- RoboCup-worldwide - lists.robocup.org

Neural Computing and Applications (NCAA) Special Issue on Interpretation of Deep Learning
by Pub Conference 29 Jun '21

29 Jun '21

*Neural Computing and Applications (NCAA) Special Issue **on Interpretation of Deep Learning: Prediction, Representation, Modeling and Utilization* https://www.springer.com/journal/521/updates/19187658 Aims, Scope and Objective While Big Data offers the great potential for revolutionizing all aspects of our society, harvesting of valuable knowledge from Big Data is an extremely challenging task. The large scale and rapidly growing information hidden in the unprecedented volumes of non-traditional data requires the development of decision-making algorithms. Recent successes in machine learning, particularly deep learning, has led to breakthroughs in real-world applications such as autonomous driving, healthcare, cybersecurity, speech and image recognition, personalized news feeds, and financial markets. While these models may provide the state-of-the-art and impressive prediction accuracies, they usually offer little insight into the inner workings of the model and how a decision is made. The decision-makers cannot obtain human-intelligible explanations for the decisions of models, which impede the applications in mission-critical areas. This situation is even severely worse in complex data analytics. It is, therefore, imperative to develop explainable computation intelligent learning models with excellent predictive accuracy to provide safe, reliable, and scientific basis for determination. Numerous recent works have presented various endeavors on this issue but left many important questions unresolved. The first challenging problem is how to construct self-explanatory models or how to improve the explicit understanding and explainability of a model without the loss of accuracy. In addition, high dimensional or ultra-high dimensional data are common in large and complex data analytics. In these cases, the construction of interpretable model becomes quite difficult and complex. Further, how to evaluate and quantify the explainability of a model is lack of consistent and clear description. Moreover, auditable, repeatable, and reliable process of the computational models is crucial to decision-makers. For example, decision-makers need explicit explanation and analysis of the intermediate features produced in a model, thus the interpretation of intermediate processes is requisite. Subsequently, the problem of efficient optimization exists in explainable computational intelligent models. These raise many essential issues on how to develop explainable data analytics in computational intelligence. This Topical Collection aims to bring together original research articles and review articles that will present the latest theoretical and technical advancements of machine and deep learning models. We hope that this Topical Collection will: 1) improve the understanding and explainability of machine learning and deep neural networks; 2) enhance the mathematical foundation of deep neural networks; and 3) increase the computational efficiency and stability of the machine and deep learning training process with new algorithms that will scale. Potential topics include but are not limited to the following: - Interpretability of deep learning models - Quantifying or visualizing the interpretability of deep neural networks - Neural networks, fuzzy logic, and evolutionary based interpretable control systems - Supervised, unsupervised, and reinforcement learning - Extracting understanding from large-scale and heterogeneous data - Dimensionality reduction of large scale and complex data and sparse modeling - Stability improvement of deep neural network optimization - Optimization methods for deep learning - Privacy preserving machine learning (e.g., federated machine learning, learning over encrypted data) - Novel deep learning approaches in the applications of image/signal processing, business intelligence, games, healthcare, bioinformatics, and security Guest Editors Nian Zhang (Lead Guest Editor), University of the District of Columbia, Washington, DC, USA, nzhang(a)udc.edu Jian Wang, China University of Petroleum (East China), Qingdao, China, wangjiannl(a)upc.edu.cn Leszek Rutkowski, Czestochowa University of Technology, Poland, leszek.rutkowski(a)pcz.pl Important Dates Deadline for Submissions: March 31, 2022 First Review Decision: May 31, 2022 Revisions Due: June 30, 2022 Deadline for 2nd Review: July 31, 2022 Final Decisions: August 31, 2022 Final Manuscript: September 30, 2022 Peer Review Process All the papers will go through peer review, and will be reviewed by at least three reviewers. A thorough check will be completed, and the guest editors will check any significant similarity between the manuscript under consideration and any published paper or submitted manuscripts of which they are aware. In such case, the article will be directly rejected without proceeding further. Guest editors will make all reasonable effort to receive the reviewer’s comments and recommendation on time. The submitted papers must provide original research that has not been published nor currently under review by other venues. Previously published conference papers should be clearly identified by the authors at the submission stage and an explanation should be provided about how such papers have been extended to be considered for this special issue (with at least 30% difference from the original works). Submission Guidelines Paper submissions for the special issue should strictly follow the submission format and guidelines ( https://www.springer.com/journal/521/submission-guidelines). Each manuscript should not exceed 16 pages in length (inclusive of figures and tables). Manuscripts must be submitted to the journal online system at https://www.editorialmanager.com/ncaa/default.aspx. Authors should select “TC: Interpretation of Deep Learning” during the submission step ‘Additional Information’.

1 0

RoboCup Symposium day, including awards ceremonies
by Peter Stone 28 Jun '21

28 Jun '21

Dear RoboCuppers, Congratulations to everyone on what by all appearances was a very successful set of competitions! While the competitions have completed, Monday brings the RoboCup Symposium, our community's main scientific event. Please tune in on the Underline mainstage starting at 9am UTC for a fun and interesting program. Each paper will be presented with a short 5-minute video. There will be time to talk with the authors and ask questions afterwards at the interactive sessions in Gather Town. You can browse the posters and videos in Gather Town at your convenience any time. At 11am UTC, there will be a panel on building a research career in RoboCup with representatives from different stages of their careers. Between noon and 2pm UTC, there will be the RoboCup Junior awards ceremony (noon), the Handover ceremony for everyone with a preview of RoboCup 2022 (12:45), and the RoboCup Major awards ceremony (1:15). All participants are strongly encouraged to attend - whether or not you won an award! Immediately following, we will have our final keynote speech, by Stefanie Tellex: "Towards Complex Language in Partially Observed Environments." At the end of the day, there will be a panel reflecting back on 25 years of RoboCup. I look forward to seeing you all there! Best, Peter Stone President, RoboCup Federation

1 0

PhD studentship in Machine Learning for Human-Robot Interaction (PI: Frank Foerster, University of Hertfordshire)
by Daniel Polani 27 Jun '21

27 Jun '21

Dear all, on behalf of Frank Förster, I'd like to bring to your notice this PhD opportunity (deadline for applications 30. June 2021): PhD studentship MACHINE LEARNING FOR HUMAN-ROBOT INTERACTION Adaptive Systems Research Group Centre for Computer Science and Informatics Research School of Physics, Engineering and Computer Science University of Hertfordshire, UK Contact: Frank Foerster (f.foerster(a)herts.ac.uk) ============ Short-listings will start on 30 June 2021* Bursary £15,285 p.a. * application before this date is strongly encouraged We invite applications for a PhD studentship at the University of Hertfordshire, UK, under the supervision of Dr. Frank Foerster in the area of robotic language acquisition or symbol grounding as well as approaches to implement repair mechanisms in human-robot interaction more generally. We are particularly interested in pursuing research that connects to the following two topics, but alternative ideas will be considered too. Research Topics Topic 1: Socially driven Machine Learning in Robotic Language Acquisition Topic 2: Repair Mechanisms in Interaction More information including relevant papers are provided in the following PDF: https://www.herts.ac.uk/__data/assets/pdf_file/0006/331737/ML_HRI.pdf Independent of the particular topic, we have recently become member of the HomeBank corpora, and would strongly encourage interaction and collaboration with developmental psychologists and psycholinguists. Person Profile You will have an excellent first degree and a very keen interest and motivation in human-machine interaction in general or in language acquisition in particular. Optimally you should have an excellent background in Computer Science, Computational/Cognitive Robotics, (computational) linguistics, Artificial intelligence, or similar disciplines with a considerable quantitative/computational component. Due to the interdisciplinary nature of the topic we will also consider applicants with a background in (developmental) psychology, philosophy, or pragmatics as long as you have some experience in programming, machine learning, or dialogue systems. Prior experience with topics such as reinforcement learning, or statistical learning more generally is highly desirable, but not essential if the quantitative background is otherwise very strong. The knowledge of later Wittgenstein is a big plus. If you have questions, have alternative suggestions for a related, but distinct topic, and/or are generally interested in applying, please contact Dr. Frank Foerster f.foerster(a)herts.ac.uk ============ Research in Computer Science at the University of Hertfordshire has been recognised as excellent by the latest Research Assessment Exercise, with 50% of the research submitted being rated as internationally excellent or world leading. The University of Hertfordshire provides a very stimulating environment, offering a large number of specialised and interdisciplinary seminars as well as general training and researcher development opportunities. The University is situated in Hatfield, in the green belt just north of London. Hatfield is close to Central London (less than 25 minutes by direct train to Kings Cross), with convenient access to Stansted, Luton and Heathrow airports, and, via the nearby historic town of St. Albans, also to Gatwick airport. Application forms and submission instructions are available under https://www.herts.ac.uk/study/schools-of-study/physics-engineering-and-comp… Eligibility ----------- Applicants must submit or obtain: - a completed application form, which can be obtained from website linked above - a research statement stating past experience/research background and interest and motivation/research ambition for current project - two academic references - copies of qualification certificates and transcripts - a copy of your passport Applications from outside the UK or EU are eligible for this studentship. The application form should be returned to: doctoralcollegeadmissions(a)herts.ac.uk

1 0

Finals day!
by Peter Stone 27 Jun '21

27 Jun '21

Dear RoboCuppers, Sunday brings our last day of competitions in RoboCup 2021. Traditionally, we schedule the games sequentially so that we can all watch the finals in all the leagues and then at the end of the day we have the awards ceremony. Due to people being in different time zones, we don't have such a scripted finals day this year. But I still encourage you to watch the top teams in as many leagues as possible. We may be able to update the schedule on the website. But in case not, I'm attaching a document with the timings and links of Sunday's games in many of the leagues. Meanwhile, we will hold the award ceremony in the middle of the symposium on Monday. Please plan on being there. Good luck to everyone on Sunday! Best, Peter Stone President, RoboCup Federation

1 0

Friday at RoboCup: 2nd keynote talk
by Peter Stone 25 Jun '21

25 Jun '21

RoboCuppers, I know I've said this already, but it really is thrilling to see the videos and livestreams of the competitions from all around the world. Kudos to all of you for keeping the RoboCup spirit alive this year! On Friday, please tune in to the Underline main stage at 13:30 UTC for the 2nd keynote talk of the symposium by Jean-Paul Laumond: "Robotics: The Science of Motion." Immediately after the talk, I will be in the gather.town space to meet with some of my RoboCup friends. I hope you'll join us there as well! Best, Peter Stone President, RoboCup Federation

1 0

Recordings of opening ceremony and invited talk available
by Peter Stone 24 Jun '21

24 Jun '21

Dear RoboCuppers, I hope your competitions are all proceeding nicely. In case you missed them, there are now recordings of the opening ceremony and the first keynote talk available on the Underline page. Click on the schedule for June 23rd to find them. By the way, I've heard reports that the website works better in Firefox and Chrome than in Safari. If you're having any trouble with it, you may want to try switching browsers. Good luck with your games on Thursday! Best, Peter Stone President, RoboCup Federation

1 0

Main stage access
by Peter Stone 23 Jun '21

23 Jun '21

RoboCup participants, In case it isn't clear, to access the main stage, click on the star in the left navigation window of the Underline page. The direct link is: https://www.underline.io/events/108/mainstage Best, Peter

2 1

RoboCup 2021 opening ceremony and first keynote
by Peter Stone 22 Jun '21

22 Jun '21

Dear RoboCuppers, It's exciting to see some of the live streams from the leagues running. Congratulations to everyone on getting to this point! The opening ceremony will begin in just a few hours - at 13:30 UTC on Wednesday. Please plan to tune in to the Underline mainstage at that time, followed by the first symposium keynote by Dieter Fox "Toward Robust Manipulation in Complex Environments" at 14:00. Immediately after that (around 15:00), I encourage you to log in to gather.town. Dieter intends to be there to answer questions, and you will have an opportunity to also mingle with each other. Remember that all the symposium posters and presentations are now accessible in the symposium room. And next to the symposium room, there is now a set of meeting rooms that you can use as needed (in addition to the league rooms). I've already enjoyed catching up with some of you in gather.town, and I look forward to seeing more of you there over the coming days. See you soon! Peter Stone President, RoboCup Federation

1 0

RoboCup 2021!
by Peter Stone 21 Jun '21

21 Jun '21

RoboCup community, I'm very excited about RoboCup getting started. Some of the leagues are already underway, and the rest will be starting in the next couple of days. While fine-tuning your code and preparing for the competition, I hope you'll all take the time to also interact with each other - learn about the approaches other teams are taking, share your own advances, catch up with friends from past years, and make new friends - both within your leagues and across leagues. As usual, each league is expected to have league meetings to go over the rules, brainstorm changes for next year, and elect technical committees for next year. To help that happen, we've prepared gather.town environments for you to join, with separate rooms for each league and booths for our sponsors - please visit them! Registered participants can log in on the underline site and then navigate to "RoboCup Lounge" in the left panel to get there. These can be used for informal meetings, league meetings, or however you wish - you should be able to join any time (some leagues are using other platforms for such meetings, which is also fine - please follow the instructions of your own organizing committees). I'm mainly writing now to ask everyone to mark your calendar for the opening ceremony and first symposium invited talk on Wednesday: June 23rd ========= UTC 13:30 - opening ceremony - Underline mainstage UTC 14:00 - invited talk by Dieter Fox - Underline mainstage UTC 15:00 - community gathering - Gather.town Before then, please make sure that if you've registered, you are able to access Underline and successfully join our Gather.town. I look forward to seeing you all soon. And good luck to all your teams! Best, Peter Stone President, RoboCup Federation

1 0

CFP - KBS Special Issue on Deep Learning
by Pub Conference 17 Jun '21

17 Jun '21

Robust, Explainable, and Privacy-Preserving Deep Learning https://www.journals.elsevier.com/knowledge-based-systems/call-for-papers/r… <https://urldefense.com/v3/__https://www.journals.elsevier.com/knowledge-bas…> *Aim and Scope* The exponentially growing availability of data such as images, videos and speech from myriad sources, including social media and the Internet of Things, is driving the demand for high-performance data analysis algorithms. Deep learning is currently an extremely active research area in machine learning and pattern recognition. It provides computational models of multiple nonlinear processing neural network layers to learn and represent data with increasing levels of abstraction. Deep neural networks are able to implicitly capture intricate structures of large-scale data and deploy in cloud computing and high-performance computing platforms. The deep learning approach has demonstrated remarkable performances across a range of applications, including computer vision, image classification, face/speech recognition, natural language processing, and medical communications. However, deep neural networks yield ‘black-box’ input-output mappings that can be challenging to explain to users. Especially in the healthcare, cybersecurity, and legal fields, black-box machine learning techniques are unacceptable, since decisions may have a profound impact on peoples’ lives due to the lack of interpretability. In addition, many other open problems and challenges still exist, such as computational and time costs, repeatability of the results, convergence, and the ability to learn from a very small amount of data and to evolve dynamically. Further, despite their enormous societal benefits, deep learning can pose real threats to personal privacy. For example, deep neural networks and other machine learning models are built based on patients' personal and highly sensitive data such as clinical records or tracked health data in the domain of healthcare. Moreover, they can be vulnerable to attackers trying to infer the sensitive data that was used to build the model. This raises important research questions about how to develop deep learning models that protect private data against inference attacks while still being accurate and useful predictive models. This Special Issue will present robust, explainable, and efficient next-generation deep learning algorithms with data privacy and theoretical guarantees for solving challenging artificial intelligence problems. This Special Issue aims to: 1) improve the understanding and explainability of deep neural networks; 2) improve the accuracy of deep learning leveraging new stochastic optimization and neural architecture search; 3) enhance the mathematical foundation of deep neural networks; 4) design new data privacy mechanisms to optimally tradeoff between utility and privacy; and 5) increase the computational efficiency and stability of the deep learning training process with new algorithms that will scale. Potential topics include but are not limited to the following: · Novel theoretical insights on the deep neural networks · Exploration of post-hoc interpretation methods which can shed light on how deep learning models produce a specific prediction and generate a representation · Investigation of interpretable models which aim to construct self-explanatory models and incorporate interpretability directly into the structure of a deep learning model · Quantifying or visualizing the interpretability of deep neural networks · Stability improvement of deep neural network optimization · Optimization methods for deep learning · Privacy preserving machine learning (e.g., federated machine learning, learning over encrypted data) · Novel deep learning approaches in the applications of image/signal processing, business intelligence, games, healthcare, bioinformatics, and security *Important Dates* · Submission Deadline: August 31, 2021 · First Review Decision: September 30, 2021 · Revisions Due: October 31, 2021 · Final Decision: November 30, 2021 · Final Manuscript: December 31, 2021 *Dissemination, Composition and Review Procedures* · A Call for Papers (CFP) will be circulated to invite submissions. · World leading researchers will be invited as authors. · To further attracting contributors from around the world, the CFP will be advertised across numerous society newsletters, different websites, mailing lists, conferences, associations, and social media groups, etc. This special issue will run as per the timeline given from submission to publication, while maintaining the rigorous peer review and high standards of the journal. All manuscripts submitted must be original, not under consideration elsewhere, and not previously published. A guide for authors and other relevant information for submission of manuscripts are available on the Guide for Authors’ page. Authors can expect their manuscripts to be reviewed fairly, and in a skilled, conscientious manner. To enhance objectivity, and to guarantee high scientific quality and relevance to the subject, three peer reviewers will be selected to evaluate a manuscript. The peer review process shall be designed to avoid bias and conflict of interest on the part of reviewers and shall be composed of experts in the relevant field of research. A key criterion in publication decisions will be the manuscript’s fit for the special issue and the readership of KBS. Papers will be published online as soon as accepted in continuous flow. *Submission Instructions* The submission system will be open around one week before the first paper comes in. When submitting your manuscript please select the article type “*VSI: Deep Learning*”. Please submit your manuscript before the submission deadline. All submissions deemed suitable to be sent for peer review will be reviewed by at least two independent reviewers. Once your manuscript is accepted, it will go into production, and will be simultaneously published in the current regular issue and pulled into the online Special Issue. Articles from this Special Issue will appear in different regular issues of the journal, though they will be clearly marked and branded as Special Issue articles. Please see an example here: https://www.sciencedirect.com/journal/science-of-the-total-environment/spec… <https://urldefense.com/v3/__https://www.sciencedirect.com/journal/science-o…> Please ensure you read the Guide for Authors before writing your manuscript. The Guide for Authors and the link to submit your manuscript is available on the Journal’s homepage.

1 0