图 书 馆开课单位--加州大学欧文分校
1 1/1
1Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition[逃离鞍点——张量分解的在线随机梯度]
Furong Huang(加州大学欧文分校) We analyze stochastic gradient descent for optimizing non-convex functions. For non-convex functions often it is good to find a reasonable local minim...
热度：10
Furong Huang(加州大学欧文分校) We analyze stochastic gradient descent for optimizing non-convex functions. For non-convex functions often it is good to find a reasonable local minim...
热度：10
2Learning Overcomplete Latent Variable Models through Tensor Methods[用张量方法学习超完全潜变量模型]
Animashree Anandkumar(加州大学欧文分校) We provide guarantees for learning latent variable models emphasizing on the overcomplete regime, where the dimensionality of the latent space exceeds...
热度：15
Animashree Anandkumar(加州大学欧文分校) We provide guarantees for learning latent variable models emphasizing on the overcomplete regime, where the dimensionality of the latent space exceeds...
热度：15
3Lecture 20: Emotion, Motivation, and Volition 1[20讲：情感，动机，和意志1]
Michael Martinez(加州大学欧文分校) Emotion, Motivation, and Volition
热度：66
Michael Martinez(加州大学欧文分校) Emotion, Motivation, and Volition
热度：66
4
5The strength of evidence versus the power of belief: Are we all Bayesians?[证据与信仰的力量：我们都是独立的?]
Jessica Utts(加州大学欧文分校) Although statisticians have the job of making conclusions based on data, for many questions in science and society prior beliefs are strong and may ta...
热度：29
Jessica Utts(加州大学欧文分校) Although statisticians have the job of making conclusions based on data, for many questions in science and society prior beliefs are strong and may ta...
热度：29
6Communication Chains and Multitasking[通信链和多任务]
Norman Makoto Su(加州大学欧文分校) Observations revealed that information workers interact in“chains” of interactions, switching organizational contexts and communication me...
热度：33
Norman Makoto Su(加州大学欧文分校) Observations revealed that information workers interact in“chains” of interactions, switching organizational contexts and communication me...
热度：33
7Do We Need More Training Data or Better Models for Object Detection?[我们需要更多的训练数据还是更好的对象检测模型?]
Charless C. Fowlkes(加州大学欧文分校) Datasets for training object recognition systems are steadily growing in size. This paper investigates the question of whether existing detectors will...
热度：73
Charless C. Fowlkes(加州大学欧文分校) Datasets for training object recognition systems are steadily growing in size. This paper investigates the question of whether existing detectors will...
热度：73
8Analyzing Text and Social Network Data with Probabilistic Models[使用概率模型分析文本和社交网络数据]
Padhraic Smyth(加州大学欧文分校) Exploring and understanding large text and social network data sets is of increasing interest across multiple fields, in computer science, social scie...
热度：44
Padhraic Smyth(加州大学欧文分校) Exploring and understanding large text and social network data sets is of increasing interest across multiple fields, in computer science, social scie...
热度：44
9Analyzing 3D Objects in Cluttered Images[分析杂乱图像中的三维对象]
Mohsen Hejrati(加州大学欧文分校) We present an approach to detecting and analyzing the 3D configuration of objects in real-world images with heavy occlusion and clutter. We focus on t...
热度：67
Mohsen Hejrati(加州大学欧文分校) We present an approach to detecting and analyzing the 3D configuration of objects in real-world images with heavy occlusion and clutter. We focus on t...
热度：67
1 1/1