Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- ArticleJuly 2016
VIPR: an interactive tool for meaningful visualization of high-dimensional data
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4274–4275Analysis, pattern discovery, and decision support all can benefit greatly from informative and interpretable visualizations, especially of high-dimensional data. Informative Projection Ensemble (IPE) methodology has proven effective in finding ...
- ArticleJuly 2016
Practical 3D tracking using low-cost cameras
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4236–4237There exist solutions for tracking of objects in 3D space involving hi-tech cameras and powerful computer systems capable of tracking many objects in large dynamic space simultaneously in real time. On the other hand, there are situations where such ...
- ArticleJuly 2016
Repairing general-purpose ASR output to improve accuracy of spoken sentences in specific domains using artificial development approach
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4234–4235General-purpose speech engines are trained on large corpus. However, studies and experiments have shown that when such engines are used to recognize spoken sentences in specific domains they may not produce accurate ASR output. Further, the accent and ...
- ArticleJuly 2016
Online Bellman residual and temporal difference algorithms with predictive error guarantees
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4213–4217We establish connections from optimizing Bellman Residual and Temporal Difference Loss to worst-case long-term predictive error. In the online learning framework, learning takes place over a sequence of trials with the goal of predicting a future ...
-
- ArticleJuly 2016
Proximal gradient temporal difference learning algorithms
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4195–4199In this paper, we describe proximal gradient temporal difference learning, which provides a principled way for designing and analyzing true stochastic gradient temporal difference learning algorithms. We show how gradient TD (GTD) reinforcement learning ...
- ArticleJuly 2016
Deep neural decision forests
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4190–4194We present a novel approach to enrich classification trees with the representation learning ability of deep (neural) networks within an end-to-end trainable architecture. We combine these two worlds via a stochastic and differentiable decision tree ...
- ArticleJuly 2016
Observability, identifiability and sensitivity of vision-aided inertial navigation
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4170–4174We analyze the observability of 3-D position and orientation from the fusion of visual and inertial sensors. The model contains unknown parameters, such as sensor biases, and so the problem is usually cast as a mixed filtering/identification problem, ...
- ArticleJuly 2016
Learning qualitative spatial relations for robotic navigation
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4130–4134We consider the problem of robots following natural language commands through previously unknown outdoor environments. A robot receives commands in natural language, such as "Navigate around the building to the car left of the fire hydrant and near the ...
- ArticleJuly 2016
Optimal and adaptive algorithms for online boosting
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4120–4124We study online boosting, the task of converting any weak online learner into a strong online learner. Based on a novel and natural definition of weak online learnability, we develop two online boosting algorithms. The first algorithm is an online ...
- ArticleJuly 2016
On the properties of GZ-aggregates in answer set programming
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4105–4109Gelfond and Zhang recently proposed a new stable model semantics based on Vicious Circle Principle in order to improve the interpretation of logic programs with aggregates. A detailed complexity analysis of coherence testing and cautious reasoning under ...
- ArticleJuly 2016
From non-convex aggregates to monotone aggregates in ASP
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4100–4104In answer set programming, knowledge involving sets of objects collectively is naturally represented by aggregates, which are rewritten into simpler forms known as monotone aggregates by current implementations. However, there is a complexity gap ...
- ArticleJuly 2016
Adversarial AI
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4094–4097In recent years AI research has had an increasing role in models and algorithms for security problems. Game theoretic models of security, and Stackelberg security games in particular, have received special attention, in part because these models and ...
- ArticleJuly 2016
Plausible reasoning based on qualitative entity embeddings
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4078–4081Formalizing and automating aspects of human plausible reasoning is an important challenge for the field of artificial intelligence. Practical advances, however, are hampered by the fact that most forms of plausible reasoning rely on background knowledge ...
- ArticleJuly 2016
Open information extraction systems and downstream applications
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4074–4077Open Information Extraction (Open IE) extracts textual tuples comprising relation phrases and argument phrases from within a sentence, without requiring a pre-specified relation vocabulary. In this paper we first describe a decade of our progress on ...
- ArticleJuly 2016
Towards intelligent visual understanding under minimal supervision
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4046–4047Because of playing one of the most important roles in the artificial intelligent systems like robots, visual understanding has gained vast interests in the past few decades. Most of the existing approaches need human labelled training data to train the ...
- ArticleJuly 2016
A framework for anomaly reasoning: interpretation through concept formation for knowledge transfer and lifelong learning
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4040–4041I am developing a framework for anomaly reasoning for agents that plan and learn in complex, sometimes unfamiliar domains. Anomaly reasoning encompasses recognizing, interpreting, and reacting to unfamiliar objects or familiar objects appearing in ...
- ArticleJuly 2016
Automated narrative information extraction using non-linear pipelines
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4036–4037Our research focuses on the problem of automatically acquiring structured narrative information from natural language. We have focused on character extraction and narrative role identification from a corpus of Slavic folktales. To address natural ...
- ArticleJuly 2016
Integrating social network structure into online feature selection
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial IntelligencePages 4032–4033Short-texts accentuate the challenges posed by the high feature space dimensionality of text learning tasks. The linked nature of social data causes new dimensions to be added to the feature space, which, also becomes sparser. Thus, efficient and ...