The Coq mailing list

[Guy Katz <guykatz AT cs.huji.ac.il>]

2nd Workshop on Formal Methods for ML-Enabled Autonomous Systems (FoMLAS 2019)

A satellite event of the CAV conference

New York City

July 14, 2019

https://fomlas2019.wixsite.com/fomlas2019

=====================================

SCOPE

In recent years, machine learning has emerged as a highly effective way for creating real-world software, and is revolutionizing the way complex systems are being designed all across the board. In particular, this new approach is being applied to autonomous systems (e.g., autonomous cars, aircraft), achieving exciting results that are beyond the reach of manually created software. However, these significant changes have created new challenges when it comes to explainability, predictability and correctness: Can I explain why my drone turned right at that angle? Can I predict what it will do next? Can I know for sure that my autonomous car will never accelerate towards a pedestrian? These are questions with far-reaching consequences for safety, accountability and public adoption of ML-enabled autonomous systems. One promising avenue for tackling these difficulties is by developing formal methods capable of analyzing and verifying these new kinds of systems. 

The goal of this workshop is to facilitate discussion regarding how formal methods can be used to increase predictability, explainability, and accountability of ML-enabled autonomous systems. The workshop welcomes results ranging from concept formulation (by connecting these concepts with existing research topics in verification, logic and game theory), through algorithms, methods and tools for analyzing ML-enabled systems, to concrete case studies and examples.

Topics of interest include, but are not limited to:

    Formal specifications for systems with ML components

    SAT-based and SMT-based methods for analyzing systems with ML components

    Mixed-integer Linear Programming and optimization-based methods for the verification of systems with ML components

    Testing approaches to ML components

    Statistical approaches to the verification of systems with ML components

    Approaches for enhancing the explainability of ML-based systems

    Techniques for analyzing hybrid systems with ML components

=====================================

IMPORTANT DATES (all dates are AOE)

    Abstract submission       April 22, 2019    (optional)

    Full paper submission    May 4, 2019

    Author notification          June 10, 2019

    Workshop                       July 14, 2019

=====================================

COMMITTEE

Conference Chairs:

  

    Guy Katz                          (The Hebrew University of Jerusalem, Israel)

    Nina Narodytska              (VMWare Research, USA)

Program Committee: 

    Clark Barrett                     (Stanford University, USA)

    Chih-Hong Cheng            (Fortiss - Research Institute of the Free State of Bavaria, Germany)

    Suman Jana                     (Columbia University, USA)

    Jean-Baptiste Jeannin     (University of Michigan, USA)

    Susmit Jha                       (SRI, USA)

    Taylor T. Johnson             (Vanderbilt University, USA)

    Temesghen Kahsai           (Groq Inc., USA)

    Marta Kwiatkowska          (University of Oxford, UK)

    Alessio Lomuscio             (Imperial College London, UK)

    Luca Pulina                      (University of Sassari, Italy)

    Armando Solar-Lezama   (MIT, USA)

    Martin Vechev                  (ETH Zurich, Switzerland)

=====================================

SUBMISSIONS

Three categories of submissions are invited:

    Original papers: papers that contain original research and sufficient detail to assess the merits and relevance of the submission. For papers reporting experimental results, authors are strongly encouraged to make their data available.

    Presentation-only papers: papers that describe work recently published or submitted. We see this as a way to provide additional access to important developments that the workshop attendees may be unaware of.

    Extended abstracts: given the informal style of the workshop, we strongly encourage the submission of preliminary reports of work in progress. They may range in length from very short (a couple of pages) to the full 10 pages and they will be judged based on the expected level of interest for the community.

All accepted papers will be posted online as part of informal proceedings on the day of the conference. At least one author of each accepted paper is expected to attend the workshop and present the work. Papers in all categories will be peer-reviewed. Papers should not exceed 10 pages and should be in standard-conforming PDF. Technical details may be included in an appendix to be read at the reviewers' discretion. Final versions should be prepared in LaTeX using the LNCS style. (The 10 page does not include references.)

To submit a paper, use EasyChair: http://www.easychair.org/conferences/?conf=fomlas2019

For any questions, please contact us at: fomlas2019 AT gmail.com