۲۸ مرداد · Workshops

ACM Summer Scholl 2017
۱۴ تیر · Classes

To see more details and register for a class visit out Evand page:

http://evand.ir/organizations/utacm

Deep Learning Summer School 2017
۲۶ خرداد · Classes

Introduction to Neural Network

Optimization in Neural Networks

Convolutional Neural Networks

Regularization in CNNs

Deep CNNs

Recurrent Neural Networks

Introduction to NLP with RNNs

Visual Tasks with RNNs

Deep learning Research (invited talk)

Deep learning softwares (Tensorflow, Pytorch) will be introduced and practiced through the course projects.

 

Register on: https://evand.com/events/utacm-deep-learning

Data Analysis Challenge
۱۳ بهمن · Contests

Discrete Mathematics Contest
۱۱ بهمن · Contests

After holding the Discrete Mathematics Contest in past semesters, ACM Student Chapter decided to hold this event once again. This event was held in a new format at the end of both semesters of last academic year. In order to improve the contest and increase student participation in the university activities, a team of eight students from Faculty of Computer Engineering of the University of Tehran was formed to set up a new website for the contest and the format of the contest changed to a hackathon

Hossein Akhlaghpour - Deep Learning & CRISPR
۲۳ دی · Talks

The power of prediction is a key to survival. We have seen rise and fall of industries in the last couple of decades; events that impacted millions of lives. In today’s world nothing impacts the job market more than birth of a disruptive technology. Two of these technologies Deep Learning and CRISPR and their impacts can be dramatically different than any other technologies. A Sci-Fi future is not just plausible, it might even be inevitable and such a future is possible only by combining these two technologies.

 

Clustered regularly interspaced short palindromic repeats (CRISPR) are segments of prokaryotic DNA containing short, repetitive base sequences.

 

Ali Eslami - Deep Learning
۱۶ دی · Talks

Deep learning has transformed the way in which we design machine learning systems. In this talk a brief overview of modern advances to the deep learning paradigm was provided. Starting off with deep reinforcement learning: DQN (Nature, 2015) and A3C (CoRR, 2015), motivate the role of generative modelling in the emerging research landscape and discuss several recent models, including Pixel CNNs (ICML, 2016), AIR (NIPS, 2016) and Conditional 2D->3D (NIPS, 2016).

 

Video : http://www.aparat.com/utacm

 Slides: http://acm.ut.ac.ir/acm/uploads/post_attachment/attachment/87/Intelligent_Perception.pd

 

 

علی‌اسلامی DeepLearning
ICPC Regional Contest University of Tehran Ranks
۰۷ دی · News

University of Tehran ACM ICPC programming contest was held on October 24th. “The Last One ?” team and “NeshesTeam” team achieved first and third place in the contest. These two teams competed among 47 teams from other universities of Iran in ICPC regional contest which was held on 24th November in Sharif university of technology and the teams from University of Tehran could achieve second and third place in the contest and NeshesTeam got the opportunity to attend The 2017 ACM-ICPC World Finals.

Dr. Lesani - Certified Concurrent and Distributed Systems
۰۷ دی · Talks

Aspects of concurrency and distribution pervasively appear in modern computing systems, including personal devices, data centers, aircrafts and medical devices. Due to complicated interactions between processes, concurrent and distributed systems are subtle and prone to bugs. Such bugs have led to death of patients and blackouts with millions of dollars financial loss. Can we build concurrent and distributed systems with static safety and security guarantees?

Fault-tolerant distributed runtime verification
۳۰ آذر · Talks

Runtime Verification (RV) is a lightweight method for monitoring the formal specification

of a system during its execution. In this talk, I will show that employing the existing formal

logics semantics for runtime verification result in inconsistent distributed monitoring for

some formulas. To tackle this problem, we introduced a family of logics, that refines LTL by

incorporating 2k +4 truth values, for each k >= 0. These truth values can be effectively used

by local monitors to reach a consistent global set of verdicts for each given formula, provided

k is sufficiently large. I will also intoriduce an algorithm for monitor construction enabling

fault-tolerant distributed monitoring based on the aggregation of the individual verdicts by

each monitor.

 

On-Time Actors in Cyber-Physical Systems - Can We Trust Self-Driving Cars?
۲۶ آذر · Talks

In the era of Cyber-Physical systems and Internet of Things, software system developers have to deal with increasing complexity of huge and heterogenous systems. Building distributed, asynchronous, and event-based systems is a complicated task. Moreover, because of the dynamic and evolving nature of autonomous systems, a key challenge is providing runtime quality assurance techniques - in form of verification and performance analysis – that can react to changes in a timely manner.

Last< >Next