搜索结果: 1-15 共查到“理学 Deep”相关记录499条 . 查询时间(0.125 秒)
On the Interplay Between Deep Learning and Dynamical Systems
Deep Learning Dynamical Systems 北大
font style='font-size:12px;'>
2023/6/16
The explosion of spatiotemporal data in the physical world requires new deep learning tools to model complex dynamical systems.
Live: Particle pursuit, a journey of the Deep Underground Neutrino Experiment（图）
中微子实验 粒子追逐 欧洲核子研究中心
font style='font-size:12px;'>
2023/6/12
On 15 June, join CERN, Fermilab and Sanford Underground Research Facility (SURF) for an interactive livestream that will take you on a journey of the Deep Underground Neutrino Experiment (DUNE). The C...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Deep leaning-based hyperspectral image classification
深度倾斜 高光谱 图像分类
font style='font-size:12px;'>
2023/5/4
In this talk, we will introduce some hyperspectral image classification methods based on deep learning architecture. Recently, deep learning-based hyperspectral image classification has attracted more...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Optimization-inspired deep unfolding correction-distillation network for CS-MRI reconstruction
优化启发 CS-MRI 重建深度展开 校正-蒸馏网络
font style='font-size:12px;'>
2023/4/27
In this talk, we discuss a unifying deep unfolding multi-sampling-ratio interpretable CS-MRI framework. The combined approach offers more generalizability than the existing deep-learning-based CS-MRI ...
Humans need Earth-like ecosystem for deep-space living（图）
地球 生态系统 深空生活
font style='font-size:12px;'>
2023/5/17
Can humans endure long-term living in deep space?The answer is a lukewarm maybe, according to a new theory describing the complexity of maintaining gravity and oxygen, obtaining water, developing agri...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Convergence and Implicit Regularization of Deep Learning Optimizers
深度学习 优化 收敛 隐式正则化
font style='font-size:12px;'>
2023/4/13
In this talk, I will present our recent work on the convergence/generalization analysis for the popular optimizers in deep learning. (1) We establish the convergence for Adam under (L0,L1 ) smoothness...
Study on methane in deep-sea sediments shows small releases happen more often than thought（图）
深海沉积物 甲烷 化石生物 单细胞生物
font style='font-size:12px;'>
2023/6/26
New research describes evidence that deep sea methane deposits change into gas more frequently than could be monitored previously and that a set of fossilized organisms has a unique ability to detect ...
Racing to catalog, study deep-sea biodiversity（图）
深海生物 物种多样性 生物学
font style='font-size:12px;'>
2023/6/19
Paula Rodríguez-Flores has always been obsessed with invertebrates. “Like really, really obsessed,” said the biodiversity postdoctoral fellow, who works in Harvard’s Museum of Comparative Zoology.
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：A Sparse Expansion of (Deep) Gaussian Processes
深层 高斯过程 稀疏展开
font style='font-size:12px;'>
2023/4/18
Conventional inferential methods for (deep) Gaussian Processes models can suffer from high computational complexity as they require large-scale operations with kernel matrices for training and inferen...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Real-time tool path planning using deep learning for subtractive manufacturing
深度学习 减材制造 实时刀具 路径规划
font style='font-size:12px;'>
2023/4/25
Tool path planning is a crucial factor of computer-aided design and manufacturing (CAD/CAM). To generate suitable tool paths, the previous methods often transform the problem into local or global opti...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Deep learning of multi-scale PDEs based on data generated from particle methods
粒子方法 数据 多尺度 偏微分方程 深度学习
font style='font-size:12px;'>
2023/4/26
Solving multi-scale PDEs is difficult in high-dimensional and/or convection-dominant cases. The interacting particle methods (IPM) are shown to outperform solving PDEs directly. Examples include compu...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Convergence Thery of Deep Neural Networks: Arbitrary Activation Functions and Pooling
深度神经网络 激活函数 池化
font style='font-size:12px;'>
2023/4/28
Deep neural networks, as a powerful system to represent high dimensional complex functions, play a key role in deep learning. Convergence of deep neural networks is a fundamental issue in building the...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Deep image prior for inverse problems: acceleration and probabilistic treatment
反问题 深度图像 加速 概率处理
font style='font-size:12px;'>
2023/5/10
Since its first proposal in 2018, deep image prior has emerged as a very powerful unsupervised deep learning technique for solving inverse problems. The approach has demonstrated very encouraging empi...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Deep adaptive sampling for numerical PDEs
数值 偏微分方程 深度 自适应采样
font style='font-size:12px;'>
2023/5/15
Adaptive computation is of great importance in numerical simulations. The ideas for adaptive computations can be dated back to adaptive finite element methods in 1970s. In this talk, we shall first re...
Ocean scientists measure sediment plume stirred up by deep-sea-mining vehicle（图）
深海采矿车 沉积物羽流 海洋科学
font style='font-size:12px;'>
2023/6/19
What will be the impact to the ocean if humans are to mine the deep sea? It’s a question that’s gaining urgency as interest in marine minerals has grown.