开课单位--多伦多大学
21
Dropout: A simple and effective way to improve neural networks[辍学:改进神经网络的一种简单有效的方法]
Geoffrey E. Hinton(多伦多大学) In a large feedforward neural network, overfitting can be greatly reduced by randomly omitting half of the hidden units on each training case. This pr...
热度:52
Geoffrey E. Hinton(多伦多大学) In a large feedforward neural network, overfitting can be greatly reduced by randomly omitting half of the hidden units on each training case. This pr...
热度:52
22
Incorporating Structure in Deep Learning[深度学习中的整合结构]
Raquel Urtasun(多伦多大学) Deep learning algorithms attempt to model high-level abstractions of the data using architectures composed of multiple non-linear transformations. A m...
热度:69
Raquel Urtasun(多伦多大学) Deep learning algorithms attempt to model high-level abstractions of the data using architectures composed of multiple non-linear transformations. A m...
热度:69
23
Deep Learning[深度学习]
Ruslan Salakhutdinov(多伦多大学) Building intelligent systems that are capable of extracting high-level representations from high-dimensional sensory data lies at the core of solving ...
热度:25
Ruslan Salakhutdinov(多伦多大学) Building intelligent systems that are capable of extracting high-level representations from high-dimensional sensory data lies at the core of solving ...
热度:25
24
Playing Atari with Deep Reinforcement Learning[在深层强化学习中玩雅达利]
Volodymyr Mnih(多伦多大学) We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learn...
热度:38
Volodymyr Mnih(多伦多大学) We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learn...
热度:38
25
Automatically labeled data generation for classification of reputation defence strategies[声誉防御策略分类的自动标记数据生成]
Nona Naderi(多伦多大学) Reputation defence is a form of persuasive tactic that is used in various social settings especially in political situations. Detection of reputation ...
热度:28
Nona Naderi(多伦多大学) Reputation defence is a form of persuasive tactic that is used in various social settings especially in political situations. Detection of reputation ...
热度:28
26
Characterization of pancreatic alpha-cell physiology in pancreatic slices[胰腺切片胰岛α细胞生理特性]
Ya-Chi Huang(多伦多大学) Characterization of pancreatic alpha-cell physiology in pancreatic slices
热度:229
Ya-Chi Huang(多伦多大学) Characterization of pancreatic alpha-cell physiology in pancreatic slices
热度:229
27
Dropout: A simple and effective way to improve neural networks[辍学:改进神经网络的一种简单有效的方法]
Geoffrey E. Hinton(多伦多大学) In a large feedforward neural network, overfitting can be greatly reduced by randomly omitting half of the hidden units on each training case. This pr...
热度:20
Geoffrey E. Hinton(多伦多大学) In a large feedforward neural network, overfitting can be greatly reduced by randomly omitting half of the hidden units on each training case. This pr...
热度:20
28
Gaussian Processes for Monocular 3D People tracking[高斯过程单眼3D的人跟踪]
Raquel Urtasun(多伦多大学) We advocate the use of Gaussian Processes (GPs) to learn prior models of human pose and motion for 3D people tracking. The Gaussian Process Latent var...
热度:51
Raquel Urtasun(多伦多大学) We advocate the use of Gaussian Processes (GPs) to learn prior models of human pose and motion for 3D people tracking. The Gaussian Process Latent var...
热度:51
29
Learning Human Pose and Motion Models for Animation[学习人体姿势和运动模型的动画]
Aaron Hertzmann(多伦多大学) Computer animation is an extraordinarily labor-intensive process; obtaining high-quality motion models could make the process faster and easier. I wil...
热度:57
Aaron Hertzmann(多伦多大学) Computer animation is an extraordinarily labor-intensive process; obtaining high-quality motion models could make the process faster and easier. I wil...
热度:57
30
Web Service Composition via Generic Procedures & Customizing User Preferences[Web服务组合通过通用程序]
Shirin Sohrabi Araghi(多伦多大学) Research 7: Web Service Composition via Generic Procedures & Customizing User Preferences.
热度:63
Shirin Sohrabi Araghi(多伦多大学) Research 7: Web Service Composition via Generic Procedures & Customizing User Preferences.
热度:63