图 书 馆开课单位--卡内基梅隆大学
41
42
43
44
45
46
47
48
49
50
41Reducing the Sampling Complexity of Topic Models[降低主题模型的抽样复杂度]
Aaron Li(卡内基梅隆大学) Inference in topic models typically involves a sampling step to associate latent variables with observations. Unfortunately the generative model loses...
热度：33
Aaron Li(卡内基梅隆大学) Inference in topic models typically involves a sampling step to associate latent variables with observations. Unfortunately the generative model loses...
热度：33
42Opinion Fraud Detection in Online Reviews by Network Effects[基于网络效应的在线评论意见欺诈检测]
Leman Akoglu(卡内基梅隆大学) User-generated online reviews can play a significant role in the success of retail products, hotels, restaurants, etc. However,review systems are ofte...
热度：67
Leman Akoglu(卡内基梅隆大学) User-generated online reviews can play a significant role in the success of retail products, hotels, restaurants, etc. However,review systems are ofte...
热度：67
43A Globally Optimal Data-Driven Approach for Image Distortion Estimation[一种全局最优数据驱动的图像失真估计方法]
Yuandong Tian(卡内基梅隆大学) Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformat...
热度：33
Yuandong Tian(卡内基梅隆大学) Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformat...
热度：33
44Data-Driven Scene Understanding from 3D Models[基于三维模型的数据驱动场景理解]
Scott Satkin(卡内基梅隆大学) In this paper, we propose a data-driven approach to leverage repositories of 3D models for scene understanding. Our ability to relate what we see in a...
热度：57
Scott Satkin(卡内基梅隆大学) In this paper, we propose a data-driven approach to leverage repositories of 3D models for scene understanding. Our ability to relate what we see in a...
热度：57
45How Optimized Environmental Sensing Helps Address Information Overload on the Web[优化的环境感知如何帮助解决网络上的信息过载问题]
Tom Mitchell(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：3
Tom Mitchell(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：3
46The sample complexity of agnostic learning under deterministic labels[确定性标签下不可知学习的样本复杂度]
Ruth Urner(卡内基梅隆大学) With the emergence of Machine Learning tools that allow handling data with a huge number of features, it becomes reasonable to assume that, over the f...
热度：37
Ruth Urner(卡内基梅隆大学) With the emergence of Machine Learning tools that allow handling data with a huge number of features, it becomes reasonable to assume that, over the f...
热度：37
47Jointly Modeling Aspects, Ratings and Sentiments for Movie Recommendation (JMARS)[联合建模方面，收视率和情感电影推荐（JMARS）]
Chao-Yuan Wu(卡内基梅隆大学) Recommendation and review sites offer a wealth of information beyond ratings. For instance, on IMDb users leave reviews, commenting on different aspec...
热度：84
Chao-Yuan Wu(卡内基梅隆大学) Recommendation and review sites offer a wealth of information beyond ratings. For instance, on IMDb users leave reviews, commenting on different aspec...
热度：84
48Should Model Architecture Reflect Linguistic Structure?[模型建筑应该反映语言结构吗？]
Chris Dyer(卡内基梅隆大学) Sequential recurrent neural networks (RNNs) over finite alphabets are remarkably effective models of natural language. RNNs now obtain language modeli...
热度：21
Chris Dyer(卡内基梅隆大学) Sequential recurrent neural networks (RNNs) over finite alphabets are remarkably effective models of natural language. RNNs now obtain language modeli...
热度：21
49Learning Deep Generative Models[学习深层生成模型]
Ruslan Salakhutdinov(卡内基梅隆大学) In this tutorial I will discuss mathematical basics of many popular deep generative models, including Restricted Boltzmann Machines (RBMs), Deep Boltz...
热度：28
Ruslan Salakhutdinov(卡内基梅隆大学) In this tutorial I will discuss mathematical basics of many popular deep generative models, including Restricted Boltzmann Machines (RBMs), Deep Boltz...
热度：28
50Unfolding an Indoor Origami World[展开室内折纸世界]
David Ford Fouhey(卡内基梅隆大学) In this work, we present a method for single-view reasoning about 3D surfaces and their relationships. We propose the use of mid-level constraints for...
热度：33
David Ford Fouhey(卡内基梅隆大学) In this work, we present a method for single-view reasoning about 3D surfaces and their relationships. We propose the use of mid-level constraints for...
热度：33