※ 3월 27일 일요일 오혜연 교수님 강의(주황색 바탕으로 표시)에 실습이 예정되어 있으니, 관심 있는 분들은 노트북을 지참해주시기 바랍니다.
Machine Learning Tutorial 2016 Program | ||||
IEIE's Distinguished Lecturer Series for Machine Learning | ||||
날짜 | 시간 | 주제 | 강사 | |
2016-03-24 목요일 |
09:00~11:00 | 등 록 | ||
11:00~11:10 | 환 영 인 사 | |||
11:10~12:00 | Deep Learning for Natural Language Processing |
1. Introduction 2. Word embedding and Compositionality 3. RNNs and LSTMs for modeling sequential data 4. RNNs and LSTMs for NLP applications: Sequential labeling, neural machine translation, QA(question answering), etc. 5. Recursive neural networks for parsing sequential data 6. Memory-based LSTMs: Neural turning machine, etc 7. Discussion and Conclusion |
나승훈 교수 전북대학교 |
|
12:00~13:00 | Lunch | |||
13:00~13:50 | Deep Learning for Natural Language Processing | |||
13:50~14:00 | Break | |||
14:00~14:50 | Deep Learning for Natural Language Processing | |||
14:50~15:10 | Break | |||
15:10~16:30 | Computational Genomics | 1. Introduction to computational genomics 2. Gene prediction (based on HMM) and motif discovery (based on EM algorithm) 3. Transcriptome (microarray, RNA-seq, gene expression analysis) 4. Integrative approaches to genome-scale data sets 5. Applications in cancer genomics |
이현주 교수 GIST |
|
16:30~16:50 | Break | |||
16:50~18:10 | Computational Genomics | |||
2016-03-25 금요일 |
09:00~10:20 | Bayesian Nonparametrics for Machine Learning | 1. Introduction 2. Dirichlet process prior and its applications 3. Variants of Dirichlet process prior 4. Beta process prior and its applications |
김용대 교수 서울대학교 |
10:20~10:40 | Break | |||
10:40~12:00 | Bayesian Nonparametrics for Machine Learning | |||
12:00~13:00 | Lunch | |||
13:00~14:20 | Using Neural Networks for Modelling and Representing Natural Languages | 1. Introduction 2. Basic machine learning applied to NLP 3. Introduction to neural networks 4. Distributed representations of words 5. Neural network based language models 6. Future research 7. Resources |
Tomas Mikolov |
|
14:20~14:40 | Break | |||
14:40~16:00 | Using Neural Networks for Modelling and Representing Natural Languages | |||
16:00~16:20 | Break | |||
16:20~17:40 | Machine Learning for Biomedical Informatics | 1. Introduction 2. Current research problems 3. Non-parametric Bayesian models for joint inference of multiple related tasks 4. Sparse structured regression models for knowledge-guided prediction 5. Summary |
손경아 교수 아주대학교 |
|
17:40~18:00 | Break | |||
18:00~19:20 | Machine Learning for Biomedical Informatics | |||
2016-03-26 토요일 |
09:00~10:20 | Deep Learning in Vision | 1. Introduction to deep learning 2. Convolutional neural networks 3. Image classification 4. Understanding and visualizing concolutional neural networks 5. Image captioning |
김준모 교수 KAIST |
10:20~10:40 | Break | |||
10:40~12:00 | Deep Learning in Vision | |||
12:00~13:00 | Lunch | |||
13:00~14:20 | SNS Analysis and Recommendation System | 1. Sentiment Analysis 2. Sentiment Analysis Tools 3. Rumor Detection Problem in OSN 4. Rumor Detection Analysis 5. Recommendation System 6. Crowd Sourcing System |
정교민 교수 서울대학교 |
|
14:20~14:40 | Break | |||
14:40~16:00 | SNS Analysis and Recommendation System | |||
16:00~16:20 | Break | |||
16:20~17:40 | Large-scale Optimization for Deep Learning | 1. Introduction & Background 2. First-order methods for convex optimization 3. Second-order methods for convex optimization 4. Methods for non-convex optimization 5. Applications in machine learning |
신진우 교수 KAIST |
|
17:40~18:00 | Break | |||
18:00~19:20 | Large-scale Optimization for Deep Learning | |||
2016-03-27 일요일 |
10:00~11:20 | Programming Exercises for Word2vec and Latent Dirichlet Allocation |
1. Introduction 2. Elice programming platform 3. Word2vec 4. Latent Dirichlet Allocation 5. Program |
오혜연 교수 KAIST |
11:20~11:40 | Break | |||
11:40~13:00 | Programming Exercises for Word2vec and Latent Dirichlet Allocation |
|||
13:00~14:00 | Lunch | |||
14:00~15:20 | Then, Now and the Future of Deep Learning | 1. Foundation of Machine learning 2. Start of deep learning 3. Graphical models and rise of deep 4. Recent research output 5. Future of Deep Learning 6. Summary & references |
유창동 교수 KAIST |
|
15:20~15:40 | Break | |||
15:20~15:40 | Then, Now and the Future of Deep Learning | |||
※ 강의 내용에 대한 저작권 관계로, 내용의 전체 또는 일부를 휴대폰 및 카메라 등을 이용하여 촬영하실 수 없습니다.
이에 양해를 부탁드립니다.