AI Meets

PHYSICS-물리학-物理學 & ASTRONOMY-천문학-天文學

session 1-1 : Astronomy [11/07 Thu]

[Checking Session Timetable]

Speaker: Shin, Min-Su (신민수, msshin@kasi.ac.kr, home)

  • 한국천문연구원 광학천문본부 선임연구원

Title: Application of Machine Learning for Big Data Analysis in Astronomy (천문학 자료분석에서의 기계학습의 활용)

Abstract:

천문학 관측 자료의 분석의 경우, 관측 환경의 변화 등에 의해서 야기된 관측 부정확성이나 편향성, 그리고 비균질적인 자료 획득 등의 특징적인 문제를 가지고 있다. 이러한 천문 관측 자료의 특성을 고려해서, 천문학자들은 천체나 천체 현상의 검출, 분류, 특성의 추론 등의 문제를 접하게 된다. 이러한 문제들은 관측 자료의 급속한 증가와 함께 더욱 심각해지는데, 기계학습의 활용을 통하여 정량적인 검출, 분류, 추론의 문제들을 해결해 가고자 노력 중이다. 이번 발표에서는 이러한 문제들을 clustering, anomaly detection, classification, regression, recommendation 문제의 시각에서 기계학습을 활용한 사례들을 소개하고, 최근 시도되고 있는 ensemble learning, multi-task learning 등의 활용도 간랸히 제시하고자 한다. 더불어서 천체와 그 현상에 대한 천체물리적 이해를 위한 기계학습의 활용 방향에 대해서 의견을 제시한다.

Speaker: Kim, Ji-hoon (김지훈, mornkr@snu.ac.kr, home)

Ji-hoon Kim is an Assistant Professor of Physics and Astronomy at Seoul National University studying computational cosmology and astrophysics. His research focuses on galaxy and supermassive black hole (SMBH) formation using high-resolution numerical simulation codes. He also has been coordinating a large inter-institutional cosmological simulations comparison project called AGORA. He got his Bachelor’s Degree in Physics from Seoul National University in 2002, and his Ph.D. Degree in Physics from Stanford University in 2011. Among his previous experiences, he was formerly a research associate and a NASA Einstein Fellow in the Department of Physics and Kavli Institute for Particle Astrophysics and Cosmology (KIPAC) at Stanford University.

Title: Machine Learning In Astrophysics: Estimating Galactic Baryonic Properties from Their Dark Matter

Abstract:

As astrophysics and cosmology deal with inherently "cosmological" sizes of data, machine learning is being rapidly adopted in a variety of astrophysical applications. In this talk, I will introduce a pipeline that estimates baryonic (visible) properties of a galaxy based purely on dark matter (DM; invisible) properties in large-scale DM-only simulations. It is shown that our pipeline promptly generates a galaxy catalogue from a DM halo catalogue using a machine trained on smaller-scale, fully-hydrodynamic, high-resolution simulations. An extremely randomized tree algorithm is used together with multiple novel improvements we developed such as a refined error function and two-stage learning. Our model may become a promising method to transplant the baryon physics of galaxy-scale hydrodynamic calculations onto a larger-volume DM-only run.

session 1-2 : Physics [11/07 Thu]

[Checking Session Timetable]

Speaker: Jung, Sunghoon (정성훈, sunghoonj@snu.ac.kr, home)

Prof. Sunghoon Jung is an Assistant Professor of Physics and Astronomy Department. He was previously a research fellow at SLAC at Stanford Univ, Korea Institute for Advanced Study, Enrico Fermi Institute at the Univ of Chicago, and received his Ph.D degree at the Univ of Michigan. His research is on theoretical particle physics, primarily on probing and understanding the fundamental Nature beyond the Standard Model.

Title: What can we learn with ML in particle physics, and how?

Abstract:

ML has a deep potential to extend our ability to understand Nature, beyond common knowledge. As the very first steps to realize it, we use ML to seek for answers to one of the not-well-solved problems in particle physics. Our focus is not only to improve the solution, but to develop ways to figure out what the network has learned.

Speaker: Sven Krippendorf (sven.krippendorf@physik.uni-muenchen.de , home)

Title: Searching for Axions and new concepts in fundamental physics with Machine Learning

Abstract:

In this talk I will review how ultralight axion-like particles can be constrained using X-ray observations of bright localised sources (AGNs, Quasars) in and behind galaxy clusters. To find axion-like particles in these settings corresponds to finding their characteristic pattern (quasi-sinusoidal oscillations) in noisy data. Using ML-techniques we are able to improve the search sensitivity for these particles and are able to set stronger bounds compared to previous methods. In the second part of the talk I shall highlight avenues where ML can be used to accelerate our understanding of fundamental physics (string theory) and potentially vice versa.

Speaker: Kim, Hyung Do (김형도, hdkim@phya.snu.ac.kr, home)

Title: Learning QCD Jet Flavors in search for Invisible Higgs Decays

Speaker: Yoo, Hwidong (유휘동, hdyoo@yonsei.ac.kr, home)

Title: Recent developments of Deep Learning in experimental high energy physics

Abstract: 최근들어 딥러닝 기술은 기초 과학 분야에도 광범위하게 연구되고 있다. 이를 통해 얻어진 지식 및 기술이 차세대 연구 시스템 및 환경을 변화시키고 결과를 획기적으로 향상시키기 위해 다양하게 적용될 것으로 기대되고 있다. 현재 고에너지 물리 실험분야에서 활발하게 연구되고 있는 딥러닝 관련 연구에 대해 소개하고 향후 기대 효과에 대해 논의 한다.

Overview of Research

session 2 : Physics [11/08 fri]

[Checking Session Timetable]

Title: Architecture of Neuromorphic Hardware with Embedded Learning

Speaker: Jo, Junghyo (조정효, jojunghyo@snu.ac.kr, home)

"I am a theoretical physicist working on biological systems. I have a great interest in real and artificial neural networks and their learning mechanisms. Recently, I am working on interpreting the internal processes of machine learning by using information theory. Furthermore, I study biological rhythms, Bayesian modeling, causality inference, data classification, and so on. "

Title: Information in unsupervised learning

Abstract:

Information bottleneck theory explains that neural networks maximally compress unnecessary information in input data, and transfer sufficient information to output. Unlike the supervised learning, the information flow of unsupervised learning has not been explored much. In this talk, I introduce the information extraction of unsupervised learning by using a representative generative model, deep belief networks. Then, I show that the unsupervised learning maximally extracts relevant information given a fixed information compression for its internal representations. This relation between the information bottleneck theory and our theory reminds the duality between the rate distortion theory and channel capacity in information theory.

[국문] Information bottleneck 이론은 지도학습과정에서 일어나는 신경망의 정보흐름을 정량화하는 이론이다. 이 이론에 따르면 신경망의 학습은 입력과 출력을 연결시켜주는 최소한의 정보만 전달하고 불필요한 정보는 최대한 압축하는 과정임을 보여주었다. 우리는 입력과 출력이 정의되는 지도학습과 달리 비지도학습과정에서 일어나는 신경망의 정보흐름에 대해 연구했다. 이 발표에서는 대표적인 생성모형인 딥빌리프네트워크를 통해서 비지도학습과정의 정보추출에 대해 소개하려고 한다. 우리는 딥빌리프네트워크가 주어진 해상도의 내적표현을 가질 때, 내적표현의 빈도수에서 최대한의 정보를 추출한다는 사실을 발견하였다. Information bottleneck 이론과 우리 이론의 관계는 마치 정보이론의 rate distortion theory와 channel capacity 사이의 쌍대성을 떠올리게 한다.

Speaker: Yu, Jaejun (유재준, jyu@snu.ac.kr, home)

Profile

  • Physics professor at Seoul National University
  • Expert in theoretical and computational condensed matter physics
  • Research area focused on electronic, magnetic, and other physical properties of novel transition metal oxides and related materials

Position

  • Dean, Faculty of Liberal Education, Seoul National University
  • Director, Center for Theoretical Physics, Seoul National University
  • Professor, Department of Physics and Astronomy, Seoul National University

Title: Exploration of energy surfaces and conformation of molecules and solids by utilizing a machine-learning technique

Abstract:

Predicting the physical properties of novel materials requires an accurate description of atomic interactions as provided by first-principles quantum mechanical calculations. Efficient and practical calculation tools have been developed along with the progress of density functional theory (DFT). Still, however, the computational complexity associated with the quantum mechanical treatment limits their applications to systems of a few hundreds of atoms at most. Here, we present an application of the Gaussian process regression (GPR) scheme to the global optimization, conformation space annealing, and pathway optimization methods. We demonstrate that the use of GPR-based pathway optimization technique, e.g., action-derived molecular dynamics (ADMD) method, can be useful in enhancing the computational performance. We will discuss possible future applications of the GPR-based machine learning technique for the exploration of energy surfaces and conformation of molecules and solids.

Speaker: Bang, Jeongho (방정호, jbang@kias.re.kr )

Title: Quantum Algorithms and Quantum Machine Learning

Abstract:

정보처리/컴퓨팅에의 초소형화/고집적화 그리고 무어의 법칙 등은 정보이론과 양자물리학의 융합 및 발전이 필연임을 반영한다. 양자물리학에 기반한 컴퓨팅에의 속도향상 등의 연구는 그 가능성을 증명하는 수준을 넘어, 양자기술의 실현이라는 현실적 목표앞에 와 있다. 이제, 양자컴퓨팅/통신 등의 용어는 학계를 넘어 이미 우리 일상에 와 있다. 이에, 본 강연에서는 기본적인 양자원리, 즉 양자중첩 및 얽힘 등을 이해하고, 알려진 유명한 양자알고리즘들과 더불어 어떻게 양자머신러닝에의 속도향상이 가능한지 간략히 살펴보고자 한다. 아울러, 최근 연구 동향 및 이슈 등 또한 간략히 소개하고자 한다.