public marks

PUBLIC MARKS with tag hierarchy






YouTube - Visual Perception with Deep Learning

by ogrisel (via)
A long-term goal of Machine Learning research is to solve highly complex "intelligent" tasks, such as visual perception auditory perception, and language understanding. To reach that goal, the ML community must solve two problems: the Deep Learning Problem, and the Partition Function Problem. There is considerable theoretical and empirical evidence that complex tasks, such as invariant object recognition in vision, require "deep" architectures, composed of multiple layers of trainable non-linear modules. The Deep Learning Problem is related to the difficulty of training such deep architectures. Several methods have recently been proposed to train (or pre-train) deep architectures in an unsupervised fashion. Each layer of the deep architecture is composed of an encoder which computes a feature vector from the input, and a decoder which reconstructs the input from the features. A large number of such layers can be stacked and trained sequentially, thereby learning a deep hierarchy of features with increasing levels of abstraction. The training of each layer can be seen as shaping an energy landscape with low valleys around the training samples and high plateaus everywhere else. Forming these high plateaus constitute the so-called Partition Function problem. A particular class of methods for deep energy-based unsupervised learning will be described that solves the Partition Function problem by imposing sparsity constraints on the features. The method can learn multiple levels of sparse and overcomplete representations of data. When applied to natural image patches, the method produces hierarchies of filters similar to those found in the mammalian visual cortex. An application to category-level object recognition with invariance to pose and illumination will be described (with a live demo). Another application to vision-based navigation for off-road mobile robots will be described (with videos). The system autonomously learns to discriminate obstacles from traversable areas at long range.



by Xavier Lacot
"The problem of where to file: Is it possible to construct the perfect classification system?"

Internet Archive: Details: Jeff Hawkins, Numenta: "Prospects and Problems of Cortical Theory"

by ogrisel (via)
Jeff Hawkins, Numenta: "Prospects and Problems of Cortical Theory". This is the 10th and final talk given at the Redwood Center for Theoretical Neuroscience


On Intelligence

by YukuanBlog
《創智慧》,原書《On Intelligence》,作者 Hawkins 提出一套大腦新皮質(neocortex)運作的理論:

Feed of MSN Search's TOP 10 Catalog pages by topic

by access2
MSN Search makes results available as feeds, which makes it easy to aggregate related "topic" pages from our bookstore, regardless of their postion in Amazon's hierarchy. Makes browsing faster and searching smarter. (BETA)


Active users

last mark : 05/03/2015 15:07

last mark : 11/01/2012 13:04

last mark : 22/02/2009 09:10

last mark : 13/10/2008 06:57

last mark : 24/06/2008 21:12

Xavier Lacot
last mark : 01/10/2007 07:31

last mark : 01/08/2006 06:27

last mark : 29/03/2006 20:15

last mark : 25/03/2006 15:06

last mark : 07/06/2005 08:57