We have a Webpage for this workshop: <https://sites.google.com/es.net/dise-workshop/home>.

You can find the papers and presentations uploaded here.

----------------------------------------

This is a Joint Workshop between ICML (https://icml.cc/Conferences/2018/CallForWorkshops), AAMAS (http://celweb.vuse.vanderbilt.edu/aamas18/workshopsList/) and IJCAI (https://www.ijcai-18.org/workshops/).

Modern technological advances in engineering fields such as automotive, aerospace, robotic, even data centers and networks, are exploiting machine learning to improve and maintain mission critical activities. These systems are large, complex and require real-time learning with feedback to ensure they function as desired. Detecting anomalies, analyzing failures and predicting future system state are imperative and are becoming part of engineering integrative approaches. Research in algorithmic methods to make real-time decisions based on fast arriving, high-volume condition data, on-site feedback and data models is needed to train machine learning models quickly and correctly.

This workshop aims to bring together diverse researchers from areas such as reinforcement learning, autonomous agents, game theory, controls and operations engineering teams to develop approaches which enable real-time discovery, inference and computational tools. These techniques are aimed to influence engineering operations teams in aerospace, self-driving automotive, robotics, data centers and any engineering operations that automate mission-critical and safety applications.

We encourage focus on aspects of deep learning to solve problems into domains where continuous training and fast results are needed without jeopardizing prediction accuracy. However, we also encourage exploration of new innovative machine learning approaches, which can solve these problems with improved latency. We are also seeking contributions in advances of streaming and distributed algorithms, heterogeneous and high-dimensional data sets and real-time decision- making algorithms for operations.

Some possible topics of interests but not confined are:

• Adaptation: How can systems learn and adapt to changes in the environment (especially in dynamic environments) when training data is less and requires quick model assumption. How can principles of autonomous agents working together to build large engineering systems be exploited to react in dynamic situations.

• Noisy and poor data sets: How can machine learning models be trained to understand noisy data sets for quick learning. Missing data exploration?

• Detecting anomalous behavior: How can anomalies be detected quickly and partitioned appropriately such that correct actions are applied?

• Improving latency: How can machine learning algorithms be improved to produce results quickly than previously anticipated?

• Improving software and hardware performance: Exploring models of GPU, HPC processing and FPGAs to improve the performance of algorithms can greatly influence their use in engineering design. Experimental demonstrations are encouraged to display this.

• Reinforcement learning: How can machine learn correct behavior? Can training be made quicker with guidance to allow algorithms to produce corrective measure when anomalies are detected?

• Human factors: how can engineers maintaining the system interact with the self- autonomous system

• Open problems in engineering where machine learning is not proving fruitful. What are the open problems in operations where practical machine learning is difficult to apply? What are the limitations and how can these be improved?

Workshop dates will be 15th of July 2018, located as part of Joint IJCAI/ECAI/AAMAS/ICML Call for Workshops. Specific dates will be announced soon. 

The abstract and paper submission deadline is the 28th of May 2018. Please upload the final PDF as an updated version in your existing submission on EasyChair.

All submissions must obey the following formatting requirements.

• Submit papers of no more than six (6) single–spaced pages for long papers (and four (4) for short papers), including figures, tables, any appendices, etc., followed by as many pages as necessary for references.
• Submit papers formatted for printing on Letter-sized (8.5” by 11”) paper. Paper text blocks must follow ACM guidelines: double-column, with each column 9.25” by 3.33”, 0.33” space between columns. Each column must use 10-point font or larger, and contain no more than 55 lines of text.
• It is your responsibility to ensure that your submission satisfies the above requirements. If you are using LaTeX, you can make use of this template for ACM conference proceedings. 
• For your posters, we suggest A0 size measuring 841 × 1189 mm (33.1 × 46.8 in). Note that the workshop venue cannot accommodate posters larger than 910 × 1220 mm (36 × 48 in). 

All papers must be original and not simultaneously submitted to another journal or conference. The following paper categories are welcome:

• Full papers describing mature solutions of deep learning in safety critical systems from various engineering domains such as security networks and self-autonomous cars or more.
• Short paper on early demonstrations of deep learning in safety critical systems from various engineering domains.
• Posters on early works (PhD students and early career researchers are particularly encouraged)

Committees

Program Committee

• Mariam Kiran, Lawrence Berkeley National Lab, US
• Alex Sim, Lawrence Berkeley National Lab, US
• John Wu, Lawrence Berkeley National Lab, US
• Samir Khan, University of Tokyo, Tokyo, Japan
• Takehisa Yairi, University of Tokyo, Japan
• Rajkumar Kettimuthu, Argonne National Laboratory, US

Organizing committee

• Mariam Kiran, Lawrence Berkeley National Lab
• Samir Khan University of Tokyo, Tokyo, Japan

Contact

All questions about submissions should be emailed to <mkiran@es.net, khan@ailab.t.u-tokyo.ac.jp>.