Agenda
Date: August 5, 2019
Time: 1 pm - 5 pm
Room: Summit 11- Ground Level, Egan
Scroll to bottom for detailed agenda
Keynote Speakers
Dr. Jun (Luke) Huan, Head, Big Data Lab, Baidu Research
Dr. Jun (Luke) Huan directs the Baidu Big Data Lab. Before that he was the Charles and Mary Jane Spahr Professor in the Department of Electrical Engineering and Computer Science at the University of Kansas.
Dr. Huan works on Data Science, AI, Machine Learning and Data Mining. Dr. Huan's research is recognized internationally. He has published more than 130 peer-reviewed papers in leading conferences and journals and has graduated ten Ph.D. students. He was a recipient of the US National Science Foundation Faculty Early Career Development Award in 2009. His group won several best paper awards from leading international conferences. Dr. Huan service record includes Program Co-Chair of IEEE BIBM in 2015, IEEE Big Data 2019, and IEEE ICDM in 2020.
Next Generation Deep Neural Networks: Algorithms and Applications of Automated Deep Learning
Big Data, Deep Learning, and huge computing are shaping up AI and are transforming our society. In areas such as game playing, image classification, and speech recognition, AI algorithms may have already surpassed human experts’ capability. For cognition tasks such as Q&A and text generation, AI delivers capability that is comparable to human intelligence. We are also observing transformations AI produces to industry sectors such as social media, finance, and transportation.
At Baidu BDL we work on cutting-edge research that enables next-generation data-driven AI technology and service development. We focus on fundamental theoretic and computational principles that better harness huge amount of data. In this talk, I plan to provide a brief introduction to the “Open and Inclusive Initiative”at Baidu where we aim to promote equal access by all parties to advanced AI capabilities through significantly reducing the construction and management cost of AI models. I will talk about AutoDL, a suite of software and algorithms that we have been developing in order to use deep learning to design deep learning models. At the end of the talk, I will cover a few applications of automated deep learning in different vertical areas.
Professor Xia (Ben) Hu, Department of Computer Science & Engineering, Texas A&M University
Dr Hu is an Assistant Professor in Computer Science and Engineering at Texas A&M University starting from Fall 2015, and is a member of the Center for Remote Health Technologies and Systems and the Center for the Study of Digital Libraries. He is currently directing the DATA (Data Analytics at Texas A&M) Lab.
Auto-Keras: An Efficient Neural Architecture Search System
Paper Presentations
Augmented Data Science Towards Industrialization and Democratization of Data Science
- Huseyin Uzunalioglu, Jin Cao, Chitra Phadke, Gerald Lehmann, Ahmet Akyamac, Ran He, Jeongran Lee, and Maria Able - Bell Labs, Nokia
A Lightweight Algorithm to Uncover Deep Relationships in Data Tables
- Jin Cao - Bell Labs, Nokia
- Yibo Zhao - Indeed Inc.
- Linjun Zhang - University of Pennsylvania
- Jason Li - Academy for Information Technology
Practical Deep Neural Network Performance Prediction for Hyperparameter Optimization
- Yoshihiko Ozaki and Masaki Onishi - AI Research Center, AIST & GREE, INC
A Sound-based Fault Diagnosis Method using the Spectral Analysis and Convolutional Neural Network
- Caleb Vununu and Ki-Ryong Kwon - Pukyong National University
- Suk-Hwan Lee - Tongmyong University
Generalized Simple Word Embedding Model And Its Application To Text Classification With Automatic Tuning of Term Frequency and Inverse Document Frequency
- Ikenna Odinaka, Sunith Suresh, Cheuk Tse, Ryan Pilgrim, and Ya Xue - Infinia ML Inc.
Learning the Exploration for the Contextual Bandit
- Djallel Bouneffouf - IBM
- Emmanuelle Claeys - Strasbourg University
Trustable and Automated Machine Learning Running with Blockchain and Its Applications
- Tao Wang, Xinmin Wu, and Taiping He - SAS Institute
Automatic Historical Feature Generation through Tree-based Method in Ads Prediction
- Hongjian Wang, Qi Li, Lanbo Zhang, Yue Lu, Steven Yoo, and Srinivas Vadrevu - Twitter Inc.
- Zhenhui Li - The Pennsylvania State University
Agenda
1:00 Workshop Introduction
1:05 Keynote - Next Generation Deep Neural Networks: Algorithms and Applications of Automated Deep Learning – Jun (Luke) Huan
1:35 Augmented Data Science Towards Industrialization and Democratization of Data Science
1:55 A Lightweight Algorithm to Uncover Deep Relationships in Data Tables
2:10 Practical Deep Neural Network Performance Prediction for Hyperparameter Optimization
2:30 Coffee Break
3:00 Keynote - Auto-Keras: An Efficient Neural Architecture Search System – Xia (Ben) Hu
3:30 A Sound-based Fault Diagnosis Method using the Spectral Analysis and Convolutional Neural Network
3:50 Generalized Simple Word Embedding Model And Its Application To Text Classification With Automatic Tuning of Term Frequency and Inverse Document Frequency
4:05 Learning the Exploration for the Contextual Bandit
4:25 Trustable and Automated Machine Learning Running with Blockchain and Its Applications
4:40 Automatic Historical Feature Generation through Tree-based Method in Ads Prediction
4:55 Best Paper Award and Closing Remarks