开课单位--卡内基梅隆大学
111
112
113
114
115
116
117
118
119
120
![](functions/showpic.php?filename=2016112207412261.png)
Some Challenging Machine Learning Problems in Computational Biology: Time-Varying Networks Inference and Sparse Structured Input-Out Learning[计算生物学中的一些挑战性机器学习问题:时变网络推理和稀疏结构化输入法学习]
Eric P. Xing(卡内基梅隆大学) Recent advances in high-throughput technologies such as microarrays and genome-wide sequencing have led to an avalanche of new biological data that ar...
热度:46
Eric P. Xing(卡内基梅隆大学) Recent advances in high-throughput technologies such as microarrays and genome-wide sequencing have led to an avalanche of new biological data that ar...
热度:46
![](functions/showpic.php?filename=2016112207370217.png)
Object Recognition and Segmentation by Association[对象识别和分割协会]
Tomasz Malisiewicz(卡内基梅隆大学) Many object recognition systems train a different classifier for each object category and use the sliding window approach to classify image regions. I...
热度:27
Tomasz Malisiewicz(卡内基梅隆大学) Many object recognition systems train a different classifier for each object category and use the sliding window approach to classify image regions. I...
热度:27
![](functions/showpic.php?filename=2016112207232439.png)
Local Minima Free Parameterized Appearance Models [局部最小自由参数化外观模型]
Minh Hoai Nguyen(卡内基梅隆大学) Parameterized Appearance Models (PAMs) (e.g. Eigen-tracking, Active Appearance Models, Morphable Models) are commonly used to model the appearance and...
热度:53
Minh Hoai Nguyen(卡内基梅隆大学) Parameterized Appearance Models (PAMs) (e.g. Eigen-tracking, Active Appearance Models, Morphable Models) are commonly used to model the appearance and...
热度:53
![](functions/showpic.php?filename=2016102005421778.png)
![](functions/showpic.php?filename=2019042110171111.png)
Dynamic Non-Parametric Mixture Models and The Recurrent Chinese Restaurant Process[动态非参数混合模型与经常性中餐回流过程]
Eric P. Xing(卡内基梅隆大学) Dirichlet process mixture models provide a °exible Bayesian framework for estimating a distribution as an in¯nite mixture of simpler distribu...
热度:29
Eric P. Xing(卡内基梅隆大学) Dirichlet process mixture models provide a °exible Bayesian framework for estimating a distribution as an in¯nite mixture of simpler distribu...
热度:29
![](functions/showpic.php?filename=2019042108231571.png)
On the Quantitative Analysis of Deep Belief Networks[论深层信念网络的定量分析]
Ruslan Salakhutdinov(卡内基梅隆大学) Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and appr...
热度:58
Ruslan Salakhutdinov(卡内基梅隆大学) Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and appr...
热度:58
![](functions/showpic.php?filename=2019042108203230.png)
Bayesian Probabilistic Matrix Factorization using Markov Chain Monte Carlo[马尔可夫链蒙特卡罗的贝叶斯概率矩阵分解]
Ruslan Salakhutdinov(卡内基梅隆大学) Low-rank matrix approximation methods provide one of the simplest and most effective approaches to collaborative filtering. Such models are usually fi...
热度:97
Ruslan Salakhutdinov(卡内基梅隆大学) Low-rank matrix approximation methods provide one of the simplest and most effective approaches to collaborative filtering. Such models are usually fi...
热度:97
![](functions/showpic.php?filename=2019041708415062.png)
Recovering Temporally Rewiring Networks: A model-based approach[恢复暂时重新连线的网络:基于模型的方法]
Fan Guo(卡内基梅隆大学) A plausible representation of relational information among entities in dynamic systems such as a living cell or a social community is a stochastic net...
热度:39
Fan Guo(卡内基梅隆大学) A plausible representation of relational information among entities in dynamic systems such as a living cell or a social community is a stochastic net...
热度:39
![](functions/showpic.php?filename=2019041908225317.png)
Space-indexed Dynamic Programming: Learning to Follow Trajectories[空间索引动态规划:学习跟踪轨迹]
J. Zico Kolter(卡内基梅隆大学) We consider the task of learning to accurately follow a trajectory in a vehicle such as a car or helicopter. A number of dynamic programming algorithm...
热度:62
J. Zico Kolter(卡内基梅隆大学) We consider the task of learning to accurately follow a trajectory in a vehicle such as a car or helicopter. A number of dynamic programming algorithm...
热度:62
![](functions/showpic.php?filename=2019041007220823.png)
EDM and the 4th Paradigm of Scientific Discovery - Reflections on the 2010 KDD Cup Competition[EDM与科学发现的第四范式 - 对2010年KDD杯比赛的思考]
John Stamper(卡内基梅隆大学) Technology advances have made the ability to collect large amounts of data easier than ever before. These massive datasets provide both opportunities ...
热度:60
John Stamper(卡内基梅隆大学) Technology advances have made the ability to collect large amounts of data easier than ever before. These massive datasets provide both opportunities ...
热度:60