[UAI] Postdoc position in Geometric Methods for Deep and Reinforcement Learning at RIST
=== *Subject*: Postdoc position in Machine Learning (1 year, renewable up to 2.5 years) *Institution*: RIST - Romanian Institute of Science and Technology, Cluj-Napoca *Keywords*: Deep Learning, Reinforcement Learning, Stochastic Optimization, Optimization over Manifolds, Information Geometry, Riemannian Geometry *Application deadline*: 30 June 2018 (applicants are encouraged to apply earlier) *Salary*: around 2190 euro net *Official announcement*: http://rist.ro/en/details/news/postdoc-positio ns-in-deep-learning-and-machine-learning.html === Dear colleagues, the Romanian Institute of Science and Technology (RIST) has an opening for a postdoc position, in the context of the DeepRiemann project “Riemannian Optimization Methods for Deep Learning”, funded by European structural funds through the Competitiveness Operational Program (POC 2014-2020). The appointments will be for 1 year, with possible extensions up to 2.5 years. The DeepRiemann project aims at the design and analysis of novel training algorithms for Neural Networks in Deep Learning, by applying notions of Riemannian optimization and differential geometry. The task of the training a Neural Network is studied by employing tools from Optimization over Manifolds and Information Geometry, by casting the learning process to an optimization problem defined over a statistical manifold, i.e., a set of probability distributions. The project is highly interdisciplinary, with competences spanning from Machine Learning to Optimization, Deep Learning, Statistics, and Differential Geometry. The objectives of the project are multiple and include both theoretical and applied research, together with industrial activities oriented to transfer knowledge, from the institute to a startup or spin-off of the research group. The positions will be part of the new Machine Learning and Optimization group http://luigimalago.it/group.html, which performs research at the intersection of Machine Learning, Stochastic Optimization, Deep Learning, and Optimization over Manifolds, from the unifying perspective of Information Geometry. The group is one of two newly-formed groups in Machine Learning at RIST, where about 20 new postdoctoral research associates and research software developers will be hired by 2018. The official job announcement can be seen here: http://rist.ro/en/details/news/postdoc-positions-in-deep-lea rning-and-machine-learning.html Informal inquiries can be sent to Dr. Luigi Malagò , principal investigator of the DeepRiemann project. Application deadline: 30 June 2018 (applicants are encouraged to apply earlier) best regards, Luigi Malagò ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
[UAI] ACAI 2018 - Early Registration Deadline Approaching
The early registration deadline (June th) is approaching. http://acai2018.unife.it/ Important dates: 15 June early registration deadline 27 July late registration deadline The Advanced Course on AI (ACAI) is a specialized course in Artificial Intelligence sponsored by EurAI. The 2018 edition will be in Ferrara, Italy on August 27th - 31st 2018, save the date! The theme of the 2018 ACAI School is Statistical Relational Artificial Intelligence (StarAI). StarAI is an emerging area that combines logical (or relational) AI and probabilistic (or statistical) AI. Relational AI deals very effectively with complex domains involving many and even a varying number of entities connected by complex relationships, while statistical AI manages well the uncertainty that derives from incomplete and noisy descriptions of the domains. Both fields achieved significant successes over the last thirty years but evolved largely independently until about fifteen years ago, when the potential originating from their combination started to emerge. Statistical Relational Learning (SRL) was proposed for exploiting relational descriptions in statistical machine learning methods from the field of graphical models. Meanwhile, the scope of SRL was significantly advanced in StarAI to cover all forms of reasoning and models of AI. StarAI is nowadays an ample area encompassing many and diverse approaches. The school includes courses on foundations of relational and statistical AI together with advanced courses on the new StarAI approaches and applications. The talks will provide theoretical background, practical examples and real applications where StarAI can play a role. Hands-on classes will be also organized where the main StarAI techniques will be applied to 'small' examples. The list of confirmed lectures is: Luc De Raedt: Probabilistic Programming Paolo Frasconi: Kernels and deep networks for structured data Sebastian Riedel: Differentiable Program Interpreters Artur d'Avila Garcez: Neural-symbolic learning Marco Lippi: Applications of Statistical Relational Artificial Intelligence Sriraam Natarajan: Human-in-the-loop Statistical Relational Learning Mathias Niepert and Alberto García Durán: Multi-Modal Neural Link Prediction Kristian Kersting: Lifted Statistical Machine Learning Fabrizio Riguzzi: Probabilistic Inductive Logic Programming Vibhav Gogate: Lifted Systematic Search and Sampling David Poole: TBA Up to date information can be found at the event website http://acai2018.unife.it/. ACAI 2018 is part of the Relational Artificial Intelligence Days 2018 (RAID 2018, http://raid2018.unife.it/ ), which will be held in Ferrara, Italy, on August 27th 2018 - September 4th 2018. RAID includes, besides ACAI 2018, also: - PLP 2018: 5th Workshop on Probabilistic Logic Programming, September 1st 2018, http://stoics.org.uk/plp/plp2018/ ; - ILP 2018: 28th International Conference on Inductive Logic Programming, September 2nd - 4th 2018, http://ilp2018.unife.it/ . Probabilistic Logic Programming (PLP) addresses the need to reason about relational domains under uncertainty arising in a variety of application domains. PLP is part of a wider current interest in probabilistic programming. PLP 2018 aims to bring together researchers in all aspects of probabilistic logic programming, including theoretical work, system implementations and applications. The ILP conference series, started in 1991, is the premier international forum for learning from structured or semi-structured relational data. Originally focusing on the induction of logic programs, over the years it has significantly expanded and it welcomes contributions to all aspects of learning in logic, multi-relational data mining, statistical relational learning, graph and tree mining, learning in other (non-propositional) logic-based knowledge representation frameworks, exploring intersections to statistical learning and other probabilistic approaches. RAID 2018 offers a very good opportunity to get up to date with the latest trends in logical and relational AI. We really hope to meet you in Ferrara! Organizers Kristian Kersting, TU Darmstadt, Germany Marco Lippi, University of Modena and Reggio Emilia, Italy Sriraam Natarajan, University of Texas at Dallas, USA Fabrizio Riguzzi, University of Ferrara, Italy Elena Bellodi, University of Ferrara, Italy Tom Schrijvers, KU Leuven, Belgium Riccardo Zese, University of Ferrara, Italy ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
[UAI] [DEADLINE EXTENSION] PLP 2018 - Probabilistic Logic Programming Workshop
*Deadline extended to 21st June, 2018 * - - PLP-2018: The Fifth Workshop on Probabilistic Logic Programming A workshop of the 28th International Conference on Inductive Logic Programming 1 September 2018 Ferrara, Italy http://stoics.org.uk/plp/plp2018/ Overview Probabilistic logic programming (PLP) approaches have received much attention in this century. They address the need to reason about relational domains under uncertainty arising in a variety of application domains, such as bioinformatics, the semantic web, robotics, and many more. Developments in PLP include new languages that combine logic programming with probability theory, as well as algorithms that operate over programs in these formalisms. The workshop encompasses all aspects of combining logic, algorithms, programming and probability. PLP is part of a wider current interest in probabilistic programming. By promoting probabilities as explicit programming constructs, inference, parameter estimation and learning algorithms can be ran over programs which represent highly structured probability spaces. Due to logic programming's strong theoretical underpinnings, PLP is one of the more disciplined areas of probabilistic programming. It builds upon and benefits from the large body of existing work in logic programming, both in semantics and implementation, but also presents new challenges to the field. PLP reasoning often requires the evaluation of large number of possible states before any answers can be produced thus braking the sequential search model of traditional logic programs. While PLP has already contributed a number of formalisms, systems and well understood and established results in: parameter estimation, tabling, marginal probabilities and Bayesian learning, many questions remain open in this exciting, expanding field in the intersection of AI, machine learning and statistics. This workshop provides a forum for the exchange of ideas, presentation of results and preliminary work, in the following areas * probabilistic logic programming formalisms * parameter estimation * statistical inference * implementations * structure learning * reasoning with uncertainty * constraint store approaches * stochastic and randomised algorithms * probabilistic knowledge representation and reasoning * constraints in statistical inference * applications, such as * bioinformatics * semantic web * robotics * probabilistic graphical models * Bayesian learning * tabling for learning and stochastic inference * MCMC * stochastic search * labelled logic programs * integration of statistical software The above list should be interpreted broadly and is by no means exhaustive. Purpose --- The fifth edition of PLP is held at the ILP conference in Ferrara. We hope that this encourages further collaboration between researchers in PLP and researchers working in other areas of ILP. In particular, we hope that both (a) other ILP researchers will become interested in using PLP formalisms and (b) that PLP researchers are inspired by other inductive learning approaches. Submissions --- Submissions will be managed via EasyChair ( https://easychair.org/conferences/?conf=plp2018). Contributions should be prepared in the LNCS style. A mixture of papers are sought including: new results, work in progress as well as technical summaries of recent substantial contributions. Papers presenting new results should be 6-12 pages in length. Works in progress and technical summaries can be shorter (2-5 pages). The workshop proceedings will clearly indicate the type of each paper. At least one author of each accepted paper will be required to attend the workshop to present the contribution. Registration to the event Registrations are open. Visit http://raid2018.unife.it/registration/ for all the information. Publication --- Proceedings will be stored permanently in the form of CEUR Workshop Proceedings (http://ceur-ws.org/). They will consist of clearly marked sections corresponding to the different types of submissions accepted. Special Issue of IJAR - Like for past editions of PLP, we plan to invite all authors to submit a revised version of their paper for a Probabilistic Logic Programming special issue of the IJAR journal. Deadlines - Papers due: 11th June 2018 --> *21st June* *2018* Notification to authors: 11th July 2018 Camera ready version due: 27th July 2018 Workshop day: 1st September 2018 (the deadline for all dates is 23:59 BST) Invited Speakers - Riccardo Zese, University of Ferrara, Italy Angelika Kimmig, Cardiff University, UK *** Co-located Events
[UAI] CFP: Symposium on Reasoning and Learning in Real-World Systems for Long-Term Autonomy
* *Reasoning and Learning in Real-World Systems for Long-Term Autonomy* * AAAI Fall Symposium October 18-20, 2018 Arlington, Virginia http://rbr.cs.umass.edu/lta *Submission Deadline: July 31, 2018* Over the past decade, decision-making agents have been increasingly deployed in industrial settings, consumer products, healthcare, education, and entertainment. The development of drone delivery services, virtual assistants, and autonomous vehicles have highlighted numerous challenges surrounding the operation of autonomous systems in unstructured environments. This includes mechanisms to support autonomous operations over extended periods of time, techniques that facilitate the use of human assistance in learning and decision-making, addressing the practical scalability of existing methods, relaxing unrealistic assumptions, and alleviating safety concerns about deploying these systems. This symposium aims to identify the challenges and bridge the gaps between theoretical frameworks for planning and learning in autonomous agents and the requirements imposed by deployment in the real world. We seek papers that find a common middle ground between theory and applications, and analyze the lessons learned from these efforts, particularly with respect to long-term autonomy. We invite submissions of full papers (6-8 pages) and short papers (3-4 pages). Full papers can present novel work or summarize a collection of recent work. Short papers can present preliminary work, describe new real-world challenge problems, or present a position related to these topics. Topics of particular interest include, but are not limited to: - Decision-making representations, models, and algorithms for the real world - Hierarchical and multi-objective solutions for scalable planning and learning - Efficient integrations of task and motion planning - Integrating planning, reasoning, and learning for long-term deployments - Safety in real-world decision-making and learning - Scalable multiagent and human-in-the-loop techniques - Proactively incorporating human feedback in decision-making - Leveraging the complimentary capabilities of humans and robots in real-world tasks - Evaluation metrics for long-term autonomy - Case studies and descriptions of deployed autonomous systems - Lessons learned from deployed applications of autonomous systems Papers should be submitted to this symposium's track on EasyChair: https://easychair.org/conferences/?conf=fss18. Complete details can be found at the symposium website: http://rbr.cs.umass.edu/lta. Organizing Committee: Kyle H. Wray, University of Massachusetts Amherst Julie A. Shah, Massachusetts Institute of Technology Peter Stone, University of Texas at Austin Stefan J. Witwicki, Nissan Research Center - Silicon Valley Shlomo Zilberstein, University of Massachusetts Amherst ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
