Profile_bird

Hey there! mplab is using Twitter.

Twitter is a free service that lets you keep in touch with people through the exchange of quick, frequent answers to one simple question: What's happening? Join today to start receiving mplab's tweets.

Already using Twitter
from your phone? Click here.

mplab

  1. Robovie used as shopping companion http://www.youtube.com/watch?v=TneFT2hMKSY
  2. [Xiang et al.] Dynamic spatially smoothed regularization ensures boosting to select clustered but not scattered features.
  3. [Seeger.] Informax fMRI pulse seq. design, extends previous single 2d slice work to 3d volume optimization, which shows some improvement.
  4. [Berkes et al] No evidence of active sparsification in V1. They paralyzed some inputs of V1, the result mismatches sparse model prediction.
  5. [Zinkevich] An asynchronous parallel SGD implementation showed that delayed propagation of new gradient leads to faster convergence.
  6. [Cavagnaro] (standard D-opt) experiment design for human memory experiment. Compared 3 different short-term memory model.
  7. [Bengio et al.] class dependent feature selection, similar to "personal spam filter". Mixed norm regularization generate sparses features.
  8. [Schmidt] blind source separation with arbitrary linear/equality constraint on source. Solved using MCMC
  9. Vul gave a talk on an ideal observer model for multiple object tracking using particle filters. Accounts for human experiments. Poster 2nite
  10. Graph-based consensus maximization: incorporate grouping constraints with outputs of classification algorithms
  11. Hinton gave a talk on extending RBMs to higher order interactions and applying it to a range problems with impressive results.
  12. Hsu and Griffith use generative versus discriminative models of language learning to help give insight into the debate on nativism of lang.
  13. [Zoran and Weiss] reported that edge filter could be obtained from natural images using maximum tree dependency algorithms(nonsparse code!).
  14. [Ouyang and David] An Bayesian framework for realtime handdrawn sketch recognition with "component recog./context/continuity" likelihood.
  15. [Blaschko et al] joint learning and projecting labeled data onto the manifold created from unlabeled data improves regression performance.
  16. [Fujiwara et al.] Bayesian CCA to reconstruct visual stimuli from fMRI. The learned basis varies by eccentricity from 1px to 4px patterns.
  17. ROC or Accuracy? Corinna Cortes and Mehryar Mohri[nips04], Davis & Goadrich [ICML2006], Ulf Brefeld Tobias Scheffer[icml05]
  18. Sahand Negahban analyzes error bounds of sparse or low rank parameters in Lasso regression/covariance problem.
  19. Sergio Verdu gives a nice (invited) talk on "relative entropy". More 'EE' perspective such as compression/coding than CS though.
  20. Tony Torralba has a extensive and "exhausted" tutorial of object/scene recognition. 1 paper per slide! good summary but not very systematic