge of chaos for state-of-the-art feed-forward neural networks, where its generalization power is maximal due to the highest number of asymptotic metastable states. However, how to leverage this principle to improve the model training process remains open. Here, by mapping the model evolution during training to the phase diagram in the classic analytic result of Sherrington–Kirkpatrick model in spin glasses, we illustrate on a simple neural network model that one can provide principled training of the network without manually tuning the training hyper-parameters. In particular, we provide a semi-analytical method to set the optimal weight decay strength, such that the model will converge toward the edge of chaos during training. Consequently, such hyper-parameter setting leads the model to achieve the highest test accuracy. Another benefit for restricting the model at the edge of chaos is its robustness against the common practical problem of label noise, as we find that it automatically avoids fitting the shuffled labels in the training samples while maintaining good fitting to the correct labels, providing simple means of achieving good performance on noisy labels without any additional treatment.","PeriodicalId":68167,"journal":{"name":"人工智能与机器人研究","volume":"268 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136233157","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

AI, Thinking Machines and A Vast Active Living Intelligent System 人工智能，会思考的机器和一个巨大的主动生活智能系统

人工智能与机器人研究 Pub Date : 2023-09-08 DOI: 10.1142/s2972335323020015

Bud Mishra

引用次数: 0

Traffic Signals Recognition Based on YOLOv8 基于YOLOv8的交通信号识别

人工智能与机器人研究 Pub Date : 2023-01-01 DOI: 10.12677/airr.2023.123028

恩兴赵

引用次数: 0

Recognition and Classification Technology of Abnormal Gait in Stroke Patients 脑卒中患者异常步态识别与分类技术

人工智能与机器人研究 Pub Date : 2023-01-01 DOI: 10.12677/airr.2023.122012

灶荣黄