トップページ  »   Nov. 18, 2016, 10:30~11:30【FRIIS Seminar】Professor Tomoki Toda (Nagoya University) Statistical Voice Conversion and Its Application to Augmented Speech Production

  • Nagoya Instituteof Technology

Nov. 18, 2016, 10:30~11:30【FRIIS Seminar】Professor Tomoki Toda (Nagoya University) Statistical Voice Conversion and Its Application to Augmented Speech Production

Dr. Keiichi Tokuda is going to host a research seminar in #110 room (Center for Social Contribution and Collaboration) at Bldg.4, NITech. No reservation required.

This seminar will be counted as Tokubetsu Enshu (Details are shown at the bottom of the flyer).

Oct. 26, 2016, 14:00-16:00 【FRIIS Seminar】 Prof. Ilangko Balasingham(Oslo University Hospital, Norway)

Wang Group in FRIIS is going to host a research seminar at room 0221, 2nd floor, Bldg 2, at NITech. No reservation required. Please find the detail of the presentation below.

 

Frontier Seminar 20160715 Eng (Prof Tamaki)

Oct. 17, 2016, 13:30-14:30 【FRIIS Seminar】 Asst. Prof. Susel Fernandez(Telematic Services Engineering research group (GIST), University of Alcala, Spain)

Ito Group in FRIIS is going to host a research seminar at Main Hall on 1st floor in Bldg. 4. No reservation required. Please find the detail of the presentation below.

 

Frontier Seminar 20160715 Eng (Prof Tamaki)

Oct 6, 2016, 10:30 – 12:00 【FRIIS Seminar】 Professor Chengqi Zhang [University of Technology Sydney (UTS), Australia]

2016.09.26 FRIIS The International Collaborative Symposium for Informatics

===============================================

The International Collaborative Symposium for Informatics

  - Towards Global and Joint Collaboration –

(国際連携情報学シンポジウム)

===============================================

 

We are pleased to announce the International Conference of Information Science.

This symposium is designed for our upcoming International Joint PhD Program

between NITech and University of Wollongong, Australia.

We are looking forward to welcoming you at this meeting.

More detail:http://www.itolab.nitech.ac.jp/ICSI/

 

Sponsor: NITech Frontier Research Institute for Information Science

Date: September 26th, 2016 (mon), 10:00 – 18:00

Location: Hall, 1st floor, Building 4, Nagoya Institute of Technology, Gokiso, Nagoya

 

■主催: 名古屋工業大学 情報科学フロンティア研究院

■日時: 9月26日(月) 10:00 〜 18:00

■会場: 名古屋工業大学 4号館1階 ホール

■参加費: 無料

 * セミナーは同時通訳を予定しております。

■ Registrationhttp://goo.gl/Idu0GK

 

■懇親会会場: The Strings Hotel, Nagoya(1F シャトー・シャンパーニュ)

■参加費: 無料

* 送迎バスあり

 

[ Symposium ]

10:00-10:10 Opening by Vice President/Executive Director Professor Ichi Takumi

 

Session 1: UoW-NIT Joint Phd Degree

10:10-10:40 Professor Minjie Zhang, University of Wollongong, Australia

"Load Forecasting in a Smart Grid through Customer Behavior Learning"

10:40-11:10 Professor Takayuki Ito, Nagoya Institute of Technology, Japan

11:10-11:40 Professor Chengqi Zhang, University of Technology, Sydney, Australia

"Research Management at UTS research centres"

 

Session 2: Recent International Progress on Informatics

13:30-14:00 Professor Jun Yan, University of Wollongong, Australia

"QoS-aware Service Level Agreement Management with the Agent Technology"

14:00-14:30 Professor Quan Bai, Auckland University of Technology, New Zealand

"Influence propagation modelling for complex social networks"

14:30-15:00 Professor Shohei Kato, Nagoya Institute of Technology, Japan

 

Session 3: Recent Progress in Crowd Decision Support Systems

15:30-16:00 Professor Katsuhide Fujita, Tokyo University of

Agriculture and Technology, Japan

"Agent-based Negotiation for Crowd Decision Support Systems"

16:00-16:30 Professor Shun Shiramatsu, Nagoya Institute of Technology, Japan

"Corpus Analysis of Web-based Discussion towards Autonomous Facilitator Agents"

16:30-17:00 Professor Tokuro Matsuo, Advanced Institute of Industrial

Technology, Japan

"Social Informatics Impacts: Synergies Between Social Science and

Information Technology"

 

17:00 Closing

 

[ Dinner party ](参加費無料)

17:45- バス送迎 : 名工大4号館 〜 ストリングスホテル

 

18:30-20:30 Dinner party

Strings Hotel (1F Chateau Champagne) ストリングスホテル(1F シャトー・シャンパーニュ)

 

20:45- バス送迎 : ストリングスホテル 〜 名工大

21:00 シャトルバス : ストリングスホテル 〜 名古屋駅(太閤口)

 

お問い合わせ先:

名古屋工業大学 国際連携情報学シンポジウム 事務局

e-mail: hayakawa.tomomichi [at] nitech.ac.jp

Aug 31, 2016, 15:00 – 16:30 【FRIIS Seminar】 Professor Kwei-Jay Lin(University of California, Irvine, USA)

Ito Group in FRIIS is going to host a research seminar at Main Hall on 1st floor in Bldg. 4. No reservation required. Please find the detail of the presentation below.

 

Frontier Seminar 20160715 Eng (Prof Tamaki)

Aug 22, 2016, 13:00 – 14:30 【FRIIS Seminar】 Jean-Luc Gaudiot(Professor, Department of Electrical Engineering and Computer Science, University of California, Irvine, USA)

FRIIS is pleased to organize a research seminar at Main Hall on 1st floor in Bldg. 4. Please find the detail of the presentation below.

 

Frontier Seminar 20160715 Eng (Prof Tamaki)

August 03, 2016 【13:30 – 14:30 FRIIS Seminars 】 Professor. Joseph Salmon(TELECOM Paris Tech, France)

Room 611B, 6th floor in Bldg.2, NITech

Skeaker :Joseph Salmon(Professor, TELECOM Paris Tech, France)

Organizer: Prof. Ichiro Takeuchi ( Frontier Research Institute for Information Science, NITech)

 

Title:

Efficient Smoothed Concomitant Lasso Estimation for High Dimensional Regression

 

Abstract:

In high dimensional settings, sparse structures are crucial for efficiency, both in term of memory, computation and performance. It is customary to consider l1 penalties to enforce sparsity in such scenarios.

For efficiency, they rely on tuning a parameter trading data fitting versus sparsity. For the Lasso theory to hold this tuning parameter should be proportional to the noise level, yet the latter is often unknown in practice. A possible remedy is to jointly optimize over the regression parameter as well as over the noise level. This has been considered under several names in the literature: Scaled-Lasso, Square-root Lasso, Concomitant Lasso estimation for instance, and could be of interest for confidence sets or uncertainty quantification.

In this work, after illustrating numerical difficulties for the Concomitant Lasso formulation, we propose a modification we coined Smoothed Concomitant Lasso, aimed at increasing numerical stability.  We propose an efficient and accurate solver leading to a computational cost no more expansive than the one for the Lasso. We leverage on standard ingredients behind the success of fast Lasso solvers: a coordinate descent algorithm, combined with safe screening rules to achieve speed efficiency, by eliminating early irrelevant features.

 

This is a joint work with Eugene Ndiaye, Olivier Fercoq, Alexandre Gramfort and Vincent Leclère

August 03, 2016 【14:45-15:45 FRIIS Seminars 】 Dr. Mathieu Blondel (NTTコンピュータサイエンス研究所)

Room 611B, 6th floor in Bldg.2, NITech

Skeaker : Dr. Mathieu Blondel (NTTコンピュータサイエンス研究所)

Organizer: Prof. Ichiro Takeuchi ( Frontier Research Institute for Information Science, NITech)

 

Title

Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms

 

Abstract

Polynomial networks and factorization machines are two recently-proposed models that can efficiently use feature interactions in classification and regression tasks. In this paper, we revisit both models from a unified perspective.

Based on this new view, we study the properties of both models and propose new efficient training algorithms. Key to our approach is to cast parameter learning as a low-rank symmetric tensor estimation problem, which we solve by multi-convex optimization. We demonstrate our approach on regression and recommender system tasks.

 

Page top