DeepLearn 2022 Winter: early registration October 9

October 13th, 2021 Daniela Lopez de Luise
5th INTERNATIONAL SCHOOL ON DEEP LEARNING
DeepLearn 2022 Winter
Bournemouth, UK
anuary 17-21, 2022
***********
Co-organized by:
Department of Computing and Informatics
Bournemouth University
Institute for Research Development, Training and Advice – IRDTA
Brussels/London
******************************************************************
Early registration: October 9, 2021
******************************************************************
SCOPE:
DeepLearn 2022 Winter will be a research training event with a global scope aiming at updating participants on the most recent advances in the critical and fast developing area of deep learning. Previous events were held in Bilbao, Genova, Warsaw and Las Palmas de Gran Canaria.
Deep learning is a branch of artificial intelligence covering a spectrum of current exciting research and industrial innovation that provides more efficient algorithms to deal with large-scale data in a huge variety of different environments: computer vision, neurosciences, speech recognition, language processing, human-computer interaction, drug discovery, biomedical informatics, image analysis, recommender systems, advertising, fraud detection, robotics, games, etc. etc. Renowned academics and industry pioneers will lecture and share their views with the audience.
Most deep learning subareas will be displayed, and main challenges identified through 23 four-hour and a half courses and 3 keynote lectures, which will tackle the most active and promising topics. The organizers are convinced that outstanding speakers will attract the brightest and most motivated students. Face to face interaction and networking will be main components of the event.
An open session will give participants the opportunity to present their own work in progress in 5 inutes. Moreover, there will be two special sessions with industrial and recruitment profiles.
ADDRESSED TO:
Graduate students, postgraduate students and industry practitioners will be typical profiles of participants. However, there are no formal pre-requisites for attendance in terms of academic degrees, so people less or more advanced in their career will be welcome as well. Since there will be a variety of levels, specific knowledge background may be assumed for some of the courses. Overall, DeepLearn 2022 Winter is addressed to students, researchers and practitioners who want to keep themselves updated about recent developments and future trends. All will surely find it fruitful to listen to and discuss with major researchers, industry leaders and innovators.
VENUE:
DeepLearn 2022 Winter will take place in Bournemouth, a coastal resort town on the south coast of England. The venue will be:
TBA
STRUCTURE:
3 courses will run in parallel during the whole event. Participants will be able to freely choose he ourses they wish to attend as well as to move from one to another.
Full in vivo online participation will be possible. However, the organizers want to emphasize the importance of face to face interaction and networking in this kind of research training event.
ORGANIZING COMMITTEE:
Rashid Bakirov (Bournemouth, co-chair)
Nan Jiang (Bournemouth, co-chair)
Carlos Martín-Vide (Tarragona, program chair)
Sara Morales (Brussels)
David Silva (London, co-chair)
REGISTRATION:
It has to be done at
he selection of up to 8 courses requested in the registration template is only tentative and non-binding. For the sake of organization, it will be helpful to have an estimation of the respective demand for each course. During the event, participants will be free to attend the courses they wish.
Since the capacity of the venue is limited, registration requests will be processed on a first come first served basis. The registration period will be closed and the on-line registration tool disabled when the capacity of the venue will get exhausted. It is highly recommended to register prior to the event.
FEES:
Fees comprise access to all courses and lunches. There are several early registration deadlines. Fees depend on the registration deadline.
ACCOMMODATION:
Accommodation suggestions will be available in due time at
CERTIFICATE:
A certificate of successful participation in the event will be delivered indicating the number of hours of lectures.
QUESTIONS AND FURTHER INFORMATION:
ACKNOWLEDGMENTS:
Bournemouth University
Institute for Research Development, Training and Advice – IRDTA, Brussels/London
Read More »

AIJ Special Issue on Risk-Aware Autonomous Systems: Theory and Practice

October 13th, 2021 Daniela Lopez de Luise

TL;DR: the deadline to submit to the AIJ Special Issue on Risk-Aware Autonomous Systems has been extended to January 15th, 2022 (the website will be updated accordingly in the next few days).

 

Dear all, 

 

Artificial Intelligence’s Special Issue on “Risk-Aware Autonomous Systems: Theory and Practice” is now open for submissions. The special issue is co-edited by Prof. Sara Bernardini (Royal Holloway University of London), Prof. Luca Carlone (MIT), Dr Ashkan Jasour (MIT), Prof. Andreas Krause (ETH Zurich), Prof. George Pappas (University of Pennsylvania), Prof. Brian Williams (MIT) and Prof. Yisong Yue (Caltech). Submissions will close on January 15th, 2022 (extended deadline). Artificial Intelligence is a world-leading journal in AI with an Impact Factor of 6,628 and CiteScore of 7.7. 

 

                                                                                                  

Aims and Scope

This special issue focuses on the theory and practice of risk-aware autonomous systems that reason about uncertainty and risk online to achieve safety, and that combine machine learning and decision making to accomplish real world tasks.

The topic of risk-aware autonomous systems has seen a dramatic increase in importance over the last few years, as autonomous systems are being deployed almost daily within safety-critical applications, including self-driving vehicles, autonomous undersea and aerospace systems, service robotics, and collaborative manufacturing. This broad adoption is a testament to the fast-paced progress of the research community across multiple areas, including planning, learning, perception, decision making, and control. At the same time, today’s widely used AI algorithms for autonomy are beginning to showcase fundamental limits and practical shortcomings. In particular, excessive risk taken by these algorithms can lead to catastrophic failure of the overall system and may put human life in danger. Many AI methods used today do not attempt to quantify uncertainty; they do not assess the risks that uncertainty imposes on system safety and success; they do not guarantee bounds on this risk and they do not perform these assessments in real-time.

To push the envelope of autonomous systems’ safety, this special issue will present ground-breaking research on the theory and practice of designing the next generation of risk-aware AI algorithms and autonomous systems. Key to our envisioned methods is their ability to account for uncertainty and risk of failure during their online execution, their capabilities for proactively quantifying and mitigating risks against task goals and safety constraints, and their ability to offer formal guarantees, such as bounds on the risk of failure. Emerging risk-bounded methods often operate on models of uncertainty, specifications of intended outcomes, and specifications of acceptable risks regarding these outcomes. These models and specifications are diverse. Uncertainty models may be probabilistic, set bounded, or interval based. Intended outcomes include goals achieved, deadlines met, safety constraints respected, required accuracy in model estimation and perception, and rate of false positives. Specifications of acceptable risk include risk bounds and acceptable costs of failure. These intended outcomes and acceptable risks can apply to individual AI components, such as policy and action learners, image classifiers and planners, and the aggregate systems as a whole.

This special issue is intended to represent this diversity. It aims to cover a broad set of topics related to risk-aware autonomous systems, including but not limited to:

● risk-aware task and motion planning;
● robust and adversarial learning;
● certifiable and risk-aware perception, localization and mapping;
● robust task monitoring and execution under uncertainty;
● formal methods for monitoring and verifying uncertain systems;
● constraint and mathematical programming with chance constraints;
● robust control of intelligent systems;
● system-level monitoring and risk quantification.

Submission Instructions

We welcome high quality original (unpublished) articles. Each submission will be peer-reviewed.

 

All submissions should be formatted following the AI journal instructions for authors (https://www.elsevier.com/journals/artificial-intelligence/0004-3702/guide-for-authors) and submitted to: https://www.editorialmanager.com/artint/default.aspx    

 

To ensure that all manuscripts are correctly identified for inclusion into the special issue, please select  “VSI:Risk-Aware Autonomy”  when you reach the “Article Type” step in the submission process.

 

Authors can share their research in a variety of different ways and Elsevier has a number of green open access options available: https://www.elsevier.com/open-access

 

Important Dates

● Submissions open: 15 May 2021

● Submissions close: 15 January 2022

● Publication of the special issue: 15 August 2022 (tentative)

 

Guest Editors

● Prof. Sara Bernardini (Royal Holloway University of London, sara.bernardini@rhul.ac.uk)
● Prof. Luca Carlone (Massachusetts Institute of Technology, lcarlone@mit.edu)
● Dr. Ashkan Jasour (Massachusetts Institute of Technology, jasour@mit.edu)
● Prof. Andreas Krause (ETH Zurich, krausea@ethz.ch)
● Prof. George Pappas (University of Pennsylvania, pappasg@seas.upenn.edu)
● Prof Brian Williams (Massachusetts Institute of Technology, williams@mit.edu)
● Prof. Yisong Yue (California Institute of Technology, yyue@caltech.edu)

 

For more information, please contact the editors and visit: https://www.journals.elsevier.com/artificial-intelligence/call-for-papers/risk-aware-autonomous-systems-theory-and-practice

 

Read More »

Discovery Science DS’2021 – call for participation

October 13th, 2021 Daniela Lopez de Luise
DS 2021:  the 24th International Conference on Discovery Science
Online (Halifax, Canada)
11-13 October, 2021
============================================================
DS’2021 provides an open forum for intensive discussions and exchange of
new ideas among researchers working in the area of Discovery Science.
The conference focus is on the use of artificial intelligence methods in
science. Its scope includes the development and analysis of methods for
discovering scientific knowledge, coming from machine learning, data
mining, intelligent data analysis, and big data analytics, as well as
their application in various domains.

Special Issue on The Role of Ontologies and Knowledge in Explainable AI

October 13th, 2021 Daniela Lopez de Luise
Dear colleagues,

this is a special issue that I am co-editing, and it is to be published in the Semantic Web journal, IOS Press.
https://sites.google.com/view/special-issue-on-xai-swj

Further details are giving below. Notice that, I highly appreciate if you can forward this invitation to your colleagues and collaborators. Of course, your contribution to the special issue is welcome!

***
Explainable AI (XAI) has been identified as a key factor for developing trustworthy AI systems. The reasons for equipping intelligent systems with explanation capabilities are not limited to user rights and acceptance. Explainability is also needed for designers and developers to enhance system robustness and enable diagnostics to prevent bias, unfairness, and discrimination, as well as to increase trust by all users in why and how decisions are made.

The interpretability of AI systems has been described long time ago since mid 1980s, but until recently it becomes an active research focus in computer science community due to the advances of big data and various regulations of data protection in developing AI systems, such as the GDPR. For example, according to the GDPR, citizens have the legal right to an explanation of decisions made by algorithms that may affect them (e.g., see Article 22). This policy highlights the pressing importance of transparency and interpretability in algorithm design.

XAI focuses on developing new approaches for explanations of black-box models by achieving good explainability without sacrificing system performance. One typical approach is the extraction of local and global post-hoc explanations. Other approaches are based on hybrid or neuro-symbolic systems, advocating a tight integration between symbolic and non-symbolic knowledge, e.g., by combining symbolic and statistical methods of reasoning.

The construction of hybrid systems is widely seen as one of the grand challenges facing AI today. However, there is no consensus regarding how to achieve this, with proposed techniques in the literature ranging from knowledge extraction and tensor logic to inductive logic programming and other approaches. Knowledge representation—in its many incarnations— is a key asset to enact hybrid systems, and it can pave the way towards the creation of transparent and human-understandable intelligent systems.

This special issue will feature contributions dedicated to the role played by knowledge bases, ontologies, and knowledge graphs in XAI, in particular with regard to building trustworthy and explainable decision support systems. Knowledge representation plays a key role in XAI. Linking explanations to structured knowledge, for instance in the form of ontologies, brings multiple advantages. It does not only enrich explanations (or the elements therein) with semantic information—thus facilitating evaluation and effective knowledge transmission to users—but it also creates a potential for supporting the customisation of the levels of specificity and generality of explanations to specific user profiles or audiences. However, linking explanations, structured knowledge, and sub-symbolic/statistical approaches raise a multitude of technical challenges from the reasoning perspective, both in terms of scalability and in terms of incorporating non-classical reasoning approaches, such as defeasibility, methods from argumentation, or counterfactuals, to name just a few.

**Topics of Interest**

Topics relevant to this special issue include – but are not limited to – the following:

– Cognitive computational systems integrating machine learning and automated reasoning
– Knowledge representation and reasoning in machine learning and deep learning
– Knowledge extraction and distillation from neural and statistical learning models
– Representation and refinement of symbolic knowledge by artificial neural networks
– Explanation formats exploiting domain knowledge
– Visual exploratory tools of semantic explanations
– Knowledge representation for human-centric explanations
– Usability and acceptance of knowledge-enhanced semantic explanations
– Evaluation of transparency and interpretability of AI Systems
– Applications of ontologies for explainability and trustworthiness in specific domains
– Factual and counterfactual explanations
– Causal thinking, reasoning and modeling
– Cognitive science and XAI
– Open source software for XAI
– XAI applications in finance, medical and health sciences, etc.

**Deadline**

– Submission deadline: 10th of December 2021. (Papers submitted before the deadline will be reviewed upon receipt).
– Acceptance/rejection notification: March 31st, 2022
– Revision due: May 31st, 2022
– Estimated Publication Date:  July 2022

**Author Guidelines**

Submissions shall be made through the Semantic Web journal website at
http://www.semantic-web-journal.net.
Prospective authors must take notice of the submission guidelines posted at
http://www.semantic-web-journal.net/authors.

We welcome four main types of submissions: (i) full research papers, (ii) reports on tools and systems, (iii) application reports, and (iv) survey articles. The description of the submission types is posted at http://www.semantic-web-journal.net/authors#types.

While there is no upper limit, paper length must be justified by content.

Note that you need to request an account on the website for submitting a paper. Please indicate in the cover letter that it is for the “The Role of Ontologies and Knowledge in Explainable AI” special issue. All manuscripts will be reviewed based on the SWJ open and transparent review policy and will be made available online during the review process.

Also note that the Semantic Web journal is open access.
http://www.semantic-web-journal.net/blog/call-papers-special-issue-role-ontologies-and-knowledge-explainable-ai

**Guest editors**

The guest editors can be reached at ontologies-knowledge-in-xai-swj@googlegroups.com
– Roberto Confalonieri, Free University of Bozen-Bolzano, Faculty of Computer Science, Italy
– Oliver Kutz, Free University of Bozen-Bolzano, Faculty of Computer Science, Italy
– Diego Calvanese, Department of Computing Science, Umeå University, Sweden and Free University of Bozen-Bolzano, Faculty of Computer Science
– Jose M. Alonso, University of Santiago de Compostela, CiTIUS, Spain
– Shang-Ming Zhou, University of Plymouth, Faculty of Health, UK

Read More »

New Approaches to 3D Vision, 1st-4th Nov 2021, Royal Society online meeting

October 13th, 2021 Daniela Lopez de Luise
New Approaches to 3D Vision, 1st-4th November 2021, hosted by the Royal Society 

This Royal Society online meeting brings together researchers from computer vision, animal vision, and human vision to explore recent developments in 3D vision. Speakers reflect both academia and industry, with representatives from DeepMind, Facebook Reality Labs, Google, and Microsoft Research.

Date/Time: 1st-4th November 2021, 3-6pm (3-6:30pm on the 4th), UK Time
Please note that the USA/UK time difference is 1hr less than usual

DAY ONE (1st Nov) – Seeing Beyond SLAM
Chair: Andrew Fitzgibbon (Microsoft)
Session One: Neural Scene Representation
SM Ali Eslami (DeepMind): “Neural priors, neural encoders and neural renderers”
Ida Momennejad (Microsoft Research): “Multi-scale predictive representations and human-like RL”
Session Two: Perception-Action Loop
Sergey Levine (UC Berkeley and Google): TBC
Andrew Glennerster (University of Reading): “Understanding 3D vision as a policy network”
DAY TWO (2nd Nov) – Animals in Action 
Chair: Matteo Carandini (University College London)
Session One: Locating Prey and Rewards
Jenny Read (Newcastle University): “Stupid stereoscopic algorithms that still work”
Aman Saleem (University College London): “Visual processing in the brain during navigation”
Session Two: Navigation in 3D Space
Kate Jeffery (University College London): “The cognitive map of 3D space: not as metric as we thought?”
Gily Ginosar (Weizmann Institute of Science): “Locally ordered representation of 3D space in the entorhinal cortex” 
DAY THREE (3rd Nov) – Experiencing Space
Chair: Mar Gonzalez-Franco (Microsoft Research)
Session One: Theories of Visual Space
Dhanraj Vishwanath (University of St Andrews): “Tripartite encoding of visual 3D space”
Paul Linton (City, University of London): “New approaches to visual scale and visual shape”
Session Two: Challenges for Virtual Reality
Sarah Creem-Regehr (University of Utah): “Perception and Action in Virtual and Augmented Reality”

Douglas Lanman (Facebook Reality Labs): TBC
DAY FOUR (4th Nov) – Grasping the World
Chair: Jody Culham (Western University)
Session One: One Visual Stream or Two?
Fulvio Domini (Brown University): “A novel non-probabilistic model of 3D cue integration explains both perception and action”
Irene Sperandio (University of Trento): “Dissociations between perception and action in size-distance scaling”
Session Two: 3D Space and Visual Impairment
Ione Fine (University of Washington): “Do you hear what I see? How do early blind individuals experience object motion?”

Ewa Niechwiej-Szwedo (University of Waterloo): “The role of binocular vision in the development of visuomotor control and performance of fine motor skills”
Session Three: Panel Discussion
Andrew Fitzgibbon (Microsoft), Matteo Carandini (University College London), Mar Gonzalez-Franco (Microsoft Research), and Jody Culham (Western University), share their thoughts on future directions for 3D vision.
Organisers: Michael Morgan FRS (City, University of London), Paul Linton (City, University of London), Jenny Read (Newcastle University), Dhanraj Vishwanath (University of St Andrews), Sarah Creem-Regehr (University of Utah), Fulvio Domini (Brown University)
Read More »
« Older Entries
Newer Entries »
Design by 2b Consult