Past Meetup

KDD.SG Tutorial: Image Classification Using Convolutional Neural Networks

This Meetup is past

48 people went

Singapore Management University

School of Economics and Social Sciences · Singapore

How to find us

SOE/SOSS Seminar Rm B1-1 (Rm B127), Basement 1 of School of Economics/School of Social Sciences

Location image of event venue

Details

You are invited to the upcoming KDD.SG Tutorial organized by SIGKDD Singapore, DataScience SG & SMU SIS.

Title: Image Classification Using Convolutional Neural Networks with Applications to Facial Expression Recognition and Visual Sentiment Analysis

Abstract: With the prevalence of smartphones, everyone is now a casual photographer, leading to the abundance of images on the social media. One useful machine learning task is to categorize an image into one of several classes. In this tutorial, we will cover how to build such a classifier using a deep learning technique called Convolutional Neural Networks or CNN. While the task is generally applicable, this tutorial will focus on two applications relevant to user sentiments and preferences. One application is facial emotion recognition, classifying whether a photo indicates emotion such as happiness and sadness. Another application is visual sentiment analysis, classifying whether an image found in a review signifies high or low rating.

Speakers: Hady W. Lauw & Quoc-Tuan Truong

Hady W. Lauw is an Assistant Professor of Information Systems at Singapore Management University (SMU), as well as NRF Fellow of the Singapore National Research Foundation. Formerly, he served as postdoctoral researcher at Microsoft Research in Silicon Valley, as well as scientist at A*STAR's Institute for Infocomm Research. He received his PhD from Nanyang Technological University on A*STAR Graduate Scholarship. At SMU, he leads the Preferred.AI research project, whose research activities span data mining and machine learning, focusing on preference analytics and recommender systems. More information may be found at http://www.hadylauw.com.

Quoc-Tuan Truong is a PhD candidate in School of Information Systems, Singapore Management University (SMU). His research interests include machine learning, text mining and social network data analytics, with a focus on mining user preferences from review text and images. Quoc-Tuan received his Bachelor degree from University of Engineering and Technology, Vietnam National University, Hanoi. He was one of the ten Vietnamese recipients of the prestigious Honda Y-E-S (Young Engineer and Scientist's) Award in 2016. More information may be found at http://www.qttruong.info.

Venue: SOE/SOSS Seminar Rm B1-1 (Rm B127), Basement 1, School of Economics/School of Social Sciences, Singapore Management University

Campus Map: https://www.smu.edu.sg/campus-life/visiting-smu/campus-map

Prerequisite: You should be proficient in programming; familiarity with Python is a plus. Prior knowledge of neural networks would be immensely helpful.

Preparation: Bring your own laptop. There is guest wifi connectivity with limited speeds on site. You are also welcome to bring your own internet connectivity. We will inform confirmed registrants of the data and packages to be downloaded a week beforehand.

Follow our activities on https://kdd.sg/news/.