Sciweavers

Share
AAAI
2015
3 years 11 months ago
Tensor-Variate Restricted Boltzmann Machines
Restricted Boltzmann Machines (RBMs) are an important class of latent variable models for representing vector data. An under-explored area is multimode data, where each data point...
Tu Dinh Nguyen, Truyen Tran, Dinh Q. Phung, Svetha...
AAAI
2015
3 years 11 months ago
A Novel Neural Topic Model and Its Supervised Extension
Topic modeling techniques have the benefits of modeling words and documents uniformly under a probabilistic framework. However, they also suffer from the limitations of sensitivi...
Ziqiang Cao, Sujian Li, Yang Liu, Wenjie Li, Heng ...
AAAI
2015
3 years 11 months ago
A Probabilistic Model for Bursty Topic Discovery in Microblogs
Bursty topics discovery in microblogs is important for people to grasp essential and valuable information. However, the task is challenging since microblog posts are particularly ...
Xiaohui Yan, Jiafeng Guo, Yanyan Lan, Jun Xu, Xueq...
AAAI
2015
3 years 11 months ago
Complexity Results for Compressing Optimal Paths
In this work we give a first tractability analysis of Compressed Path Databases, space efficient oracles used to very quickly identify the first arc on a shortest path. We stud...
Adi Botea, Ben Strasser, Daniel Harabor
AAAI
2015
4 years 3 days ago
Optimizing the CVaR via Sampling
Conditional Value at Risk (CVaR) is a prominent risk measure that is being used extensively in various domains. We develop a new formula for the gradient of the CVaR in the form o...
Aviv Tamar, Yonatan Glassner, Shie Mannor
AAAI
2015
4 years 3 days ago
Loss-Calibrated Monte Carlo Action Selection
Bayesian decision-theory underpins robust decisionmaking in applications ranging from plant control to robotics where hedging action selection against state uncertainty is critica...
Ehsan Abbasnejad, Justin Domke, Scott Sanner
AAAI
2015
4 years 3 days ago
Steering Evolution Strategically: Computational Game Theory and Opponent Exploitation for Treatment Planning, Drug Design, and S
Living organisms adapt to challenges through evolution and adaptation. This has proven to be a key difficulty in developing therapies, since the organisms develop resistance. I p...
Tuomas Sandholm
AAAI
2015
4 years 3 days ago
Real-Time Symbolic Dynamic Programming
Recent advances in Symbolic Dynamic Programming (SDP) combined with the extended algebraic decision diagram (XADD) have provided exact solutions for expressive subclasses of fini...
Luis Gustavo Rocha Vianna, Leliane N. de Barros, S...
AAAI
2015
4 years 3 days ago
Robust Subspace Clustering via Thresholding Ridge Regression
Given a data set from a union of multiple linear subspaces, a robust subspace clustering algorithm fits each group of data points with a low-dimensional subspace and then cluster...
Xi Peng 0001, Zhang Yi 0001, Huajin Tang
AAAI
2015
4 years 3 days ago
HACKAR: Helpful Advice for Code Knowledge and Attack Resilience
This paper describes a novel combination of Java program analysis and automated learning and planning architecture to the domain of Java vulnerability analysis. The key feature of...
Ugur Kuter, Mark H. Burstein, J. Benton, Daniel Br...
books