Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 10
Learning on Structured Data
David McAllester
Video in druga učna gradiva
Oznake: computer science;machine learning;structured data
Discriminative learning framework is one of the very successful fields of machine learning. The methods of this paradigm, such as Boosting, and Support Vector Machines have significantly advanced the state-of-the-art for classification by improving the accuracy and by increasing the applicability of ...
Leto: 2005 Vir: videolectures.net
Unsupervised Learning for Stereo Vision
David McAllester
Video in druga učna gradiva
Oznake: computer science;machine learning;computational learning theory
We consider the problem of learning to estimate depth from stereo image pairs. This can be formulated as unsupervised learning - the training pairs are not labeled with depth. We have formulated an algorithm which maximizes conditional likelihood the left image given right image in a model that invo ...
Leto: 2009 Vir: videolectures.net
Remembering Partha Niyogi
David McAllester
Video in druga učna gradiva
Oznake: physics;astronomy
Leto: 2010 Vir: videolectures.net
Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss
David McAllester
Video in druga učna gradiva
Oznake: computer science;machine learning;structured data;computational linguistics;machine translation
We consider latent structural versions of probit loss and ramp loss. We show that these surrogate loss functions are consistent in the strong sense that for any feature map (finite or infinite dimensional) they yield predictors approaching the infimum task loss achievable by any linear predictor ove ...
Leto: 2011 Vir: videolectures.net
Training Structured Predictors for Novel Loss Functions
David McAllester
Video in druga učna gradiva
Oznake:
As a motivation we consider the PASCAL image segmentation challenge. Given an image and a target class, such as person, the challenge is to segment the image into regions occupied by objects in that class (person foreground) and regions not occupied by that class (non-person background). At the pres ...
Leto: 2009 Vir: videolectures.net
Some PAC-Bayesian Theorems
David McAllester
Video in druga učna gradiva
Oznake: computer science;machine learning;bayesian learning
Leto: 2010 Vir: videolectures.net
A PAC-Bayesian Analysis of Dropouts
David McAllester
Video in druga učna gradiva
Oznake: computer science;machine learning;deep learning
Intuitively, a neural network that is robust to dropout perturbations should have better generalization properties - it should perform better on novel inputs. Stochastic model perturbation is the fundamental concept underlying PAC-Bayesian generalization theory. This talk will briefly summarize P ...
Leto: 2013 Vir: videolectures.net
Welcome
David McAllester , John Langford
Video in druga učna gradiva
Oznake: events
Leto: 2005 Vir: videolectures.net
Lunch debate 25.5.2005
Robert Schapire , Yann LeCun , John Langford , Yasemin Altun , Yoram Singer , David McAllester
Video in druga učna gradiva
Oznake: computer science;machine learning
Leto: 2005 Vir: videolectures.net
Lunch debate 23.5.2005
Sanjoy Dasgupta , Yann LeCun , David McAllester , John Langford , Yasemin Altun , Zoubin Ghahramani , Partha Niyogi
Video in druga učna gradiva
Oznake: events
Leto: 2005 Vir: videolectures.net
Št. zadetkov: 10
Ključne besede:
Leto izdaje:
Repozitorij:
Tipologija:
Jezik: