- PowerPoint PPT Presentation

画風２ Neural Style Transfer [Gatys et al., 2015] 画風１ Image1 Image2’ Image2

Neural Style Transfer [Gatys et al., 2015]

Neural Style Transfer [Gatys et al., 2015]

Neural Style Transfer [Gatys et al., 2015]

Neural Style Transfer [Gatys et al., 2015] [Gatys et al., 2015]

‘Solving’ Games

神経科学研究者D.ハサビスらが率い るベンチャー(2014年、Googleが 500億円程で買収) Deep Q-Network [DeepMind,`16] Deep Mind

Deep Q-Network [DeepMind,`16] https://www.youtube.com/watch?v=iqXKQf2BOSE

3. Useful methods for Basic Science

1. Curse of Dimensionality 次元の呪い

Curse of Dimensionality & Lazy Learning Near Far Without learning, just recording the whole data. To find pattern/ classify new data, measure similarity (distance) between them and new data point. (eg. K-mean clustering) new sample

in D-dimension Volume of radius R ball Curse of Dimensionality & Lazy Learning V D ( R ) = R D × V D (1)

A ball whose radius is one Ratio of vol. of thin skin ( ) in radius1 ball Curse of Dimensionality & Lazy Learning V D ( R ) = R D × V D (1) 0 . 99 ≤ r ≤ 1 V D (1) − V D (0 . 99) = 1 − (0 . 99) D V D (1)

A ball whose radius is one 0.0297 = 3% Curse of Dimensionality & Lazy Learning . . . . . . 0.0956 = 10% 0.0199 = 2% 0.01 = 1% 10 3 2 1 Ratio of vol. of thin skin ( ) in radius1 ball 1 − (0 . 99) D D 0 . 99 ≤ r ≤ 1 V D (1) − V D (0 . 99) = 1 − (0 . 99) D V D (1)

Curse of Dimensionality & Lazy Learning 0.01 = 1% In higher dim, data is too sparse to extract a . . . . . . 0.0956 = 10% 0.0297 = 3% 0.0199 = 2% 10 Thin skin dominates the volume！！ Opposite to 3 2 1 Separated Maximally 0.9999 = 99.99..% 1000 intuition geometric structure even in ‘big data’ situation. 1 − (0 . 99) D D

Representation Learning & Dim. Compression Good information representation Clustering in lower dim. Anomaly detection

How to make Good Representation Good rep. 1. Unsupervised: Auto-Encoder 2. Supervised Good rep. x x x y

2. Search 探索

Reinforcement Learning (強化学習) Reward r Agent (program) （点数） Action a State s ’

（点数） Action value function Total reward under the policy π Q-Learning Reward r Agent (program) policy a ∼ π (a | s ) Action a State s ’ Q π ( s, a )

Deep Q-Learning Action value Optimization We know deep learning is powerful learner. MonteCarlo + Reinforcement Learning Q π ( s, a ) State s Q π ( s, a 1 ) Action a n Q π ( s, a 2 ) Q π ( s, a 3 )

3. Detection 検出

YOLO

4. Libraries

Language is Python basically Many Libraries for DL are Python-based. Coding is not the main purpose. Analyzing data and doing Machine Learning is (basically) our job.

Libraries for DL Libraries I have used are for instance + Theano etc. Which is the best? → Whichever you like. by Google by Googler by Facebook by Preferred Network

A criterion for usual user Libraries for DL http://www.timqian.com/star-history/#tensorflow/tensorflow&BVLC/caffe&caffe2/caffe2&Microsoft/CNTK&apache/ incubator-mxnet&torch/torch7&pytorch/pytorch&deeplearning4j/deeplearning4j&Theano/Theano&amzn/amazon- dsstne&chainer/chainer

Keras is my recommendation Libraries for DL https://towardsdatascience.com/battle-of-the-deep-learning- frameworks-part-i-cff0e3841750

5. Scientific Application - breast cancer -

New Model for segmentation [M.T & Murata, TBA]