Lightning Research Introduction Seminars Series 4 (Fall 2015)

12 October 2015 (Monday)

Seminar: Lightning Research Introduction Seminar (4)

Date: 12 October 2015 (Monday)

Time: 4-5pm (light refreshment will be arranged outside the LTF after the seminar)

Venue: LTF (near lifts 25/26), HKUST

Host: Prof. S.C. CHEUNG (Associate Head of Dept.)

Speakers: CSE Faculty Members

  1. Shing-Chi CHEUNG
  2. Sunil ARYA
  3. James KWOK
  4. Albert CHUNG
  5. Raymond WONG
  6. Wilfred NG
  7. Bo LI
  8. Dit-Yan YEUNG
  9. Ting-Chuen PONG
  10. Pedro SANDER

Schedule:

Time Speaker Talk Title Abstract Slides Video
4:00-4:05pm Prof. Shing-Chi CHEUNG Finding Deep Bugs in Software Abstract Slides Playback
4:05-4:10pm Dr. Sunil ARYA Approximate Nearest Neighbor Searching Abstract Slides Playback
4:10-4:15pm Prof. James KWOK Learning from Data Abstract Slides Playback
4:15-4:20pm Prof. Albert CHUNG Medical Image Analysis N/A N/A Playback
4:20-4:25pm Dr. Raymond WONG Big Data Analytics on Big Spatial Database Abstract Slides Playback
4:25-4:30pm Dr. Wilfred NG Searching Microblogs - Big Topics on Big Data Abstract Slides Playback
4:30-4:35pm Prof. Bo LI The Internet-based Computing and Datacenter Networks Abstract Slides Playback
4:35-4:40pm Prof. Dit-Yan YEUNG Sequence-to-Sequence Learning Abstract Slides Playback
4:40-4:45pm Prof. Ting-Chuen PONG Digital Technologies for E-learning Abstract Slides Playback
4:45-4:50pm Dr. Pedro SANDER Exciting Rendering and Imaging Problems in Computer Graphics Abstract Slides Playback
4:50-5:00pm Q&A Session Playback

Full Video Playback

Abstracts

Talk 1

Title: "Finding Deep Bugs in Software"

Speaker: Prof. Shing-Chi CHEUNG

Abstract:

Finding bugs in software is known to be difficult even for experienced 
software developers. Deep bugs are those that have not been identified by 
developers or exposed by existing test cases. We may even not be able to 
have good oracles to detect them. Finding these bugs automatically is a 
non-trivial research challenge. In the lightening talk, I will review this 
research challenge and our latest attempts on open source systems, Android 
apps and spreadsheets.

Talk 2

Title: "Approximate Nearest Neighbor Searching"

Speaker: Dr. Sunil ARYA

Abstract:

I will briefly talk about my research on the approximate nearest neighbor 
problem.

Talk 3

Title: "Learning from Data"

Speaker: Prof. James KWOK

Abstract:

I will outline my past and current machine learning research.

Talk 5

Title: "Big Data Analytics on Big Spatial Database"

Speaker: Dr. Raymond WONG

Abstract:

Nowadays, location-based services (LBSs), which refer to those services 
that are based on location (or spatial) data, are broadly used in our daily 
life. In this talk, we will talk about the recent development of LBSs. Some 
examples are "Search-nearby", "Spatial Crowdsourcing", "Trace Tracking" and 
"Shortest Distance.

Talk 6

Title: "Searching Microblogs - Big Topics on Big Data"

Speaker: Dr. Wilfred NG

Abstract:

In recent years, we have seen the emergence of the concept of big data. We 
also see that microblogs is everywhere - a very typical and important kind 
of big data. Microblogs are short length, unstructured and have diverse 
topics. The data are generated in high volume by users in the scale of 
second. In the seminar, I would highlight some research issues of 
microblogs our group has been working on.

Talk 7

Title: "The Internet-based Computing and Datacenter Networks"

Speaker: Prof. Bo LI

Abstract:

This talk presents a highlight of my current research on the Internet-based 
computing and datacenter networking.

Talk 8

Title: "Sequence-to-Sequence Learning"

Speaker: Prof. Dit-Yan YEUNG

Abstract:

While machine learning tasks such as object recognition and spam filtering 
typically do not represent both the input and output as sequences, a number 
of real-world applications require learning the association between input 
and output sequences. This setting is referred to as sequence-to-sequence 
learning. In this flash of lightning, I will highlight sequence-to-sequence 
learning as a common theme underlying some of my ongoing research projects.

Talk 9

Title: "Digital Technologies for E-learning"

Speaker: Prof. Ting-Chuen PONG

Abstract:

Recent advances in e-learning technologies have led to transformative 
changes in the landscapes of education from K-12 to higher education to 
professional and continuing education. The proliferation of Massive Open 
Online Courses (or MOOCs) has generated optimism about realizing the dream 
of providing education for all while delivering personalized learning at 
scale. In this talk, I will discuss research opportunities in some 
challenging areas including learning analytics from structured and 
unstructured data, knowledge mining from e-learning content, and multimedia 
and VR tools for e-learning.

Talk 10

Title: "Exciting Rendering and Imaging Problems in Computer Graphics"

Speaker: Dr. Pedro SANDER

Abstract:

In this brief 5-minute talk, I will highlight some interesting recent 
results and potential research directions for 3D rendering and Imaging 
research problems.