|
|
 |
|
|
| Modeling Human Sentence Processing |
 |
Google Tech Talks
April, 17 2008
ABSTRACT
Modeling human sentence-processing can help
us both better understand how the brain
processes language, and also help improve
user interfaces. For example, our systems
could compare different (computer-generated)
sentences and produce ones that are easiest
to understand.
I will talk about my work on evaluating
theories about syntactic processing
difficulty on a large eye-tracking corpus,
and present a model of sentence processing
which uses an incremental, fully connected
parsing strategy.
Speaker: Vera Demberg
Vera Demberg is a Ph.D. student in
Computational Linguistics from the University
of Edinburgh, Scotland. Her research focus is
on building computational models of human
sentence processing.
Vera obtained a Diplom (MSc) in Computational
Linguistics from Stuttgart University, and a
MSc in Artificial Intelligence from the
University of Edinburgh. She has published
papers in a number of top venues for language
processing and psycholinguistic research,
including ACL, EACL, CogSci and Cognition.
For her PhD research, she's been awarded the
AMLaP Young Scientist Award for best platform
presentation by a junior scientist. She was a
finalist for the Google Europe Anita Borg
Memorial Scholarship in 2007.
Tags : google techtalks techtalk engedu talk talks googletechtalks education |
|
Affichage : 8202
Durée : 2975 s |
| Simple interactive 3D modeling for all |
 |
Google Tech Talks
April, 15 2008
ABSTRACT
The recent increase in demand for 3D content,
for a wide variety of purposes, has led to a
corresponding increase in the number and
diversity of people using 3D modeling
software. It has also amplified the pressure
to deliver 3D models on tight budgets, and at
pace. These combined pressures have driven an
increase in the sophistication of 3D
modelling software, but also a new focus on
its usability. VideoTrace represents a
significant change in the way 3D models are
made, and exemplifies a new kind of interface
design. The VideoTrace user sketches the
shape they require over a frame of a video
sequence, and automated image analysis
techniques generate the model. The interface
is thus intuitive, and easy to use, but
supported by strong mathematical analysis. It
allows unskilled users to achieve models that
would be impossible using more conventional
modelling software, and skilled users to
dramatically improve their accuracy and
productivity.
Speaker: Anton van den Hengel
Anton van den Hengel is the Director of the
Australian Centre for Visual Technologies, a
Director of PunchCard Visual Technologies Pty
Ltd, and an Associate Professor in Computer
Vision at the University of Adelaide, South
Australia. Dr van den Hengel's primary
research interests are in interactive 3D
modeling from image sets and large-scale
video surveillance.
Tags : google techtalks techtalk engedu talk talks googletechtalks education |
|
Affichage : 9899
Durée : 3171 s |
| Bayesian nonparametrics in document and language modeling |
 |
Google Tech Talks
August 28, 2008
ABSTRACT
Bayesian nonparametric models have garnered
significant attention in recent years in both
the machine learning and statistics
communities. These are highly flexible models
whose complexity grows with the amount of
data, and are nice approaches to addressing
the common problem of model selection. In
this talk I shall first give a brief overview
of Dirichlet processes and infinite mixture
models, the cornerstone of Bayesian
nonparametric models. Then I shall introduce
the hierarchical Dirichlet process, a
Bayesian nonparametric model for problems
involving multiple related groups of data. I
illustrate the use of hierarchical Dirichlet
processes using some applications to document
and language modelling.
Speaker: Yee Whye Teh
I am interested in statistical machine
learning and its applications. Specifically,
I look into theories, models and
methodologies to make graphical models
applicable to large and complex problems. I
am also keen on deploying the knowledge
gained in applications ranging from natural
language processing, to machine vision to
biological problems.
I studied Computer Science and Mathematics at
the University of Waterloo, obtaining my
B.Math. in 1997. Then I embarked on my
graduate studies at the University of Toronto
under the tutelage of Geoffrey Hinton.
Between 1999 and 2001 I spent two years in
London England at the Gatsby Computational
Neuroscience Unit where Geoff was the
founding director. In 2001 we returned to
Toronto and I finished my Ph.D. in 2003.
Immediately I started a postdoc with Michael
Jordan at UC Berkeley, finishing in 2004.
Starting in January 2007, I am now a lecturer
back at the Gatsby Unit.
Tags : google techtalks techtalk engedu talk talks googletechtalks education |
|
Affichage : 3521
Durée : 3829 s |
| Data Modeling for the Database Developer, Designer & Admin. |
 |
DBAs, developers and designers are often
tasked with building and managing databases.
Especially when the database has been
developed by someone else, you have little to
no insight into the database structure. Join
Quest Software to learn more about Toad Data
Modeler and its features that provide:
* Database Design -- Create high-quality
database structures, generated automatically,
following standard best-practice design
methodologies
* Documentation -- Generate high-quality,
detailed reports for documenting existing
database structures
* Database Redesign -- Take existing
databases, re-design the model, and generate
the new design SQL
* Database Migration -- Generate out existing
database structures to a new database
platform for migration or copy to a different
database
AGENDA:
* Overview of Data Modeling
* Brief product overview and benefits
* Functionality demonstration
-- Create ER diagrams and generate SQL
scripts
-- Reverse engineer
-- Add self-relationship, use rolenames,
DDL preview
-- Data flow diagrams
* Overcoming common data modeling mistakes
* Q&A
Tags : data modeling database developer designer administrator quest software toad modeler management |
|
Affichage : 24392
Durée : 3493 s |
|
|
|
|
|
|
|
|
|
|
 |
| |
|
