[UAI] Call-for-Papers Special Issue "Explainable User Models" (Multimodal Technologies and Interaction Journal)

[Oana Inel]

— Apologies for cross-posting —

Special Issue "Explainable User Models"

A special issue of Multimodal Technologies and 
Interaction (ISSN 2414-4088).

Important Dates & Facts:
Abstract/title submission: ideally until November 5, 2021
Manuscripts due by: February 20, 2022
Notification to authors: March 15, 2022

Website: https://www.mdpi.com/journal/mti/special_issues/Explainable_User_Models


Special Issue Information

This special issue addresses research on Explainable User Models. As AI 
systems’ actions and decisions will significantly affect their users, it is 
important to be able to understand how an AI system represents its users. It is 
a well-known hurdle that many AI algorithms behave largely as black boxes. One 
key aim of explainability is, therefore, to make the inner workings of AI 
systems more accessible and transparent.

Such explanations can be helpful in the case when the system uses information 
about the user to develop a working representation of the user, and then uses 
this representation to adjust or inform system behavior. E.g., an educational 
system could detect whether students have a more internal or external locus of 
control, a music recommender system could adapt the music it is playing to the 
current mood of a user, or an aviation system could detect the visual memory 
capacity of its pilots. However,  when adapting to such user models it is 
crucial that these models are accurately detected. Furthermore, for such 
explanations to be useful, they need to be able to explain or justify their 
representations of users in a human-understandable way. This creates a 
necessity for techniques that will create models for the automatic generation 
of satisfactory explanations intelligible for human users interacting with the 
system.

The scope of the special issue includes but is not limited to:

Detection and Modelling
• Novel ways of Modeling User Preferences
• Types of information to model (Knowledge, Personality, Cognitive differences, 
etc.)
• Distinguishing between stationary versus transient user models (e.g., 
Personality vs Mood)
• Context modeling (e.g., at work versus at home, lean in versus lean out 
activities)
• User models from heterogeneous sources (e.g., behavior, ratings, and reviews)
• Enrichment and Crowdsourcing for Explainable User Models

Ethics
• Detection of sensitive or rarely reported attributes (e.g., gender, race, 
sexial orientation)
• Implicit user modeling versus explicit user modeling (e.g., questionnaires 
versus inference from behavior)
• User modeling for self actualization (e.g., user modeling to improve dietary 
or news consumption habits)

Human understandability
• Metrics and methodologies for evaluating fitness for the purpose of 
explanations
• Balancing completeness and understandability for complex user models
• Explanations to mitigate human biases (e.g., confirmation bias, anchoring)
• Effect of user model explanation on subsequent user interaction (e.g., 
simulations, and novel evaluation methodologies)

Effectiveness
• Analysis or comparison of context of use of explanation (e.g., risk, time 
pressure, error tolerance)
• Analysis of context of use of system (e.g., decision support, prediction)
• Analysis or comparison of effect of explaining in specific domains (e.g., 
education, health, recruitment, security)

Adaptive presentation of the explanations
• For different types of user
• Interactive explanations
• Investigation of which presentational aspects are beneficial to tailor in the 
explanation (e.g., level of detail, terminology, modality text or graphics, 
level of interaction)


Prof. Dr. Nava Tintarev
Ms. Oana Inel
Guest Editors
___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

[UAI] Looking for PhD students and post-doctoral researchers

[Steven Latré]

Dear colleagues and students,

The IDLab research group of the University of Antwerp and imec, has several 
interesting open positions. We're looking both for enthusiastic PhD students 
and senior post-doctoral researchers. More specifically, we have the following 
open positions

PhD Students

  *   PhD Vacancy in Artificial Intelligence for Graph Evolution Prediction: 
working on GNNs and its application to process control in domains such as 
chemical engineering, water treatment and HVAC.
  *   PhD Vacancy on Next Generation AI for Perception and Cognition: working 
on next generation neural network architectures such as spiking neural networks 
and hyperdimensional computing
  *   PhD Vacancy in Artificial Intelligence for an Automated Lab: automating 
process control systems in the pharmaceutical sector

Senior researchers

  *   Senior Researcher on Causal Artificial Intelligence: leading a small team 
of PhD students working on topics such as causal machine learning and 
relational learning
  *   Artificial Intelligence Project Manager: translating machine learning 
research to applied projects in collaboration with industry.

All these positions can be found at https://jobs.idlab.uantwerpen.be/

Feel free to forward this mail to anyone that comes to mind.

Thanks in advance,

Steven Latre
steven.la...@uantwerpen.be

--
prof. dr. Steven Latré
Director
at IDlab, University of Antwerp, in collaboration with imec
steven.la...@uantwerpen.be
The Beacon I Sint-Pietersvliet 7 I 2000 Antwerpen I Belgium

T: +32 3 265 34 47
W: idlab.uantwerpen.be| 
idlab.technology | www.imec.be
T: @IDLabResearch
[https://idlab.uantwerpen.be/logos/imec.png] 
[https://idlab.uantwerpen.be/logos/uantwerp.png]  
[https://idlab.uantwerpen.be/logos/idlab.png]
___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

[UAI] Research Assistant in NLP at Uni Bath

[Ekaterina Kochmar]

The Department of Computer Science, University of Bath invites 
applications for a Research Assistant position in natural language 
processing and machine learning.


This is an interdisciplinary project, which is part of a collaboration 
between experts in forensic psychology, cyber-psychology and natural 
language processing across Bath and Bath Spa Universities. This 
interdisciplinary project is aiming to build and test a model of 
persuasive dialogue, consisting of conversational moves and linguistic 
strategies, which can be used to identify if and where persuasion is 
taking place in dialogue. Specifically, the research will focus on 
identification of attempts to persuade someone to act against their best 
interests – e.g., in scam communications. Results from this research 
will be integrated in the development of natural language processing and 
machine-learning tools to support the automation of persuasive dialogue 
detection within large corpora of texts.


Knowledge, skills, and experience:

- A graduate level degree (or close to obtaining one) in a relevant 
field
- Strong background in machine learning and/or natural language 
processing

- Strong programming skills
- Experience of working with text analysis and NLP toolkits
- Excellent command of English and strong communication and presentation 
skills


Employment conditions:

Grade 6, salary range: £26,715 – £32,817

Full time, fixed-term post

The post is initially available for 13 months (with possibility of 
subsequent renewal or PhD studentship).


Application deadline: 08/09/2021

For informal enquiries, please contact Ekaterina Kochmar 
(ek...@bath.ac.uk).


Please provide a CV and supporting statement with your application.

More information: https://www.bath.ac.uk/jobs/Vacancy.aspx?ref=CC8571
___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

[UAI] KRR@sac2022

[Carlo Taticchi]

###
The 37th ACM SIGAPP Symposium On Applied Computing
Brno, Czech Republic
April 25 - April 29, 2022

Track on Knowledge Representation and Reasoning (KRR)
Website: http://www.dmi.unipg.it/bista/organizing/KRR@sac2022

SUBMISSION DEADLINE: October 15, 2021

###




Overview:
The topic of the track covers an important field of research in Artificial 
Intelligence: Knowledge Representation and Reasoning (KRR) is dedicated to 
representing information about the world in a form that a computer system can 
utilise to solve complex tasks. Examples of knowledge representation formalisms 
include semantic nets, systems architecture, frames, rules, and ontologies. 
Some examples of automated reasoning engines include inference engines, theorem 
provers, and classifiers. KRR track will be a venue for all the researchers and 
practitioners working on the fundaments and applications of reasoning, and 
cross-fertilisation among different areas (e.g., Argumentation and Belief 
Revision). ACM SAC is ranked CORE:B, MAS:A-, SHINE:A. The average acceptance 
rate per track is under 25%. KRR track is organised for the third consecutive 
year at SAC.



Call for paper:
Knowledge Representation is the field of artificial intelligence that focuses 
on designing computer representations that capture information about the world 
that can be used to solve complex problems. Its goal is to understand and build 
intelligent behaviour from the top-down, focusing on what an agent needs to 
know with the purpose to behave intelligently, how this knowledge can be 
represented symbolically, and how automated reasoning procedures can make this 
knowledge available as needed. In KRR a fundamental assumption is that an 
agent's knowledge is explicitly represented in a declarative form, suitable for 
processing by dedicated reasoning engines. Topics of interest include:

• Argumentation.
• Belief revision and update, belief merging.
• Commonsense reasoning.
• Contextual reasoning.
• Description logics.
• Diagnosis, abduction, explanation.
• Inconsistency and exception tolerant reasoning, paraconsistent logics.
• KR and autonomous agents: intelligent agents, cognitive robotics, multi-agent 
systems.
• KR and decision making, game theory, social choice.
• KR and machine learning, inductive logic programming, knowledge discovery and 
acquisition.
• Logic programming, answer set programming, constraint (logic) programming.
• Non-monotonic logics, default logics, conditional logics.
• Preferences: modelling and representation, preference-based reasoning.
• Reasoning about knowledge and belief, dynamic epistemic logic, epistemic and 
doxastic logics.
• Reasoning systems and solvers, knowledge compilation.
• Spatial reasoning and temporal reasoning, qualitative reasoning.
• Uncertainty, representations of vagueness, many-valued and fuzzy logics.

We would like to invite authors to submit papers on research in the KRR area, 
with particular emphasis on assessing the current state of the art and 
identifying future directions.
Submissions fall into the following categories:
• Original and unpublished research work.
• Reports of innovative computing applications in the arts, sciences, 
engineering, and business areas.
• Reports of successful technology transfer to new problem domains.
• Reports of industrial experience and demos of new innovative systems.




Deadlines and Important Dates:
October 15, 2021: Submission of regular papers and SRC abstracts.
December 10, 2021: Notification of papers and posters and SRC 
acceptance/rejection.
December 21, 2021: Camera-ready copies of accepted papers, and registration of 
at least one author.
April 25-29, 2022: Conference




Submissions Instructions for Regular Papers and SRC Abstracts:
Original papers addressing any of the listed topics of interest (or related 
topics) will be considered. Each submitted paper will be fully refereed and 
undergo a double-blind review process by at least three referees. Accepted 
papers will be included in the ACM SAC 2022 proceedings and published in the 
ACM digital library, being indexed by Thomson ISI Web of Knowledge and Scopus. 
Submissions should be properly anonymised to facilitate blind reviewing: the 
author(s) name(s) and address(es) must NOT appear in the body of the paper, and 
self-reference should be in the third person.

Paper size is *strictly* limited to 8 pages in SAC style; a maximum of 2 
additional pages may be included for an additional fee, extending the final 
version of the accepted paper.

Please check the author kit latex style on the main SAC website: 
https://www.sigapp.org/sac/sac2022/authorkit.html. Papers failing to comply 
with length limitations risk immediate rejection.

Submissions will be in electronic format, via the website: (TO BE ANNOUNCED)
PLEASE PAY ATTENTION TO SELECT THE KRR TRACK BY CHECKING THE TRACK RADIO 
BU

[UAI] [robotics meeting] CFP and participate seminars, IEEE IROS2021 workshop “Cognitive and Social Aspects of Human Multi-Robots Interaction”

[Liu, Rui]

Dear colleagues,

We would like to draw your attention and invite you to contribute to our 
IROS2021 workshop “Cognitive and Social Aspects of Human Multi-Robots 
Interaction”, submission due on Sep 12th, 2021.

Workshop official website: https://www.kent.edu/cae/hmrs2021


---

Title: Cognitive and Social Aspects of Human Multi-Robot Interaction
- Workshop date: September, 27th , 2021
- Submission Deadline: September 12th, 2021
- Submission to Email: hmrs.iros2...@gmail.com
- Submission contents: Short abstract 1-4 pages; full length paper 6 pages; 
previously-published papers are also encouraged to submit.


Motivation
The last 30 years have witnessed significant progress in robot swarms and 
multi-robot systems (MRS). These systems incorporate multiple robots, possibly 
with diverse perceiving and executing capabilities, which are put together in 
collaborative settings to achieve a common goal. Swarm and MRS have been used 
to serve a variety of real-life applications such as victim rescue, 
reconnaissance, intelligence gathering, and multiple ground target tracking. 
These tasks cannot be executed by single-robot systems due to requirements for 
diverse specialization, spatial distribution, or temporal requirements imposing 
the need for parallelization.

Despite the great potential and unique qualities these systems have, they lack 
human-like intelligence that enables them to work under full autonomy. As such, 
the human element must be involved due to its so far unmatched cognitive 
abilities which enable a human to ensure the alignment between system 
operations and mission objective, set priorities, detect failures, and 
intervene to fix errors. In the foreseeable future, when robot capabilities 
advance, it is expected that humans will still take part in these systems due 
to ethical and accountability considerations. However, due to the multi-agent 
characteristics bringing in accumulated uncertainty and increased complexity, 
it is challenging to establish effective collaboration between humans and 
robots.

First, a human has limited cognitive resources, making it difficult to 
simultaneously supervise multiple robots, respond to their requests, and 
identify their faults. Second, human users vary in their ability to assess team 
performance and detect behavior abnormality.

In this workshop, the objective is to explore the cognitive and social aspects 
in human multi-robot system (MRS) interaction. Our intent is to take 
inspiration and learn from the broad base of researchers in the following area:

Topics of Interest
• Trust measurement, modeling, and maintenance
• Safety in MRS and human-swarm interaction
• Distributed cognition (or distributed cognitive systems)
• Human cognitive load measurement
• Transparency and explanation in MRS
• Modelling and analysis human-swarm interaction
• Social acceptance, norms, and ethical issues in human 
environments
• Autonomy dependency
• Cognitive Control for heteregenous teaming.
• Shared decision making in multi-robot multi-human interaction
• Datasets and simulator kits
• New applications related to intuitive human-MRS/swarm 
interaction
• Self-learning and healing in Human MRS/swarm interaction\


Invited Speakers
• Katia Sycara, Professor, AAAI/IEEE Fellow, School of Computer 
Science, Carnegie Mellon University, USA
• Guang-zhong Yang, Professor, IEEE Fellow, Institute of 
Medical Robotics, Shanghai Jiao Tong University, China, Editor in Chief of 
Science Robotics
• Michael Lewis, Professor, School of Computing and 
Information, University of Pittsburgh, USA
• Hussein Abbass, Professor, IEEE Fellow, School of Engineering 
& IT, University of New South Wales, Canberra, Australia, Editor in Chief of 
IEEE Transactions on Artificial Intelligence
• Maria Gini, Professor, AAAI/ACM//IEEE Fellow, College of 
Science & Engineering, University of Minnesota, USA
• Lorenzo Sabattini, Associate Professor ，University of Modena 
and Reggio Emilia, France, Editor in Chief of IEEE ICRA2021
• Joseph Lyons, Senior Research Scientist, US Air Force 
Research Lab, USA
• Wei Dong, Associate Professor, Shanghai Jiao Tong University, 
China
• Wilko Schwarting, Postdoctoral Research Associate, 
Massachusetts Institute of Technology, USA
• Sylvia Herbert, Assistant Professor, University of 
California, San Diego, USA

Call for contributions
We invite interested participants to submit short papers 1-4 pages and 
previously published papers for the contribution talks of 10 minutes. Please 
send you

[UAI] [HIRING] Research/Applied Scientist for Surface Transportation / Sustainability @ Amazon EU in Luxembourg

[Gross, Martin]

Hello everyone,

Amazon EU has an opening for a research / applied scientist at the Amazon EU in 
Luxembourg to work on problems related to surface transportation and 
sustainability (i.e. the middle-mile logistics part of Amazon's climate pledge).

You will be joining a quickly growing multi-national research team that tackles 
challenging problems related to logistics and sustainability on a world wide 
scale. Our team is in the fast growing Amazon EU headquarters in Luxembourg 
City, which has more than 3000 employees already.

Luxembourg is a small country in the heart of Europe with a very international 
population and excellent public health care and social security, free public 
transport and very low crime. It is well connected to all the major European 
cities. Luxembourg has three official languages (Luxembourgish, French, German) 
and English is widely spoken as well.

Amazon is committed to a diverse and inclusive workplace. Amazon is an equal 
opportunity employer and does not discriminate on the basis of race, national 
origin, gender, gender identity, sexual orientation, protected veteran status, 
disability, age, or other legally protected status.

We are very willing to sponsor visas!

BASIC QUALIFICATIONS

* PhD in Operations Research, Machine Learning, Statistics, Applied 
Mathematics, Engineering, Computer Science or other field related to algorithms.

* Excellent written and verbal communication skills. Ability to communicate at 
a level appropriate to the audience.

* Experience implementing algorithms in traditional programming languages (C++/ 
Java/ python)

* Comfortable to tradeoff complexity and efficiency of solution methodologies, 
according to the requirements of the problem. Ability to deal with ambiguity.

* Experience designing and implementing models and algorithms for one or more:

* Combinatorial optimization problems (e.g., scheduling, vehicle routing, and 
facility location).

* Continuous optimization problems (e.g., linear programming, convex 
programming, non-convex programming).

* Predictive analytics (e.g., forecasting, time-series, neural networks)

* Prescriptive analytics (e.g., stochastic optimization, bandits, reinforcement 
learning).

PREFERRED QUALIFICATIONS

* Detailed knowledge of optimization methods including linear and mixed-integer 
programming, network modeling, constraint programming, approximation 
algorithms, and advanced heuristic techniques.

* Expertise on MIP strategies to customize and leverage commercial algorithms 
and adapt them as required.

* Detailed knowledge of forecasting techniques with time-series tools, 
including ARIMA models, exponential smoothing, LSTM, CNNs.

* Expertise on policy optimization techniques, including reinforcement 
learning, deep Q-learning, bandits, and online optimization.

* Experience implementing models and analysis tools through the use of 
high-level modeling languages (e.g. R, Matlab as examples).

* Experience collecting, processing and combining big data with appropriate 
methodologies (e.g. Hadoop, Map-Reduce)

To apply please use the link:

https://amazon.jobs/en/internal/jobs/1667294/research-scientist

Best regards,
_
Martin Gross
Senior Research Scientist
EU ATS-RS
[ATS-RS-logo-small]




Amazon EU societe a responsabilite limitee, 38 avenue John F. Kennedy, L-1855 
Luxembourg, R.C.S. Luxembourg n
B101818, autorisation d'etablissement en qualite de commercante n 134248, TVA 
LU 20260743


___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

[UAI] [HIRING / Updated] Research/Applied Scientist for Surface Transportation / Sustainability @ Amazon EU in Luxembourg

[Gross, Martin]

[Updated: Now with correct link]

Hello everyone,

Amazon EU has an opening for a research / applied scientist at the Amazon EU in 
Luxembourg to work on problems related to surface transportation and 
sustainability (i.e. the middle-mile logistics part of Amazon's climate pledge).

You will be joining a quickly growing multi-national research team that tackles 
challenging problems related to logistics and sustainability on a world wide 
scale. Our team is in the fast growing Amazon EU headquarters in Luxembourg 
City, which has more than 3000 employees already.

Luxembourg is a small country in the heart of Europe with a very international 
population and excellent public health care and social security, free public 
transport and very low crime. It is well connected to all the major European 
cities. Luxembourg has three official languages (Luxembourgish, French, German) 
and English is widely spoken as well.

Amazon is committed to a diverse and inclusive workplace. Amazon is an equal 
opportunity employer and does not discriminate on the basis of race, national 
origin, gender, gender identity, sexual orientation, protected veteran status, 
disability, age, or other legally protected status.

We are very willing to sponsor visas!

BASIC QUALIFICATIONS

* PhD in Operations Research, Machine Learning, Statistics, Applied 
Mathematics, Engineering, Computer Science or other field related to algorithms.

* Excellent written and verbal communication skills. Ability to communicate at 
a level appropriate to the audience.

* Experience implementing algorithms in traditional programming languages (C++/ 
Java/ python)

* Comfortable to tradeoff complexity and efficiency of solution methodologies, 
according to the requirements of the problem. Ability to deal with ambiguity.

* Experience designing and implementing models and algorithms for one or more:

* Combinatorial optimization problems (e.g., scheduling, vehicle routing, and 
facility location).

* Continuous optimization problems (e.g., linear programming, convex 
programming, non-convex programming).

* Predictive analytics (e.g., forecasting, time-series, neural networks)

* Prescriptive analytics (e.g., stochastic optimization, bandits, reinforcement 
learning).

PREFERRED QUALIFICATIONS

* Detailed knowledge of optimization methods including linear and mixed-integer 
programming, network modeling, constraint programming, approximation 
algorithms, and advanced heuristic techniques.

* Expertise on MIP strategies to customize and leverage commercial algorithms 
and adapt them as required.

* Detailed knowledge of forecasting techniques with time-series tools, 
including ARIMA models, exponential smoothing, LSTM, CNNs.

* Expertise on policy optimization techniques, including reinforcement 
learning, deep Q-learning, bandits, and online optimization.

* Experience implementing models and analysis tools through the use of 
high-level modeling languages (e.g. R, Matlab as examples).

* Experience collecting, processing and combining big data with appropriate 
methodologies (e.g. Hadoop, Map-Reduce)

To apply please use the link:

https://www.amazon.jobs/en/jobs/1667294/research-scientist

Best regards,
_
Martin Gross
Senior Research Scientist
EU ATS-RS
[ATS-RS-logo-small]




Amazon EU societe a responsabilite limitee, 38 avenue John F. Kennedy, L-1855 
Luxembourg, R.C.S. Luxembourg n
B101818, autorisation d'etablissement en qualite de commercante n 134248, TVA 
LU 20260743


___
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai