If you are looking for an answer to the question What is Artificial Intelligence? and you only have a minute, then here's the definition the Association for the Advancement of Artificial Intelligence offers on its home page: "the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines."
However, if you are fortunate enough to have more than a minute, then please get ready to embark upon an exciting journey exploring AI (but beware, it could last a lifetime) …
We consider the problem of learning Relational Logistic Regression (RLR). Unlike standard logistic regression, the features of RLRs are first-order formulae with associated weight vectors instead of scalar weights. We turn the problem of learning RLR to learning these vector-weighted formulae and develop a learning algorithm based on the recently successful functional-gradient boosting methods for probabilistic logic models. We derive the functional gradients and show how weights can be learned simultaneously in an efficient manner. Our empirical evaluation on standard and novel data sets demonstrates the superiority of our approach over other methods for learning RLR.
Planning with preferences has been employed extensively to quickly generate high-quality plans. However, it may be difficult for the human expert to supply this information without knowledge of the reasoning employed by the planner and the distribution of planning problems. We consider the problem of actively eliciting preferences from a human expert during the planning process. Specifically, we study this problem in the context of the Hierarchical Task Network (HTN) planning framework as it allows easy interaction with the human. Our experimental results on several diverse planning domains show that the preferences gathered using the proposed approach improve the quality and speed of the planner, while reducing the burden on the human expert.
Molina, Alejandro (TU Dortmund) | Vergari, Antonio (University of Bari) | Mauro, Nicola Di (University of Bari) | Natarajan, Sriraam (Indiana University) | Esposito, Floriana (University of Bari) | Kersting, Kristian (TU Darmstadt)
While all kinds of mixed data---from personal data, over panel and scientific data, to public and commercial data---are collected and stored, building probabilistic graphical models for these hybrid domains becomes more difficult. Users spend significant amounts of time in identifying the parametric form of the random variables (Gaussian, Poisson, Logit, etc.) involved and learning the mixed models. To make this difficult task easier, we propose the first trainable probabilistic deep architecture for hybrid domains that features tractable queries. It is based on Sum-Product Networks (SPNs) with piecewise polynomial leaf distributions together with novel nonparametric decomposition and conditioning steps using the Hirschfeld-Gebelein-Renyi Maximum Correlation Coefficient. This relieves the user from deciding a-priori the parametric form of the random variables but is still expressive enough to effectively approximate any distribution and permits efficient learning and inference.Our experiments show that the architecture, called Mixed SPNs, can indeed capture complex distributions across a wide range of hybrid domains.
While all kinds of mixed data -from personal data, over panel and scientific data, to public and commercial data- are collected and stored, building probabilistic graphical models for these hybrid domains becomes more difficult. Users spend significant amounts of time in identifying the parametric form of the random variables (Gaussian, Poisson, Logit, etc.) involved and learning the mixed models. To make this difficult task easier, we propose the first trainable probabilistic deep architecture for hybrid domains that features tractable queries. It is based on Sum-Product Networks (SPNs) with piecewise polynomial leave distributions together with novel nonparametric decomposition and conditioning steps using the Hirschfeld-Gebelein-R\'enyi Maximum Correlation Coefficient. This relieves the user from deciding a-priori the parametric form of the random variables but is still expressive enough to effectively approximate any continuous distribution and permits efficient learning and inference. Our empirical evidence shows that the architecture, called Mixed SPNs, can indeed capture complex distributions across a wide range of hybrid domains.
Multivariate count data are pervasive in science in the form of histograms, contingency tables and others. Previous work on modeling this type of distributions do not allow for fast and tractable inference. In this paper we present a novel Poisson graphical model, the first based on sum product networks, called PSPN, allowing for positive as well as negative dependencies. We present algorithms for learning tree PSPNs from data as well as for tractable inference via symbolic evaluation. With these, information-theoretic measures such as entropy, mutual information, and distances among count variables can be computed without resorting to approximations. Additionally, we show a connection between PSPNs and LDA, linking the structure of tree PSPNs to a hierarchy of topics. The experimental results on several synthetic and real world datasets demonstrate that PSPN often outperform state-of-the-art while remaining tractable.
This paper presents a knowledge-based approach to the task of learning and identifying galaxies from their images. To this effect, we propose a crowd-sourced pipeline approach that employs two systems - case based and rule based systems. First, the approach extracts morphological features i.e. features describing the structure of the galaxy such as its shape, central characteristics e.g., has a bar or bulge at its center)etc., using computer vision techniques. Then it employs a case based reasoning system and a rule based system to perform the classification task. Our initial results show that this pipeline is effective in learning reasonably accurate models on this complex task.
Das, Mayukh (Indiana University Bloomington) | Islam, Md. Rakibul (Washington State University) | Doppa, Janardhan Rao (Jana) (Washington State University) | Roth, Dan (University of Illinois at Urbana-Champaign) | Natarajan, Sriraam (Indiana University Bloomington)
We consider the problem of actively eliciting preferences from a human by a planning system. While prior work in planning have explored the use of domain knowledge and preferences, they assume that the knowledge must be provided before the planner starts the planning process. Our work is in building more collaborative systems where a system can solicit advice as needed. We verify empirically that this approach lead to faster and better solutions, while reducing the burden on the human expert.
Many real world applications in medicine, biology, communication networks, web mining, and economics, among others, involve modeling and learning structured stochastic processes that evolve over continuous time. Existing approaches, however, have focused on propositional domains only. Without extensive feature engineering, it is difficult-if not impossible-to apply them within relational domains where we may have varying number of objects and relations among them. We therefore develop the first relational representation called Relational Continuous-Time Bayesian Networks (RCTBNs) that can address this challenge. It features a nonparametric learning method that allows for efficiently learning the complex dependencies and their strengths simultaneously from sequence data. Our experimental results demonstrate that RCTBNs can learn as effectively as state-of-the-art approaches for propositional tasks while modeling relational tasks faithfully.
Morris, Robert (NASA) | Bonet, Blai (Universidad Simón Bolívar) | Cavazza, Marc (Teesside University) | desJardins, Marie (University of Maryland, Baltimore County) | Felner, Ariel (BenGurion University) | Hawes, Nick (University of Birmingham) | Knox, Brad (Massachusetts Institute of Technology) | Koenig, Sven (University of Southern California) | Konidaris, George (Massachusetts Institute of Technology,) | Lang, Jérôme ((Université ParisDauphine) | López, Carlos Linares (Universidad Carlos III de Madrid) | Magazzeni, Daniele (King's College London) | McGovern, Amy (University of Oklahoma) | Natarajan, Sriraam (Indiana University) | Sturtevant, Nathan R. (University of Denver,) | Thielscher, Michael (University New South Wales) | Yeoh, William (New Mexico State University) | Sardina, Sebastian (RMIT University) | Wagstaff, Kiri (Jet Propulsion Laboratory)
The Twenty-Ninth AAAI Conference on Artificial Intelligence, (AAAI-15) was held in January 2015 in Austin, Texas (USA) The conference program was cochaired by Sven Koenig and Blai Bonet. This report contains reflective summaries of the main conference, the robotics program, the AI and robotics workshop, the virtual agent exhibition, the what's hot track, the competition panel, the senior member track, student and outreach activities, the student abstract and poster program, the doctoral consortium, the women's mentoring event, and the demonstrations program.