International Conference on Machine Learning, Optimization, and Data Science最新文献

A Comparison of SVM against Pre-trained Language Models (PLMs) for Text Classification Tasks 支持向量机与预训练语言模型在文本分类任务中的比较

International Conference on Machine Learning, Optimization, and Data Science Pub Date : 2022-11-04 DOI: 10.48550/arXiv.2211.02563

Yasmen Wahba, N. Madhavji, John Steinbacher

引用次数: 7

Hierarchical Decentralized Deep Reinforcement Learning Architecture for a Simulated Four-Legged Agent 模拟四足智能体的分层分散深度强化学习体系结构

International Conference on Machine Learning, Optimization, and Data Science Pub Date : 2022-09-21 DOI: 10.48550/arXiv.2210.08003

W. Z. E. Amri, L. Hermes, M. Schilling

{"title":"Hierarchical Decentralized Deep Reinforcement Learning Architecture for a Simulated Four-Legged Agent","authors":"W. Z. E. Amri, L. Hermes, M. Schilling","doi":"10.48550/arXiv.2210.08003","DOIUrl":"https://doi.org/10.48550/arXiv.2210.08003","url":null,"abstract":"Legged locomotion is widespread in nature and has inspired the design of current robots. The controller of these legged robots is often realized as one centralized instance. However, in nature, control of movement happens in a hierarchical and decentralized fashion. Introducing these biological design principles into robotic control systems has motivated this work. We tackle the question whether decentralized and hierarchical control is beneficial for legged robots and present a novel decentral, hierarchical architecture to control a simulated legged agent. Three different tasks varying in complexity are designed to benchmark five architectures (centralized, decentralized, hierarchical and two different combinations of hierarchical decentralized architectures). The results demonstrate that decentralizing the different levels of the hierarchical architectures facilitates learning of the agent, ensures more energy efficient movements as well as robustness towards new unseen environments. Furthermore, this comparison sheds light on the importance of modularity in hierarchical architectures to solve complex goal-directed tasks. We provide an open-source code implementation of our architecture (https://github.com/wzaielamri/hddrl).","PeriodicalId":432112,"journal":{"name":"International Conference on Machine Learning, Optimization, and Data Science","volume":"481 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114782452","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: 1

On the utility and protection of optimization with differential privacy and classic regularization techniques 差分隐私和经典正则化技术优化的效用和保护

International Conference on Machine Learning, Optimization, and Data Science Pub Date : 2022-09-07 DOI: 10.48550/arXiv.2209.03175

Eugenio Lomurno, Matteo Matteucci

引用次数: 2

Adaptive Zeroth-Order Optimisation of Nonconvex Composite Objectives 非凸复合目标的自适应零阶优化

International Conference on Machine Learning, Optimization, and Data Science Pub Date : 2022-08-09 DOI: 10.48550/arXiv.2208.04579

Weijia Shao, S. Albayrak

引用次数: 0

Robust PCA for Anomaly Detection and Data Imputation in Seasonal Time Series 基于鲁棒主成分分析的季节时间序列异常检测与数据代入

International Conference on Machine Learning, Optimization, and Data Science Pub Date : 2022-08-03 DOI: 10.48550/arXiv.2208.01998

Hông-Lan Botterman, Julien Roussel, Thomas Morzadec, A. Jabbari, N. Brunel

引用次数: 1

Parallel Bayesian Optimization of Agent-based Transportation Simulation 基于agent的交通仿真并行贝叶斯优化

International Conference on Machine Learning, Optimization, and Data Science Pub Date : 2022-07-11 DOI: 10.48550/arXiv.2207.05041

K. Chhatre, Sidney A. Feygin, C. Sheppard, R. Waraich

{"title":"Parallel Bayesian Optimization of Agent-based Transportation Simulation","authors":"K. Chhatre, Sidney A. Feygin, C. Sheppard, R. Waraich","doi":"10.48550/arXiv.2207.05041","DOIUrl":"https://doi.org/10.48550/arXiv.2207.05041","url":null,"abstract":"MATSim (Multi-Agent Transport Simulation Toolkit) is an open source large-scale agent-based transportation planning project applied to various areas like road transport, public transport, freight transport, regional evacuation, etc. BEAM (Behavior, Energy, Autonomy, and Mobility) framework extends MATSim to enable powerful and scalable analysis of urban transportation systems. The agents from the BEAM simulation exhibit 'mode choice' behavior based on multinomial logit model. In our study, we consider eight mode choices viz. bike, car, walk, ride hail, driving to transit, walking to transit, ride hail to transit, and ride hail pooling. The 'alternative specific constants' for each mode choice are critical hyperparameters in a configuration file related to a particular scenario under experimentation. We use the 'Urbansim-10k' BEAM scenario (with 10,000 population size) for all our experiments. Since these hyperparameters affect the simulation in complex ways, manual calibration methods are time consuming. We present a parallel Bayesian optimization method with early stopping rule to achieve fast convergence for the given multi-in-multi-out problem to its optimal configurations. Our model is based on an open source HpBandSter package. This approach combines hierarchy of several 1D Kernel Density Estimators (KDE) with a cheap evaluator (Hyperband, a single multidimensional KDE). Our model has also incorporated extrapolation based early stopping rule. With our model, we could achieve a 25% L1 norm for a large-scale BEAM simulation in fully autonomous manner. To the best of our knowledge, our work is the first of its kind applied to large-scale multi-agent transportation simulations. This work can be useful for surrogate modeling of scenarios with very large populations.","PeriodicalId":432112,"journal":{"name":"International Conference on Machine Learning, Optimization, and Data Science","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121080367","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

Brain-like combination of feedforward and recurrent network components achieves prototype extraction and robust pattern recognition 将前馈和递归网络成分结合，实现了原型提取和鲁棒模式识别

International Conference on Machine Learning, Optimization, and Data Science Pub Date : 2022-06-30 DOI: 10.48550/arXiv.2206.15036

Naresh B. Ravichandran, A. Lansner, P. Herman

{"title":"Brain-like combination of feedforward and recurrent network components achieves prototype extraction and robust pattern recognition","authors":"Naresh B. Ravichandran, A. Lansner, P. Herman","doi":"10.48550/arXiv.2206.15036","DOIUrl":"https://doi.org/10.48550/arXiv.2206.15036","url":null,"abstract":"Associative memory has been a prominent candidate for the computation performed by the massively recurrent neocortical networks. Attractor networks implementing associative memory have offered mechanistic explanation for many cognitive phenomena. However, attractor memory models are typically trained using orthogonal or random patterns to avoid interference between memories, which makes them unfeasible for naturally occurring complex correlated stimuli like images. We approach this problem by combining a recurrent attractor network with a feedforward network that learns distributed representations using an unsupervised Hebbian-Bayesian learning rule. The resulting network model incorporates many known biological properties: unsupervised learning, Hebbian plasticity, sparse distributed activations, sparse connectivity, columnar and laminar cortical architecture, etc. We evaluate the synergistic effects of the feedforward and recurrent network components in complex pattern recognition tasks on the MNIST handwritten digits dataset. We demonstrate that the recurrent attractor component implements associative memory when trained on the feedforward-driven internal (hidden) representations. The associative memory is also shown to perform prototype extraction from the training data and make the representations robust to severely distorted input. We argue that several aspects of the proposed integration of feedforward and recurrent computations are particularly attractive from a machine learning perspective.","PeriodicalId":432112,"journal":{"name":"International Conference on Machine Learning, Optimization, and Data Science","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130978720","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

MicroRacer: a didactic environment for Deep Reinforcement Learning MicroRacer:深度强化学习的教学环境

International Conference on Machine Learning, Optimization, and Data Science Pub Date : 2022-03-20 DOI: 10.48550/arXiv.2203.10494

A. Asperti, Marco Del Brutto

引用次数: 0

Algorithms that Get Old: The Case of Generative Deep Neural Networks 过时的算法:生成式深度神经网络的案例

International Conference on Machine Learning, Optimization, and Data Science Pub Date : 2022-02-07 DOI: 10.1007/978-3-031-25891-6_14

G. Turinici

引用次数: 0

Brain Structural Saliency Over The Ages 多年来大脑结构的显著性

International Conference on Machine Learning, Optimization, and Data Science Pub Date : 2022-01-12 DOI: 10.1007/978-3-031-25891-6_40

Daniel Taylor, Jonathan Shock, Deshendran Moodley, J. Ipser, M. Treder

引用次数: 0