Seminar về lĩnh vực Khoa học dữ liệu

5/28/2020 10:05 AM

Trường Đại học Phenikaa Trân trọng kính mời các đồng nghiệp, các bạn sinh viên, học viên cao học, và nghiên cứu sinh tới tham dự buổi seminar khoa học tại Viện Nghiên cứu Tiên tiến Phenikaa, Trường Đại học Phenikaa.

✅ Tiêu đề: Learning from infinitely sequential data streams
✅ Người trình bày: PGS.TS. Thân Quang Khoát

Trưởng phòng, Phòng Nghiên cứu Khoa học Dữ liệu, Viện Công nghệ Thông tin và Truyền Thông, Đại học Bách khoa Hà Nội

✅ Thời gian: 16:00, Thứ Sáu, ngày 29/05/2020.

✅ Địa điểm: Phòng 601, nhà A1, Trường Đại học Phenikaa
Yên Nghĩa, Hà Đông, Hà Nội

✅ Tóm tắt:
How to build a machine that can continuously learn from observations in its life and make accurate inference/prediction? This is one of the central questions in Artificial Intelligence. Many challenges are present, such as the difficulty of learning from streaming data which come sequentially and infinitely, the dynamic nature of the environments, noisy and sparse data, the intractability of inference, etc. This tutorial will discuss why the Bayesian approach provides a natural and efficient answer, and provide a summarized picture about variational inference for streaming data. We will start from some basics about probabilistic models, and then the variational Bayes method for inference. Next, we will discuss how the Bayesian approach deals with an infinite sequence of data. Some challenges such as catastrophic forgetting, concept drifts, and stability-plasticity dilemma will be discussed.

✅ Giới thiệu về speaker: Khoat Than is currently Director of Data Science Laboratory, and associate professor at Hanoi University of Science and Technology. He is also a visiting scientist at VinAI Research. He received Ph.D. (2013) from Japan Advanced Institute of Science and Technology. He joins the Program Committees of various leading conferences, including ICML, NeurIPS, IJCAI, ICLR,… His research has been being supported by various funding sources, including ONRG (US), AFOSR (US), ARL (US), NAFOSTED (VN), VINIF (VN). Some recent interests include machine learning, representation learning, deep generative models, continual learning.