Some papers

Some papers that might be useful:

Conference Dates and Information

Here are some information of some conferences:

  • NIPS
    • Date: Dec 4 – 9 2017
    • Location: Long Beach Convention Centre, USA
    • Submission Deadlines: May 19 2017
  • AAAI
    • Date:  Feb 2 – 7 2017
    • Location: New Orleans, Lousiana, USA
    • Submission Deadlines: TBC
      • July 1 – September 8, 2017: Authors register on the AAAI web site
      • September 8, 2017: Electronic abstracts due at 11:59 PM UTC-10 (midnight Hawaii)
      • September 11, 2017: Electronic papers due at 11:59 PM UTC-10 (midnight Hawaii)
      • October 16–19, 2017: Author feedback about initial reviews
      • November 9, 2017: Notification of acceptance or rejection
      • November 21, 2017: Camera-ready copy due at 5:00 PM PDT (California time)
    • Date: Aug 19 – 25 2017
    • Location: Melbourne, Australia
    • Submission Deadlines: Feb 19 2017
  • ICML
    • Date: Aug 6 – 11 2017
    • Location: Sydney, Australia
    • Submission Deadlines: Feb 24 2017
  • ICLR
    • Date: 24 – 26 April 2017
    • Location: Palais des Congrès Neptune, Toulon, France
    • Submission Deadline: 5:00pm Eastern Daylight Time (EDT), November 4th 5th, 2016

If you have any conference that you would like to suggest, please leave a reply in the comments section below. Thanks!

SUTD, NTU join SMU in deploying supercomputer for AI research

The NVIDIA DGX-1deep learning supercomputer is winning over universities in Singapore. Singapore University of Technology and Design (SUTD) and Nanyang Technological University (NTU) have deployed the powerful machine for their research projects on artificial intelligence (AI).

SUTD will use the DGX-1 at the SUTD Brain Lab to further research into machine reasoning and distributed learning. Under a memorandum of understanding signed earlier this month, NVIDIA and SUTD will also set up the NVIDIA-SUTD AI Lab to leverage the power of GPU-accelerated neural networks for researching new theories and algorithms for AI. The agreement also provides for internship opportunities to selected students of the lab.

“Computational power is a game changer for AI research, especially in the areas of big data analytics, robotics, machine reasoning and distributed intelligence. The DGX-1 will enable us to perform significantly more experiments in the same period of time, quickening the discovery of new theories and the design of new applications,” said Professors Shaowei Lin and Georgios Piliouras, Engineering Systems and Design, SUTD.


Read more…

Deep Probability Flow

Brain Lab Seminar

Date. 11 Nov 2016 (Fri)

Time. 10:00am-11:30am

Room. System Modeling Lab (1.615)

Speaker. Shaowei Lin (SUTD)

Title. Deep Probability Flow

Slides. dpf-slides.pdf

Abstract. I will be speaking on our recent work on Deep Probability Flow. This is an algorithm that we hope will enable us to train much larger neural networks. Current methods in deep learning are hindered by back-propagation which computes the maximum likelihood estimate. Such algorithms may be distributed using data-parallelism where the training set is partitioned between several machines for gradient computation. The holy grail, however, is to achieve model-parallelism where different parts of the neural network are trained on separate machines. By using a different statistical objective function, we were able to derive learning rules where the weight updates only depend locally on the associated neurons. In the talk, I will discuss how variational inference is used to derive these rules. This is work in progress.