Helsinki ICT Research Events

This event feed aggregates content from the Research Events feeds from the Helsinki Institute for Information Technology HIIT, Aalto University Department of Computer Science, and the University of Helsinki Department of Computer Science.

  • M.Sc. Tiina Lindh-Knuutila will defend her doctoral dissertation Computational Modeling and Simulation of Language and Meaning: Similarity-Based Approaches on 9 May 2014 in lecture hall T2 (Computer science building). The opponents are Prof. Emeritus Fred Karlsson, University of Helsinki and Prof. Ari Visa, Technical University of Tampere. The custodian is Prof. Erkki Oja.

    Announcement (fi, pdf...

  • Improved Distributed Steiner Forest Construction

    Dr. Christoph Lenzen, MIT, US

    Abstract:

    Finding near-optimal Steiner Forests is a classic graph problem, which arises in networks where one "purchases" (builds, rents,...) edges at pre-defined costs and seeks to connect several subsets of the nodes. It is a generalization of the well-known minimum spanning tree (MST) and Steiner Tree problems, where additional intricacy is added by the fact that it may or may not be beneficial to add...

  • Machine Learning for Smart Apps

    Prof. Ole Winther, Technical University of Denmark (DTU), Denmark

    Abstract:

    The algorithms that we are exposed to when we use the internet are based upon mathematical and statistical modelling of user behaviour. In the talk I will show what is under the hood of two "smart apps": findzebra.com (a search engine for rare diseases) and matrix factorisation for the Netflix Prize and one-class collaborative filtering. These examples show that predictive...

  • 31.03.2014 16:15–18:00
    Guest lecture
    T2, T building, Konemiehentie 2, Espoo

    The Internet and Computing Forum is a wide-ranging industry forum. The topics of the forum focus on new trends, hot areas and future opportunities in computer science and Internet technologies. The guest speakers are leaders in their fields in industry - top technical experts, scientists and innovators. This forum provides you with a unique opportunity to learn about the latest technical trends in...

  • 28.03.2014 10:15–11:15
    HIIT seminar
    Exactum B119
    Title: Classifier Chains for Multi-label Classification
     
    Abstract: Work on multi-label classification in the academic literature has expanded prolifically in recent years. In the multi-label scenario, each data instance may be associated with multiple class labels simultaneously (as opposed to a single class label, as in the traditional classification task). This context arises naturally...
  • 24.03.2014 16:15–18:00
    Guest lecture
    T2, T building, Konemiehentie 2, Espoo

    The Internet and Computing Forum is a wide-ranging industry forum. The topics of the forum focus on new trends, hot areas and future opportunities in computer science and Internet technologies. The guest speakers are leaders in their fields in industry - top technical experts, scientists and innovators. This forum provides you with a unique opportunity to learn about the latest technical trends in...

  • M.Sc. Kyunghyun Cho will defend his doctoral dissertation Explaining the Foundations of Deep Learning on 21 March 2014 in lecture hall T2 (Computer Science building). The opponent is Professor Nando der Freitas, University of Oxford, UK. The custodian is Professor Juha Karhunen.

    Announcement (pdf)

  • 21.03.2014 10:15–11:15
    HIIT seminar
    Exactum B119
    Title:
     
    Addition chains meet postage stamps: Number theory helps multiplication
     
     
    Abstract:
     
    Addition chains are integer sequences such as (1,2,4,8,10), where each element is a pairwise sum of earlier elements, for example 8 = 4+4.  They are commonly used to optimize repeated multiplication: if x is...
  • New Insights on Parameter Estimation of Boltzmann Machines and Deep Neural Architectures

    Prof. Nando de Freitas, Oxford University, UK

    Abstract:

    The talk has two new insights. First, I will show that it is possible to train most deep learning approaches -regardless of the choice of regularization, architecture, algorithms and datasets ? by learning only a small number of the parameters and predicting the rest with non-parametric methods. Often, this approach makes it possible to...

  • 17.03.2014 16:15–18:00
    Guest lecture
    T2, T building, Konemiehentie 2, Espoo

    The Internet and Computing Forum is a wide-ranging industry forum. The topics of the forum focus on new trends, hot areas and future opportunities in computer science and Internet technologies. The guest speakers are leaders in their fields in industry - top technical experts, scientists and innovators. This forum provides you with a unique opportunity to learn about the latest technical trends in...

Pages

Add to My Calendar