Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 9
Video in druga učna gradiva
Oznake: computer science;information extraction
We study the standard retrieval task of ranking a fixed set of items given a previously unseen query and pose it as the half transductive ranking problem. The task is transductive as the set of items is fixed. Transductive representations (where the vector representation of each example is learned) ...
Leto: 2010 Vir: videolectures.net
Video in druga učna gradiva
Oznake:
We show how the regularizer of Transductive Support Vector Machines (TSVM) can be trained by stochastic gradient descent for linear models and multi-layer architectures. The resulting methods can be trained online, have vastly superior training and testing speed to existing TSVM algorithms, can enco ...
Leto: 2008 Vir: videolectures.net
Video in druga učna gradiva
Oznake: computer science;machine learning;artificial intelligence
Leto: 2008 Vir: videolectures.net
Video in druga učna gradiva
Oznake:
Leto: 2008 Vir: videolectures.net
Video in druga učna gradiva
Oznake: computer science;machine learning;semi-supervised learning
We show how nonlinear embedding algorithms popular for use with shallow semi-supervised learning techniques such as kernel methods can be applied to deep multi-layer architectures, either as a regularizer at the output layer, or on each layer of the architecture. This provides a simple alternative t ...
Leto: 2009 Vir: videolectures.net
Video in druga učna gradiva
Oznake: computer science;machine learning;semi-supervised learning
Labeling data is expensive, whilst unlabeled data is often abundant and cheap to collect. Semi-supervised learning algorithms that can use both types of data can perform significantly better than supervised algorithms that use labeled data alone. However, for such gains to be observed, the amoun ...
Leto: 2007 Vir: videolectures.net
Video in druga učna gradiva
Oznake: computer science;machine learning
Leto: 2013 Vir: videolectures.net
Video in druga učna gradiva
Oznake: computer science;natural language processing
This tutorial will describe recent advances in deep learning techniques for Natural Language Processing (NLP). Traditional NLP approaches favour shallow systems, possibly cascaded, with adequate hand-crafted features. In constrast, we are interested in end-to-end architectures: these systems include ...
Leto: 2009 Vir: videolectures.net
Video in druga učna gradiva
Oznake: computer science;machine learning;clustering
We present a new framework for large-scale data clustering. The main idea is to modify functional dimensionality reduction techniques to directly optimize over discrete labels using stochastic gradient descent. Compared to methods like spectral clustering our approach solves a single optimization pr ...
Leto: 2008 Vir: videolectures.net
Št. zadetkov: 9
Ključne besede:
Leto izdaje:
Repozitorij:
Tipologija:
Jezik: