图 书 馆开课单位--卡内基梅隆大学
151
152
153
154
155
156
157
158
159
160
151Differentiable Sparse Coding[可微的稀疏编码]
David Bradley(卡内基梅隆大学) Prior work has shown that features which appear to be biologically plausible as well as empirically useful can be found by sparse coding with a prior ...
热度：34
David Bradley(卡内基梅隆大学) Prior work has shown that features which appear to be biologically plausible as well as empirically useful can be found by sparse coding with a prior ...
热度：34
152How Optimized Environmental Sensing Helps Address Information Overload on the Web[如何优化环境传感使其有助于解决网络上的信息过载]
Tom Mitchell;Carlos Guestrin(卡内基梅隆大学) In this talk, we tackle a fundamental problem that arises when using sensors to monitor the ecological condition of rivers and lakes, the network of p...
热度：52
Tom Mitchell;Carlos Guestrin(卡内基梅隆大学) In this talk, we tackle a fundamental problem that arises when using sensors to monitor the ecological condition of rivers and lakes, the network of p...
热度：52
153Structured Prediction for Natural Language Processing[自然语言处理的结构化预测]
Noah Smith(卡内基梅隆大学) This tutorial will discuss the use of structured prediction methods from machine learning in natural language processing. The field of NLP has, in the...
热度：66
Noah Smith(卡内基梅隆大学) This tutorial will discuss the use of structured prediction methods from machine learning in natural language processing. The field of NLP has, in the...
热度：66
154Fast Incremental Proximity Search in Large Graphs[大图中的快速增量邻近搜索]
Purnamrita Sarkar(卡内基梅隆大学) In this paper we investigate two aspects of ranking problems on large graphs. First, we augment the deterministic pruning algorithm in Sarkar and Moor...
热度：52
Purnamrita Sarkar(卡内基梅隆大学) In this paper we investigate two aspects of ranking problems on large graphs. First, we augment the deterministic pruning algorithm in Sarkar and Moor...
热度：52
155Actively Learning Level-Sets of Composite Functions[主动学习水平集复合函数]
Brent Bryan(卡内基梅隆大学) Scientists frequently have multiple types of experiments and data sets on which they can test the validity of their parametrized models and locate pla...
热度：36
Brent Bryan(卡内基梅隆大学) Scientists frequently have multiple types of experiments and data sets on which they can test the validity of their parametrized models and locate pla...
热度：36
156People Watching: Human Actions as a Cue for Single View Geometry[人们观察︰ 人类行为作为单视图几何的线索]
Silvio Savarese; Aude Oliva; David Fouhey(卡内基梅隆大学) We present an approach which exploits the coupling between human actions and scene geometry. We investigate the use of human pose as a cue for single-...
热度：19
Silvio Savarese; Aude Oliva; David Fouhey(卡内基梅隆大学) We present an approach which exploits the coupling between human actions and scene geometry. We investigate the use of human pose as a cue for single-...
热度：19
157Learning Linear Dynamical Systems without Sequence Information[无序列信息的线性动态系统的学习]
Tzu-Kuo Huang(卡内基梅隆大学) Virtually all methods of learning dynamic systems from data start from the same basic assumption: that the learning algorithm will be provided with a ...
热度：44
Tzu-Kuo Huang(卡内基梅隆大学) Virtually all methods of learning dynamic systems from data start from the same basic assumption: that the learning algorithm will be provided with a ...
热度：44
158Learning When to Stop Thinking and Do Something![学习何时停止思考和做某事!]
Barnabás Póczos(卡内基梅隆大学) An anytime algorithm is capable of returning a response to the given task at essentially any time; typically the quality of the response improves as t...
热度：44
Barnabás Póczos(卡内基梅隆大学) An anytime algorithm is capable of returning a response to the given task at essentially any time; typically the quality of the response improves as t...
热度：44
159Optimizing Estimated Loss Reduction for Active Sampling in Rank Learning[活跃的抽样等级学习优化估计损失减少]
Pinar Donmez(卡内基梅隆大学) Learning to rank is becoming an increasingly popular research area in machine learning. The ranking problem aims to induce an ordering or preference r...
热度：20
Pinar Donmez(卡内基梅隆大学) Learning to rank is becoming an increasingly popular research area in machine learning. The ranking problem aims to induce an ordering or preference r...
热度：20
160