1 2 3 > 
1 of 3
[course] Research Seminar Artificial Intelligence 2017
Posted: 24 January 2017 09:46 AM
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

Dear students,

this is the “official” forum topic for all matters related to the course “Research Seminar Artificial Intelligence”, offered Spring 2017. Please subscribe to this topic, so that you receive an e-mail when something is posted here. Use the “subscribe to this thread” link on the top right.

The course webpage is:
http://mediatechnology.leiden.edu/openaccess/course-artificial-intelligence

Looking forward to this year’s RSAI course!
Maarten

Profile
 
 
Posted: 24 January 2017 01:09 PM   [ # 1 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

Found this in my mailbox. Perhaps interesting for students: is about deep learning (artificial intelligence) and emotions. A presentation at LIACS.

Colleagues and students,

You are welcome to attend the masters thesis defense of Wadie Assal.

Title: Deep learning for Emotional Analysis

Date: Thursday, 26 January at 4pm
Room: 403

Supervisor: Dr. Michael S. Lew

Abstract:
The detection of emotions in textual data lets us discover more about the writer. The
automatic detection of emotions is useful in a large amount of applications. Furthermore,
new developments in deep learning have made it effective in more domains. This research
combines the two area’s and explores a deep learning method for emotional analysis. The
method is benchmarked against current methods using the ISEAR and a Twitter dataset.
The deep learning method shows an improvement of 2% for precision and 1% for recall
and F1 score compared to the current state of the art. Our research shows that the new
developments in deep learning have made it viable for emotional analysis research.

Profile
 
 
Posted: 07 February 2017 10:15 PM   [ # 2 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

Dear students,

to my great regret, and shame, I accidentally left my written notes about today’s lectures on my desk at LIACS. Since I live in Utrecht, going back to fetch them is no option…

As a result, I cannot complete my written evaluations of the three presentations today, even though I mentioned how I would do so. I will be in Leiden again on Thursday and then complete the textual evaluations.

[... edited ...]

All the best, and my sincere apologies,
Maarten

Profile
 
 
Posted: 09 February 2017 12:37 PM   [ # 3 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

Dear students,

I have completed my textual evaluations of the presentations of last Tuesday. They can be found inside the course vault.

Maarten

Profile
 
 
Posted: 14 February 2017 08:02 PM   [ # 4 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

The evaluations of today’s presentations are inside the course vault.

Profile
 
 
Posted: 14 February 2017 08:16 PM   [ # 5 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

The homework for next week (21/2) is:
- sections 2.1, 2.2, 2.3 and 2.5 of: AE Eiben and JE Smith (2003), Introduction to Evolutionary Computing, Springer.
- section 7.5 of: Alison Cawsey (1997), Genetic Algorithms, Section 7.5 of The Essence of Artificial Intelligence, Prentice Hall.

Should you need it, there is an explanation of symbols used by Eiben inside the course vault.

Profile
 
 
Posted: 21 February 2017 09:30 PM   [ # 6 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

I have placed my comments and evaluation of today’s presentation (evolutionary algorithms) inside the course vault.

Next week (28/2):
- homework reading is the same as this week
- bring a laptop with Processing 3 installed, if you want to play with evolutionary algorithms.

Profile
 
 
Posted: 21 February 2017 10:24 PM   [ # 7 ]
Newbie
Rank
Total Posts:  1
Joined  2016-09-06
Maarten Lamers - 21 February 2017 09:30 PM

I have placed my comments and evaluation of today’s presentation (evolutionary algorithms) inside the course vault.

Maarten it seems like the evaluation file is not updated yet.

Profile
 
 
Posted: 21 February 2017 10:31 PM   [ # 8 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

That is strange, because it is. Have you force-refreshed your browser? Perhaps you are looking at a cached version of the document.

Profile
 
 
Posted: 27 February 2017 10:52 PM   [ # 9 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

Dear students,

This is a gentle reminder, that if you want to play with an evolutionary algorithm in class tomorrow, then bring a laptop. I have written Processing code that you can play with, so make sure that Processing 3 is installed on the laptop.

In the RSAI course vault, I have placed a file “grafica.zip” with installation instructions. It is used by the Processing code that I will provide in class tomorrow.

See you tomorrow!
Maarten

Profile
 
 
Posted: 28 February 2017 08:33 PM   [ # 10 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

This is from my mailbox: a summerschool on deep learning neural networks in Bilbao, Spain.
Perhaps of interest to our students.

INTERNATIONAL SUMMER SCHOOL ON DEEP LEARNING

DeepLearn 2017

Bilbao, Spain

July 17-21, 2017

Organized by:
University of Deusto
Rovira i Virgili University

http://grammars.grlmc.com/DeepLearn2017/

************************************************************

—- Early registration deadline: March 24, 2017—-

********************************************************

SCOPE:

DeepLearn 2017 will be a research training event with a global scope aiming at updating participants about the most recent advances in the critical and fast developing area of deep learning. This is a branch of artificial intelligence covering a spectrum of current exciting machine learning research and industrial innovation that provides more efficient algorithms to deal with large-scale data in neuroscience, computer vision, speech recognition, language processing, drug discovery, biomedical informatics, recommender systems, learning theory, robotics, games, etc. Renowned academics and industry pioneers will lecture and share their views with the audience.

Most deep learning subareas will be displayed, and main challenges identified through 4 keynote lectures, 30 six-hour courses, and 1 round table, which will tackle the most active and promising topics. The organizers are convinced that outstanding speakers will attract the brightest and most motivated students. Interaction will be a main component of the event. An open session will give participants the opportunity to present their own work in progress in 5 minutes.

ADDRESSED TO:

In principle, graduate students, doctoral students and postdocs will be typical profiles of participants. However, there are no formal pre-requisites for attendance in terms of academic degrees. Since there will be a variety of levels, specific knowledge background may be assumed for some of the courses. DeepLearn 2017 is also appropriate for more senior academics and practitioners who want to keep themselves updated on recent developments and future trends. All will surely find it fruitful to listen and discuss with major researchers, industry leaders and innovators.

REGIME:

In addition to keynotes, 3-4 courses will run in parallel during the whole event. Participants will be able to freely choose the courses they wish to attend as well as to move from one to another.

VENUE:

DeepLearn 2017 will take place in Bilbao, the largest city in the Basque Country, famous for its gastronomy and the seat of the Guggenheim Museum. The venue will be:

DeustoTech, School of Engineering
University of Deusto
Avda. Universidades, 24
48014 Bilbao, Spain

KEYNOTE SPEAKERS: (to be completed)

Richard Socher (Salesforce), Tackling the Limits of Deep Learning

<... continued below ...>

Profile
 
 
Posted: 28 February 2017 08:34 PM   [ # 11 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

<... continued from above ...>

PROFESSORS AND COURSES:

Narendra Ahuja (University of Illinois, Urbana-Champaign), [introductory/intermediate] Basics of Deep Learning with Applications to Image Processing, Pattern Recognition and Computer Vision

Pierre Baldi (University of California, Irvine), [intermediate/advanced] Deep Learning: Theory and Applications to the Natural Sciences

Sven Behnke (University of Bonn), [intermediate] Visual Perception using Deep Convolutional Neural Networks

Mohammed Bennamoun (University of Western Australia), [introductory/intermediate] Deep Learning for Computer Vision

Hervé Bourlard (Idiap Research Institute), [intermediate/advanced] Deep Sequence Modeling: Historical Perspective and Current Trends

Thomas Breuel (NVIDIA Corporation), [intermediate] Segmentation, Processing, and Tracking, with Applications to Video, Gaming, VR, and Self-driving Cars

George Cybenko (Dartmouth College), [intermediate] Deep Learning of Behaviors

Rina Dechter (University of California, Irvine), [introductory] Algorithms for Reasoning with Probabilistic Graphical Models

Li Deng (Microsoft Research), tba

Jianfeng Gao (Microsoft Research), [introductory/intermediate] An Introduction to Deep Learning for Natural Language Processing

Michael Gschwind (IBM T.J. Watson Research Center), [introductory/intermediate] Deploying Deep Learning Applications at the Enterprise Scale

Yufei Huang (University of Texas, San Antonio), [intermediate/advanced] Deep Learning for Bioinformatics

Soo-Young Lee (Korea Advanced Institute of Science and Technology), [intermediate/advanced] Multi-modal Deep Learning for the Recognition of Human Emotions in the Real

Li Erran Li (Columbia University), [intermediate/advanced] Deep Learning Security: Adversarial Examples and Adversarial Training

Michael C. Mozer (University of Colorado, Boulder), [introductory/intermediate] Incorporating Domain Bias into Neural Networks

Roderick Murray-Smith (University of Glasgow), [intermediate] Applications of Deep Learning Models in Human-Computer Interaction Research

Hermann Ney (RWTH Aachen University), [intermediate/advanced] Speech Recognition and Machine Translation: From Statistical Decision Theory to Machine Learning and Deep Neural Networks

Jose C. Principe (University of Florida), [intermediate/advanced] Cognitive Architectures for Object Recognition in Video

Marc’Aurelio Ranzato (Facebook AI Research), [introductory/intermediate] Learning Representations for Vision, Speech and Text Processing Applications

Maximilian Riesenhuber (Georgetown University), [introductory/intermediate] Deep Learning in the Brain

Ruslan Salakhutdinov (Carnegie Mellon University), [intermediate/advanced] Foundations of Deep Learning and its Recent Advances

Alessandro Sperduti (University of Padua), [intermediate/advanced] Deep Learning for Sequences

Jimeng Sun (Georgia Institute of Technology), [introductory] Interpretable Deep Learning Models for Healthcare Applications

Julian Togelius (New York University), [intermediate] (Deep) Learning for (Video) Games

Joos Vandewalle (KU Leuven), [introductory/intermediate] Data Processing Methods, and Applications of Least Squares Support Vector Machines

Ying Nian Wu (University of California, Los Angeles), [introductory/intermediate] Deep Generative Models and Unsupervised Learning

Eric P. Xing (Carnegie Mellon University), [intermediate/advanced] Statistical Machine Learning Perspectives of Extending Deep Neural Networks: Kernels, Logics, Regularizers, Priors, and Distributed Algorithms

Georgios N. Yannakakis (University of Malta), [introductory/intermediate] Deep Learning for Games - But Not for Playing them

Scott Wen-tau Yih (Microsoft Research), [introductory/intermediate] Continuous Representations for Natural Language Understanding

Richard Zemel (University of Toronto), [introductory/intermediate] Learning to Understand Images and Text

OPEN SESSION:

An open session will collect 5-minute voluntary presentations of work in progress by participants. They should submit a half-page abstract containing title, authors, and summary of the research to david.silva409 (at) yahoo.com by July 9, 2017.

ORGANIZING COMMITTEE:

José Gaviria
Carlos Martín (co-chair)
Manuel Jesús Parra
Iker Pastor
Borja Sanz (co-chair)
David Silva

REGISTRATION:

It has to be done at

http://grammars.grlmc.com/DeepLearn2017/registration.php

The selection of up to 8 courses requested in the registration template is only tentative and non-binding. For the sake of organization, it will be helpful to have an approximation of the respective demand for each course.

Since the capacity of the venue is limited, registration requests will be processed on a first come first served basis. The registration period will be closed and the on-line registration facility disabled when the capacity of the venue will be complete. It is much recommended to register prior to the event.

FEES:

Fees comprise access to all courses and lunches. There are several early registration deadlines. Fees depend on the registration deadline.

ACCOMMODATION:

A suggestion for accommodation is available on the website.

CERTIFICATE:

Participants will be delivered a certificate of attendance including the number of hours of lectures.

QUESTIONS AND FURTHER INFORMATION:

david.silva409 (at) yahoo.com

Profile
 
 
Posted: 07 March 2017 07:52 PM   [ # 12 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

My evaluations and comments for today’s presentations can be found inside the course vault.

Profile
 
 
Posted: 07 March 2017 11:04 PM   [ # 13 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

I posted a call-for-help from a dutch popular science television program. They need help to build a simple robot.

Interested? See http://mediatechnology.leiden.edu/forum/viewthread/1897/.

Profile
 
 
Posted: 13 March 2017 09:07 AM   [ # 14 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

Some results of homework tests were posted inside the course vault.

Kind regards,
Maarten

Profile
 
 
Posted: 13 March 2017 11:04 AM   [ # 15 ]
Administrator
RankRankRankRank
Total Posts:  779
Joined  2007-05-02

The results of last week’s homework test (DNA) were also added to the course vault.

See you tomorrow!
Maarten

Profile
 
 
   
 1 2 3 > 
1 of 3