搜索结果: 1-11 共查到“数学 Deep”相关记录11条 . 查询时间(0.031 秒)
On the Interplay Between Deep Learning and Dynamical Systems
Deep Learning Dynamical Systems 北大
2023/6/16
The explosion of spatiotemporal data in the physical world requires new deep learning tools to model complex dynamical systems.
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
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 ...
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
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...
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
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
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
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
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
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
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...
中国地质大学科学技术发展院唐厂，王力哲 等，计算机学院. IEEE T-PAMI (2020), DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Discriminative Multi-scale Deep Features
基于多尺度；深度；特征；迭代融合；修正；图像模糊；检测网络
2021/10/15
2020年8月6日，IEEE模式分析与机器智汇刊《IEEE Transactions on Pattern Analysis and Machine Intelligence》正式首次刊发了中国地质大学计算机学院唐厂副教授与国防科技大学、澳大利亚卧龙岗大学、悉尼大学等单位合作完成的研究成果——DeFusionNET: Defocus Blur Detection via Recurrently F...
In recent years, artificial neural networks a.k.a. deep learning have significantly improved the fields of computer vision, speech recognition, and natural language processing. The success relies on t...