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.
-
28.03.2014 10:15–11:15
HIIT seminar
Exactum B119Title: Classifier Chains for Multi-label ClassificationAbstract: 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... -
28.03.2014 10:15–11:15
HIIT seminar
Exactum B119Title: 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 and frequently in many domains:...
-
24.03.2014 16:15–18:00
Guest lecture
T2, T building, Konemiehentie 2, EspooThe 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.
-
21.03.2014 10:15–11:15
HIIT seminar
Exactum B119Title:Addition chains meet postage stamps: Number theory helps multiplicationAbstract: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... -
21.03.2014 10:15–11:15
HIIT seminar
Exactum B119Title:
Addition chains meet postage stamps: Number theory helps multiplicationAbstract:
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 given, and x^10 is required, one computes successively x^2, x^4, x^8 and then x^10 = x^2 * x^8. The... -
20.03.2014 16:00–17:15
Alumni event
Exactum, Kumpula Campus
Science in the Best CompanyThe general web page of the event can be found at http://www.helsinki.fi/facultyofscience/alumni/Alumni_evening2014.html.
The Department of Computer Science will host a demo/poster session at 16:00-17:00...
-
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, EspooThe 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...
-
The Crowd-Median Algorithm
Dr. Antti Ukkonen, HIIT
Abstract:The power of human computation is founded on the capabilities of humans to process qualitative information in a manner that is hard to reproduce with a computer. However, all machine learning algorithms rely on mathematical operations, such as sums, averages, least squares etc. that are less suitable for human computation.
This paper is an effort to combine these two aspects of data processing. We consider the...