Dr. Amir H. Payberah
Title: Distributed Learning
He is an assistant professor of computer science at the division of Software and Computer System (SCS) of KTH Royal Institute of Technology in Sweden. He is also a member of the Distributed Computing at KTH (DC@KTH) and the Center on Advanced Software Technology Research (CASTOR). Prior to that, he was a machine learning scientist at University of Oxford (2017-2018), and a senior researcher at the Swedish Institute of Computer Science (2013-2017). Amir got his PhD from KTH Royal Institute of Technology in June 2013. His research interests include distributed systems and algorithms, large scale machine learning and deep learning, and data intensive computing platforms. (https://payberah.github.io)
Training deep neural networks is computationally intensive and time consuming. This is mainly due to the massive amount of training dataset and/or large number of parameters of models. Sometimes such datasets or model parameters are too big to be stored on a single machine, and one possible solution is to parallelize the training process. In this talk we will talk about data-parallelization and model-parallelization approaches, two popular techniques to overcome the aforementioned problem.
Professor Mohammad Bagher Menhaj
University : Amirkabir University of Technology
Email : email@example.com
Home Page : https://aut.ac.ir/cv/2304/Mohammad-Bagher-Menhaj?slc_lang=en&&cv=2304&mod=scv
Title:Cognitive Computing: theory and applications
Prof. Menhaj holds a Post-doctoral in Control Engineering from Oklahoma State University. In 1993, he came to Iran from the United States at the invitation of Amirkabir University. He is the author of more than 12 volumes of books. The publication of more than 190 articles in prestigious international journals and the publication of more than 280 articles in international conferences are examples of his valuable scientific background. He was selected by the ISI as an outstanding scientist in 2004. The main areas of his research are: Adaptive Control, Computational Intelligence, Multi-Agent Systems, Robotics and Cognitive Science.
Cognitive Computing is an emerging paradigm of intelligent computing methodologies and systems based on cognitive informatics, which implements computational intelligence by autonomous inferences and processing platforms, perceptions mimicking the brain mechanisms. Its goal is to simulate human thought processes in a computerized model.
In this talk, I will first focus on principles, followed by extensive studies of cognitive computing, and ends with its applications and the case studies. I will discuss a wide variety of diverse cognitive computing applications and recent developments, such as data analysis, machine learning, neural networks, data analytics in cyber security, pattern recognition, fault detection and diagnostics, and analytical platforms to study the brain-computer interface.
Submission Deadline: Oct 30, 2020
Notification of Acceptance: Nov 13, 2020
Workshop Proposal deadline: Nov 6, 2020
Workshop Admission Announcement: Nov 20, 2020
Registration and Submission for Final Version: Nov 27, 2020
Conference Date:Dec 23 and 24, 2020
No. 64 Jalal Al Ahmad St, Mashhad, Iran
Postal Code: 9188148848
Expert Secretariat: S.M.Kashani
Oct 24, 2020