The following is the list of accepted tutorials for IJCAI 2015.
Please check the URLs provided for each tutorial; presentation slides and other relevant material is currently becoming available.
T1: AI for Smart City Innovations with Open Data - Biplav Srivastava
The area of smart city seeks to use information and communication technology (ICT) to engage citizens and seek participative ways to reduce wastage and achieve positive, measurable, economic and societal outcomes. In this tutorial, we will make early and experienced researchers aware, and equip them to create, societal innovations with AI techniques like semantics, knowledge representation, data integration, machine learning, planning, scheduling, logic, trust and agents, and open data, that is increasingly, readily available, globally from government and other sources.
T2: Argumentation in Artificial Intelligence: 20 Years after Dung’s Work - Federico Cerutti
Argumentation technology is a rich interdisciplinary area of research that, in the last twenty years, has emerged as one of the most promising paradigms for commonsense reasoning and conflict resolution in a great variety of domains. In this tutorial we provide an extensive description of the research in this field, the well-established results, as well as implementations, applications, and open questions.
T3: Termination Analysis of Logic Programs - Sergio Greco and Cristian Molinaro
Checking termination of the evaluation of logic programs is an important problem which finds applicability in a variety of settings such as answer set programming, logic-based query languages, chase termination, and ontological query answering. As the problem is in general undecidable, there have been several proposals aiming at defining restricted classes of logic programs whose evaluation is guaranteed to terminate. The tutorial presents and compares the main approaches in this area by highlighting the different perspectives they adopt in logic program analysis and their applications to different domains.
T4: Probabilistic Programming - Luc De Raedt and Angelika Kimmig
Probabilistic programming is an emerging subfield of artificial intelligence that extends traditional programming languages and constructs with primitives to support probabilistic inference and learning. Probabilistic programming is closely related to statistical relational learning but is different in that it focuses on a programming language perspective rather than on a graphical model one. This tutorial will provide a gentle introduction to the newly emerging area of probabilistic programming, focusing on the underlying concepts and primitives on which these languages are based. We shall also discuss how logical and probabilistic inference can be combined and how they are used for learning, and sketch some example applications.
T5: Automatic Synthesis & Composition of Agent Behaviors - Giuseppe De Giacomo, Fabio Patrizi and Sebastian Sardina
The tutorial will survey some of the major developments in agent behavior synthesis and composition. The tutorial will cover the problem specification, the various techniques developed to solve it, and the relationship with various problems in several areas of CS and AI.
T6: Multi-Agent Oriented Programming - Olivier Boissier, Rafael H. Bordini, Jomi Fred Hübner, Alessandro Ricci, and Jaime Simao Sichman
This tutorial shows how one should program and integrate three complementary MAS dimensions: agents, organisations and environments. It is illustrated by using the JaCaMo framework.
T7: CANCELLED - Temporal logic applied to Dynamic Pattern Recognition. Case Study: Chronicles - Jose Aguilar
In this tutorial we will study recent theoretical advances in Temporal Logic, emphasizing the approach called Chronicles. Particularly, we will analyze different approaches to temporal reasoning and learning. Next, we will study depth the chronicles approach, giving some examples of application in dynamic pattern recognition problems in the context of ambient intelligence (AmI), autonomous communication systems, enterprise service bus (ESB), etc. Finally, we will compare these applications based on chronicles with other solutions.
T8: Advances in Combinatorial Optimization for Graphical Models - Rina Dechter, Radu Marinescu, Alexander Ihler, Lars Otten
This tutorial will present state-of-the-art algorithms for solving combinatorial optimization tasks in different graphical models (Bayesian networks, Markov networks, Constraint networks) and demonstrate their applicability to problems in scheduling, design and diagnosis, bio-informatics tasks, and web-based applications.
T9: Lifelong Machine Learning in the Big Data Era - Zhiyuan Chen and Bing Liu
Introduce the important problem and existing techniques of lifelong machine learning (or lifelong learning) and discuss opportunities and challenges of big data for lifelong machine learning.
T10: Constraint (Logic) Programming - Roman Bartak
This tutorial will explain mainstream constraint satisfaction techniques, namely core consistency algorithms such as arc consistency and their integration with backtracking search. It will also give examples of modeling problems as constraint satisfaction problems.
T11: Foundations of Web Personalization and Recommender Systems - Jill Freyne and Shlomo Berkovsky
The sheer abundance of available information and products raise the need for personalized applications and recommender systems that provide services and recommendations tailored to users' preferences and needs. This tutorial provides the participants with broad overview and thorough understanding of algorithmic techniques and practically deployed applications of personalized technologies
T12: Crowd Computing: From Human Computation to Collective Intelligence - Mark Klein and Ana Cristina B. Garcia
This tutorial will review the promise, design principles, and future challenges for crowd computing systems i.e. systems where crowds (of people) and clouds (of computers) work together to make better decisions than any could make individually.
T13: CANCELLED - Spectral Machines: Algorithms, Software, and Applications - Ian Davidson and Xiang Wang -
T14: Evolutionary Semantics for Language Grounding in Robots - Luc Steels and Michael Spranger
The tutorial focuses on how robots could make use of sophisticated compositional semantics that is grounded in their sensorimotor systems and evolves with changing contexts and goals. It surveys the issues to be solved, past experiments, and current techniques, illustrated with concrete case studies.
T15: Multi-Objective Decision Making - Shimon Whiteson and Diederik M. Roijers
Many real-world tasks require making decisions that involve multiple possibly conflicting objectives. This tutorial provides an introduction to multi-objective problem formalisms, solution concepts, state-of-the-art algorithms, recent applications, and open questions.
T16: Musical Metacreation - Philippe Pasquier, Arne Eigenfeldt, Oliver Bown
This tutorial aims at introducing the field of musical metacreation (MUME) and its current developments, promises, and challenges, with a particular focus on IJCAI-relevant aspects of the field MUME involves using tools and techniques from artificial intelligence, artificial life, and machine learning, themselves often inspired by cognitive and life sciences, to endow machines with musical creativity. Concretely, it brings together artists, practitioners and researchers interested in developing systems that autonomously (or interactively) recognize, learn, represent, compose, complete, accompany, or interpret musical data.
T17: The Evolution of Natural Language Understanding and Prediction Technologies: from Formal Grammars to Large Scale Machine Learning - Nicolae Duta
This tutorial is aimed at providing the IJCAI community an overview of the deployed natural language technologies and their historical evolution. We review two fundamental problems involving natural language: the language prediction problem and the language understanding problem. The presentation focuses on the theory and algorithms used to build voiced/text-based human-computer interaction systems from the early automated directory assistance to today’s smart-phone virtual assistants and semantic web search.
T18: Answer Set Solving in Practice: Advanced techniques - Martin Gebser, Roland Kaminski, Javier Romero, and Torsten Schaub
This tutorial introduces advanced problem solving techniques addressing the growing range of applications of Answer Set Programming in practice; its particular focus lies on recent techniques needed for embedding ASP in complex software environments.
T19: Diffusion in Social Networks - Paulo Shakarian
This tutorial shall provide an overview of the major results on diffusion in social networks covering a wide variety of diffusion models from multiple disciplines (computer science, physics, biology), including the independent cascade and linear threshold models, deterministic tipping point models, graphical voter models, evolutionary graph theory models, and graphical epidemiology models (i.e. SIR/SIS). In particular, we shall focus on how these models have been studied in various artificial intelligence paradigms, such as agent-based modelling, logic programming, game theory, learning, and data mining.
T20: The Internet of Things and Multiagent Systems - Munindar P. Singh and Amit K. Chopra
This tutorial introduces the Internet of Things (IoT), a rapidly expanding technology area. It describes how ideas from artificial intelligence—specifically, multiagent systems—can support the IoT as well as additional research advances needed in the relevant areas to help realize the IoT.
T21: Context-Awareness - Juan Carlos Augusto
Context-awareness is at the core of all applications in Intelligent Environments. This Tutorial will provide participants the knowledge to understand what context-awareness is, as well as the latest achievements and challenges in this active area of research.
T22: Sensitivity Analysis in Graphical Models with Imprecise Probabilities: Applications to Robust Data Mining and Decision Support Systems - Cassio de Campos, Alessandro Antonucci, and Giorgio Corani
Probabilistic graphical models such as Bayesian networks or Markov random fields need a sharp estimate of their parameters: such a precise elicitation might be unreliable because of limited expert knowledge or few/incomplete data to learn from. During this tutorial we present a number of optimization techniques, based on the theory of imprecise probability, to analyze the sensitivity of the inferences in graphical models with respect to perturbations in the parameters; applications to single- and multi-dimensional classification, computer vision, and decision support in knowledge-based expert systems are also provided.
T23: Formal Concept Analysis for Knowledge Processing - Sergei O. Kuznetsov and Amedeo Napoli
This tutorial on Formal Concept Analysis (FCA) called “Formal Concept Analysis for Knowledge Processing” will introduce and make precise how FCA and variations, i.e. pattern structures and Relational Concept Analysis (RCA), can be used for knowledge and data processing. FCA provides a complete framework with well founded, efficient and practical algorithms, for dealing with heterogeneous data in many situations and application domains involving knowledge-based systems and ontology engineering (e.g. semantic web). In addition, FCA and variations are closely related to modeling, learning and classification, as well as pattern mining and association rule extraction, which are very important tasks in data processing. Accordingly, this tutorial is aimed at providing the IJCAI community a better knowledge of FCA actual capabilities and to show the high interest of FCA and its variations in knowledge and data processing
T24: Implementing KR Approaches with Tweety - Matthias Thimm
The Tweety Libraries for Logical Aspects of Artificial Intelligence and Knowledge Representation is a comprehensive and ever-growing collection of Java libraries for implementing a diverse range of formalisms for knowledge representation and other neighboring fields. In this tutorial, a practical account is given on the capabilities of Tweety, its most important concepts, and how to use Tweety for own works.
T25: Visual Text Analytics - Evangelos Milios and Axel Soto
Visual text analytics combines statistical learning techniques with interactive visualizations for an effective understanding, and decision making on the basis of a large unstructured data corpus. This allows creating intelligent and exploratory systems that are useful for domain users, who may be experts on the data but not on text mining.
T26: Logic-based Merging - Ramon Pino Pérez
In this tutorial we will present the foundations of the belief merging operators: a model of fusion information based on logical representation of the information. We will give constructive methods for building operators aiming to merge pieces of information coming from several sources.
T27: CANCELLED Weakly Supervised Classification Problems - Jose A. Lozano, I. Inza, and J. Hernandez-Gonzalez
The tutorial puts together a new collection of supervised classification problems where the label information of the training instances and the prediction problem are nonstandard, showing different degrees of uncertainty (aka degree of supervision). Just to name a few of these problems: partial labels, label proportions or crowd learning can be found. A taxonomy of the problems together with the solutions proposed in the literature will be surveyed. A set of solved applications will be also shown.
T28: Representation of Collaborative Knowledge: from Knowledge Engineering to Knowledge Management - Nada Matta, Jason Dai and Francois Rauscher
KE approaches handle knowledge extraction and representation. We explain in this tutorial how KE is used in Knowledge Management and especially to tackle collaborative work.
T29: A new look at the system, algorithm, and theory foundations of scalable machine learning. - Eric P. Xing and Qirong Ho
The rise of Big Data has led to new demand for Machine Learning (ML) systems, in order to learn Big Models with millions to billions of parameters that promise sufficient capacity to analyze these massive datasets. In this tutorial, you will learn about a systematic overview of modern ML models and algorithms for such applications, the insight and challenges of employing them at Big Data and Big Model scales, the principles and design of distributed-parallel ML systems for executing these methods at scale, and the new theory and analysis necessary for understanding the behaviors and guarantees of these models, algorithms, and systems.