Artificial Recurrent Neural Networks are a powerful information processing abstraction, and Reservoir Computing provides an efficient strategy to build robust implementations by projecting external inputs into high dimensional dynamical system trajectories. In this paper, we propose an extension of the original approach, a local unsupervised learning mechanism we call Phase Transition Adaptation, designed to drive the system dynamics towards the `edge of stability'. Here, the complex behavior exhibited by the system elicits an enhancement in its overall computational capacity. We show experimentally that our approach consistently achieves its purpose over several datasets.
Source-Free Domain Adaptation via Multi-view Contrastive Learning
School of Computer engineering, Iran university of Science and Technology(伊朗科学技术大学计算机工程学院);Department of Computer Engineering, SR.C, Islamic Azad university(伊斯兰 Azad 大学计算机工程系)
CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation
Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));South China Agricultural University(华南农业大学);Guangdong University of Technology(广东工业大学)
Loss Smoothing for Stable Adaptation Under Distribution Shift
Chandar Research Lab(Chandar 研究实验室);Mila – Quebec AI Institute(Mila – 魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);Polytechnique Montréal(蒙特利尔理工学院);Canada CIFAR AI Chair(加拿大 CIFAR 人工智能主席)
TRACER: Transfer Learning based Real-time Adaptation for Clinical Evolving Risk
Duke University School of Medicine(杜克大学医学学院);Duke AI Health(杜克AI健康);Department of Biostatistics and Bioinformatics(生物统计学与生物信息学系);Duke-NUS Medical School(杜克-新加坡国立大学医学院);Centre for Quantitative Medicine(定量医学中心);Duke-NUS AI + Medical Sciences Initiative(杜克-新加坡国立大学AI+医学科学倡议);Pre-hospital & Emergency Research Centre(急救与应急研究中心);Health Services and Systems Research(卫生服务与系统研究);NUS Artificial Intelligence Institute(新加坡国立大学人工智能研究所)
Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning
School of Computer Science, The University of Sheffield, UK(谢菲尔德大学计算机科学学院,英国);Cancer Research UK National Biomarker Centre, The University of Manchester, UK(英国曼彻斯特大学癌症研究UK国家生物标志物中心);School of Chemical, Materials and Biological Engineering, The University of Sheffield, UK(谢菲尔德大学化学、材料和生物工程学院,英国);Machine Learning group, Centrum Wiskunde & Informatica, Amsterdam, Netherlands(荷兰阿姆斯特丹Centrum Wiskunde & Informatica机器学习组);Institute for Ecological Economics, Vienna University of Economics and Business, Austria(奥地利维也纳经济与商业大学生态经济研究所)
A2V: A Semi-Supervised Domain Adaptation Framework for Brain Vessel Segmentation via Two-Phase Training Angiography-to-Venography Translation
EURECOM(欧洲通信学院);University of Siena(锡耶纳大学);Centre Hospitalier Universitaire de Nice(尼斯大学医院中心);Centre for Medical Image Computing University College London(伦敦大学学院医学影像计算中心);e-health Center Universitat Oberta de Catalunya(加泰罗尼亚开放大学电子健康中心);Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);Inserm(法国国家健康与医学研究院);AP-HP(巴黎公共医疗救助机构)
深度神经网络(DNN)在各种计算机视觉应用中取得了前所未有的成功,例如图像分类和目标检测。然而,在训练阶段仍然是一个常见的烦恼,人们必须准备至少数千个标记图像来微调网络到特定的域。最近的研究(Tommasi et al. 2015)表明,DNN对训练数据集具有很强的依赖性,并且如果不进行微调,学习到的特征不能轻易地转移到不同但相关的任务中。在本文中,我们提出了一种简单而强大的补救措施,称为自适应批量归一化(AdaBN),以提高DNN的泛化能力。通过调整网络中所有批量归一化层的统计信息,我们的方法实现了领域自适应任务的深度自适应效果。与其他深度学习领域自适应方法相反,我们的方法不需要额外的组件,并且是无参数的。它的档案国家的最先进的性能,尽管其令人惊讶的简单。此外,我们证明了我们的方法是与其他现有的方法的补充。将AdaBN与现有的领域自适应处理相结合可以进一步提高模型性能。