图 书 馆开课单位--多伦多大学
11
12
13
14
15
16
17
18
19
20
1112Research 7: Web Service Composition via Generic Procedures & Customizing User Preferences[研究7:通过通用过程组合Web服务和自定义用户首选项]
Shirin Sohrabi(多伦多大学) Web Service Composition via Generic Procedures & Customizing User Preferences
热度：23
Shirin Sohrabi(多伦多大学) Web Service Composition via Generic Procedures & Customizing User Preferences
热度：23
13Stochastic Image Denoising[随机性图像去噪]
Francisco Estrada(多伦多大学) We present a novel, probabilistic algorithm for image noise removal. We show that suitably constrained random walks over small image neighborhoods pro...
热度：42
Francisco Estrada(多伦多大学) We present a novel, probabilistic algorithm for image noise removal. We show that suitably constrained random walks over small image neighborhoods pro...
热度：42
14ImageNet Classification with Deep Convolutional Neural Networks[基于深度卷积神经网络的图像网络分类]
Alex Krizhevsky(多伦多大学) We trained a large, deep convolutional neural network to classify the 1.3 million high-resolution images in the LSVRC-2010 ImageNet training set into ...
热度：126
Alex Krizhevsky(多伦多大学) We trained a large, deep convolutional neural network to classify the 1.3 million high-resolution images in the LSVRC-2010 ImageNet training set into ...
热度：126
15A tutorial on Deep Learning[深度学习教程]
Geoffrey E. Hinton(多伦多大学) Complex probabilistic models of unlabeled data can be created by combining simpler models. Mixture models are obtained by averaging the densities of s...
热度：47
Geoffrey E. Hinton(多伦多大学) Complex probabilistic models of unlabeled data can be created by combining simpler models. Mixture models are obtained by averaging the densities of s...
热度：47
16Virtual Worlds, Contextualism, and the Myth of Fiction[虚拟世界的语境和虚构的神话]
Peter Ludlow(多伦多大学) In this lecture I will tell you a story about my exploits in Second Life, at the end of that I will extract two philosophical conclusions. At the begi...
热度：33
Peter Ludlow(多伦多大学) In this lecture I will tell you a story about my exploits in Second Life, at the end of that I will extract two philosophical conclusions. At the begi...
热度：33
17Factored 3-way restricted Boltzmann machines for modeling natural images[因式分解的3路受限Boltzmann机器在自然图像建模中的应用]
Marc’Aurelio Ranzato(多伦多大学) Deep belief nets have been successful in modeling handwritten characters, but it has proved more difficult to apply them to real images. The problem l...
热度：30
Marc’Aurelio Ranzato(多伦多大学) Deep belief nets have been successful in modeling handwritten characters, but it has proved more difficult to apply them to real images. The problem l...
热度：30
18Solving the uncapacitated facility location problem using message passing algorithms[使用消息传递算法解决无容量限制的设施选址问题]
Nevena Lazic(多伦多大学) The Uncapacitated Facility Location Problem (UFLP) is one of the most widely studied discrete location problems, whose applications arise in a variety...
热度：55
Nevena Lazic(多伦多大学) The Uncapacitated Facility Location Problem (UFLP) is one of the most widely studied discrete location problems, whose applications arise in a variety...
热度：55
19Improving Classification Accuracy Using Automatically Extracted Training Data[利用自动提取训练数据提高分类精度]
Ariel Fuxman(多伦多大学) Classification is a core task in knowledge discovery and data mining, and there has been substantial research effort in developing sophisticated class...
热度：41
Ariel Fuxman(多伦多大学) Classification is a core task in knowledge discovery and data mining, and there has been substantial research effort in developing sophisticated class...
热度：41
20Information Cascade at Group Scale[群体规模的信息级联]
Milad Eftekhar(多伦多大学) Identifying the k most influential individuals in a social network is a well-studied problem. The objective is to detect k individuals in a (social) n...
热度：30
Milad Eftekhar(多伦多大学) Identifying the k most influential individuals in a social network is a well-studied problem. The objective is to detect k individuals in a (social) n...
热度：30