Tehran Institute for Advanced Studies (TEIAS)

/ Actual Causality and Counter-Factual Reasoning __ Mohammad Reza Mousavi

A Myhill-Nerode Theorem for Register Automata and Symbolic Trace Languages

Talk A Myhill-Nerode Theorem for Register Automata and Symbolic Trace Languages October 14, 2020(23 Mehr, 1399) Venue This Talk is online [email protected] +982189174612 Frits Vaandrager Professor of Informatics for Technical Applications, Radboud University, Netherlands Overview We propose a new symbolic trace semantics for register automata (extended finite state machines) which records both the sequence of…

Read More

Convergence and Equilibrium in Generative Adversarial Networks

Talk Convergence and Equilibrium in Generative Adversarial Networks September 13, 2020(23 Shahrivar, 1399) Venue This Talk is online [email protected] +982189174612 Dr. Farzan Farnia Postdoctoral Research Associate at the Massachusetts Institute of Technology (MIT) Overview Generative adversarial networks (GANs) represent a zero-sum game between two machine players, a generator and a discriminator, designed to learn the…

Read More

Research Methods in Networks and Systems

Talk Research Methods in Networks and Systems September 09, 2020(19 Shahrivar, 1399) Venue This Talk is online [email protected] +982189174612 Srinivasan Keshav Robert Sansom Professor of Computer Science at the University of Cambridge   Overview In this talk, I review the basic principles for performing and disseminating great research. I start with some hints on the…

Read More

Active and Multitask Learning Approaches to Low-Resource Neural Machine Translation

Talk Active and Multitask Learning Approaches to Low-Resource Neural Machine Translation September 2, 2020(12 Shahrivar, 1399) Venue This Talk is online [email protected] +982189174612 Dr. Gholam Reza Haffari Associate Professor in Department of Data Science & AI of Monash University Overview Machine translation is being revolutionized by the introduction of neural models. However, it is challenging…

Read More