Sciweavers

AAAI
2008
13 years 6 months ago
Exposing Parameters of a Trained Dynamic Model for Interactive Music Creation
As machine learning (ML) systems emerge in end-user applications, learning algorithms and classifiers will need to be robust to an increasingly unpredictable operating environment...
Dan Morris, Ian Simon, Sumit Basu
AAAI
2008
13 years 6 months ago
Simulation-Based Approach to General Game Playing
The aim of General Game Playing (GGP) is to create intelligent agents that automatically learn how to play many different games at an expert level without any human intervention. ...
Hilmar Finnsson, Yngvi Björnsson
AAAI
2008
13 years 6 months ago
Efficient Memoization for Dynamic Programming with Ad-Hoc Constraints
We address the problem of effective reuse of subproblem solutions in dynamic programming. In dynamic programming, a memoed solution of a subproblem can be reused for another if th...
Joxan Jaffar, Andrew E. Santosa, Razvan Voicu
AAAI
2008
13 years 6 months ago
User Identification by Means of Sketched Stroke Features
We present preliminary results of using physical features of a user's sketching style, such as pen tilt and pressure, to identify a user from their sketched strokes.
Brian Eoff, Tracy Hammond
AAAI
2008
13 years 6 months ago
Prediction and Change Detection in Sequential Data for Interactive Applications
We consider the problems of sequential prediction and change detection that arise often in interactive applications: A semi-automatic predictor is applied to a time-series and is ...
Jun Zhou, Li Cheng, Walter F. Bischof
AAAI
2008
13 years 6 months ago
Reinforcement Learning for Vulnerability Assessment in Peer-to-Peer Networks
Proactive assessment of computer-network vulnerability to unknown future attacks is an important but unsolved computer security problem where AI techniques have significant impact...
Scott Dejmal, Alan Fern, Thinh Nguyen
AAAI
2008
13 years 6 months ago
Efficient Querying Relaxed Dominant Relationship between Product Items Based on Rank Aggregation
Current search engines cannot effectively rank those relational data, which exists on dynamic websites supported by online databases. In this study, to rank such structured data, ...
Zhenglu Yang, Lin Li, Masaru Kitsuregawa
AAAI
2008
13 years 6 months ago
Unknown Rewards in Finite-Horizon Domains
"Human computation" is a recent approach that extracts information from large numbers of Web users. reCAPTCHA is a human computation project that improves the process of...
Colin McMillen, Manuela M. Veloso
AAAI
2008
13 years 6 months ago
Coordination and Multi-Tasking Using EMT
We introduce a multi-model variant of the EMT-based control algorithm. The new algorithm, MM-EMT, is capable of balancing several control tasks expressed using separate dynamic mo...
Zinovi Rabinovich, Nir Pochter, Jeffrey S. Rosensc...
AAAI
2008
13 years 6 months ago
Zero-data Learning of New Tasks
We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...
Hugo Larochelle, Dumitru Erhan, Yoshua Bengio