ホーム > 学部後期課程版 > 経済学部 > Deep Learning and Related Methods for Large Dataset Information Processing

Home > Under Graduate (3rd and 4th years) > Economics > Deep Learning and Related Methods for Large Dataset Information Processing(Graduate Level)

2017年度 経済学部 0704255 Deep Learning and Related Methods for Large Dataset Information Processing Fabinger Michal
横断型

Deep learning in artificial neural networks is a collection of statistical methods that benefit from large datasets and parallel computing. Recently it led to remarkable progress in many domains of research. This course provides an introduction to the subject, including the latest research. The structure of the course is chosen with the aim to be useful to students with very different academic backgrounds. Topics include: Optimization: backpropagation, stochastic gradient descent and its accelerated versions. Supervised and semi-supervised machine learning: under-fitting and over-fitting, regularization, cross-validation, data augmentation. Neural network architecture: activation functions and their properties, layer patterns. Training neural networks: data preprocessing, weight initialization, gradient flow, batch normalization, regularization, practical aspects of GPU computing and distributed training. Hyper-parameter optimization, model ensembles, model compression. Transfer learning and fine-tuning. Spatial data modeling: convolutional networks and their recent versions, visualizing their internal data representations, susceptibility to adversarial examples. Sequence data modeling: recurrent networks, LSTMs, GRUs, and their convolutional alternatives, attention. Recursive data modeling: recursive neural networks. Natural language processing: word embedding and its visualization, neural machine translation, speech recognition and synthesis. Unsupervised machine learning: autoencoders, graphical models, adversarial networks and their Nash equilibria. Deep reinforcement learning. Use of neural networks for designing and training other neural networks: neural architecture search, meta-learning. Hybrid computing combining advantages of neural networks and conventional computers. Use of deep learning for causal inference and counterfactual predictions. Privacy and ethical issues related to artificial intelligence. Selected applications: econometric estimation of causal effects, solutions to game-theoretic models, economic time-series modeling, sentiment analysis, patient health outcome prediction, low-cost disease diagnosis, overcoming sensory loss with deep-learning technologies. The course will include a first introduction to Python and to deep learning frameworks TensorFlow and Keras (and to some extent Theano, Torch, and Caffe). The precise selection of topics for the course will be adjusted based on the students' interests.

2017 Economics 0704255 Deep Learning and Related Methods for Large Dataset Information Processing(Graduate Level) Fabinger Michal
University-wide

共通科目コード Common Course Code FEC-CE5801L3
開講学期 Semester A1
開講時限 Period
火曜2限 金曜2限 Tue 2nd Fri 2nd
単位数 Credits 2
学年 Academic Year B3 B4 B5 B6
他学部聴講 Open to other faculties 可 YES
USTEP生聴講 Permitted to USTEP Students 可 YES
教室 Classroom
国際学術総合研究棟 514演習室
授業使用言語 Language in Lecture 英語 English
講義題目 Title Deep Learning and Related Methods for Large Dataset Information Processing
授業の方法 Teaching Methods Class instruction and individual research projects.
成績評価方法 Method of Evaluation Evaluation criteria will include homework, class presentations, class participation and/or research projects.
教科書 Required Textbook
Ian Goodfellow, Yoshua Bengio, and Aaron Courville: "Deep Learning", The MIT Press, 2016
学部横断型教育プログラム
University-wide Undergraduate Education Program
国際総合日本学教育プログラム Global Japan Studies Program

Pagetop

マイリストを使うと、自身が興味を持つ科目をチェックできます。 チェックした科目は随時マイリストを開くことにより確認できます。 マイリストを使うためにはログインをしてください。 You can store courses which you are interested in into My List. You can view them at any time by opening My List page. Please sign in in order to use mylist.

Googleアカウントを使ってログイン
Sign in with Google account
Facebookアカウントを使ってログイン
Sign in with Facebook account
Twitterアカウントを使ってログイン
Sign in with Twitter account