Brains, Meaning and Corpus Statistics
- -
Google Tech Talks March 27, 3009 ABSTRACT Presented by Tom M. Mitchell E. Fredkin Professor and Department Head Machine Learning Department Carnegie Mellon University How does the human brain represent meanings of words and pictures in terms of the underlying neural activity? This talk will present our research using machine learning method... Read more
0 people like this
- -: Brains, Meaning and Corpus Statistics
March 30, 2009 (about 15 years ago)Google Tech Talks March 27, 3009 ABSTRACT Presented by Tom M. Mitchell E. Fredkin Professor and Department Head Machine Learning Department Carnegie Mellon University How does the human brain represent meanings of words and pictures in terms of the underlying neural activity? This talk will ...
0 people like this
- -: Non-Myopic Active Learning: A Reinforcement Learning Approac
March 30, 2009 (about 15 years ago)Google Tech Talk March 16, 2009 ABSTRACT Non-Myopic Active Learning: A Reinforcement Learning Approach Presented by Pascal Poupart, University of Waterloo Active learning considers the problem of actively choosing the training data. This is particularly useful in settings where the training da...
0 people like this
- -: On the Design of Bayes Consistent Loss Functions for Classification
September 2, 2010 (over 13 years ago)Google Tech Talk July 30, 2010 ABSTRACT Presented by Hamed Masnadi-Shirazi. The machine learning problem of classifier design is studied from the perspective of probability elicitation, in statistics. This shows that the standard approach of proceeding from the specification of a loss, to the ...
0 people like this
- -: 確率密度比を用いた新しい機械学習アルゴリズム
October 29, 2010 (over 13 years ago)Google Tech Talk October 4, 2010 Presented by Masashi Sugiyama, Makoto Yamada, Hirotaka Hachiya [Japanese Audio] 確率密度比を用いた新しい機械学習アルゴリズム (English : Density Ratio Estimation: A New Versatile Tool for Machine Learning) Speaker 1: 杉山将 （東京工業大学 准教授） Title： 確率密度比を用いた新しい機械学習アルゴリズム 統計的機械学習の多くの問題は，データを生...
0 people like this
- -: Development of Large-Scale Grammars Through Corpus Construction (Japanese Audio)
November 5, 2010 (over 13 years ago)Google Tech Talk 14:00- JST Oct 27 2010 At Google Japan (Japanese Audio) Speaker : Yusuke Miyao (宮尾祐介) Bio : http://www.nii.ac.jp/en/faculty/digital_content/MIYAO-Yusuke/ Affiliation : National Institute of Informatics (国立情報学研究所) Language : spoken in Japanese and slides in English Title : Deve...
0 people like this
- -: Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning
April 11, 2011 (about 13 years ago)Bay Area Vision Meeting (more info below) Unsupervised Feature Learning and Deep Learning Presented by Andrew Ng March 7, 2011 ABSTRACT Despite machine learning's numerous successes, applying machine learning to a new problem usually means spending a long time hand-designing the input represent...
0 people like this
- -: Where Did This Code Come From? Discovering the Provenance of Program Binaries
May 3, 2011 (about 13 years ago)Google Tech Talk (more info below) April 22, 2011 Presented by Nathan Rosenblum, UW-Madison ABSTRACT Where did this binary come from? How was it compiled? What language did the programmer choose? Who wrote this code? These questions rarely occur to most computer users, but for analysts working...
0 people like this
- -: Machine Learning in Support of Family Coordination
September 12, 2011 (over 12 years ago)Google Tech Talk (more info below) June 1, 2011 Presented by Scott Davidoff, Ph.D. ABSTRACT This talk describes how my work with busy families: (1) identifies how their coordination breaks down (from 3 years of fieldwork and experience prototyping) (2) Identifies how we can apply unsupervised ...
0 people like this
- -: TEDxUVM 2011 - Gary Johnson - Modelling Ecosystem Services under Uncertainty with ARIES
November 15, 2011 (over 12 years ago)GARY JOHNSON Gary Johnson models the spatial flow of services from ecosystems to people and changes to these services by different management scenarios. His research interests include ecosystem service modelling and simulation, network flow optimization and substitutability, hierarchical modellin...
0 people like this(9 results)