Colloquia and Seminars

To join the email distribution list of the cs colloquia, please visit the list subscription page.


Computer Science events calendar in HTTP ICS format for of Google calendars, and for Outlook.

Academic Calendar at Technion site.

Upcoming Colloquia & Seminars

  • The 7th Summer School on Cyber and Computer Security

    The 7th Summer School on Cyber and Computer Security

    Date:
    Tuesday, 2.10.2018, 09:30
    Place:
    Technion

    The Hiroshi Fujiwara Cyber Security Research Center will hold the 7th Summer School on Cyber and Computer Security: "Trusted Execution and Hardware Side Channels".

    The event will take place on Tuesday-Thursday, October 2nd-4th, 2018 at the Technion, Haifa.

    Chairs:
    Mark Silberstein, Technion
    Yossi Oren, Ben-Gurion University

    Speakers:
    Ittai Anati, Intel Israel
    Herbert Bos, VU Amsterdam
    Christof Fetzer, TU Dresden Daniel Genkin, University of Michigan
    Taesoo Kim, Georgia Tech
    Eyal Ronen, Weismann Institute of Science
    Avishai Wool, Tel-Aviv University

    Registration is open.

    More details, full program and information about The Hiroshi Fujiwara Cyber Security Research Center.

  • Label Expansion - Integrating Prior Knowledge to Large Label Set Tasks

    Speaker:
    Dor Zohar, M.Sc. Thesis Seminar
    Date:
    Thursday, 11.10.2018, 14:30
    Place:
    Taub 301
    Advisor:
    Prof. Roi Reichart

    In many Natural Language Processing classification tasks, the label space consists of the entire vocabulary, and therefore might have hundreds of thousands of labels. Important tasks such as language modeling, machine translation and dialog systems all have vocabulary label sets. Due to Zipf's law, a large number of words in the vocabulary will have only a few appearances in the corpus, hindering the ability to learn proper representations for these words. This work utilizes a prior hierarchical clustering of the words in the label set, in order to achieve better representation of the words. The hierarchical structure enables starting with a label set of coarse-grained concepts, and gradually refining it to the whole vocabulary. In our work, we examine two tasks with vocabulary label sets - language modeling and word2vec. We present the contribution of the prior knowledge to the performance on the two tasks comparing to the baseline, both in intrinsic and extrinsic tests.

  • Predicting a Better Future for Asynchronous Stochastic Gradient Decent with DANA

    Speaker:
    Ido Hakimi, Ph.D. Thesis Seminar
    Date:
    Tuesday, 30.10.2018, 14:30
    Place:
    Taub 601
    Advisor:
    Prof. Assaf Schuster

    Distributed training can significantly reduce the training time of neural networks. Despite its potential, however, distributed training has not been widely adopted due to the difficulty of scaling the training process. Existing methods suffer from slow convergence and low final accuracy when scaling to large clusters, and often require substantial re-tuning of hyper-parameters.

    We propose DANA, a novel approach that scales to large clusters while maintaining state-of-the-art accuracy and converge speed without having to re-tune parameters that are optimized for training on a single worker. By adapting Nesterov Accelerated Gradient to a distributed setting, DANA is able to predict the future position of the model's parameters and so mitigate the effect of gradient staleness, one of the main difficulties in asynchronous SGD.