[PYTHON] Machine Learning Professional Series Round Reading Session Slide Summary

This page summarizes the presentation slides of the Machine Learning Professional Series Round Reading Session. I will update it from time to time.

** Machine Learning Professional Series Round Reading Session ** Conpass URL: http://ml-professional.connpass.com

• 1st book: "Deep learning"
• 2nd book: "Anomaly detection and change detection"

# 1 "Deep Learning"

http://bookclub.kodansha.co.jp/product?isbn=9784061529021 Errata

chapter 1: Introduction @a_macabee

http://www.slideshare.net/beeEaMa/chapter-01-49404580

Chapter 2: Forward Propagation Neural Network @a_macabee

http://www.slideshare.net/beeEaMa/chapter-02-49488411

Chapter 3: Stochastic Gradient Descent Method @ hagino3000

Chapter 4: Backpropagation method @t_tetsuma

Chapter 5: Self-encoder @at_grandpa

http://www.slideshare.net/at_grandpa/chapter5-50042838 http://at-grandpa.hatenablog.jp/entry/2015/07/01/190226

Chapter 6: Folding Neural Network @ kenmatsu4

http://www.slideshare.net/matsukenbook/ss-50545587
http://www.slideshare.net/matsukenbook/deep-learning-chap6-convolutional-neural-net

• Demonstration using Python

Chapter 7: Recursive Neural Network @g_votte

http://www.slideshare.net/shotarosano5/chapter7-50542830

Chapter 8: Boltzmann Machine @ bigsea_t

http://www.slideshare.net/taikaitakeda/8-boltzmann-machine

LT Frame 1: Implementation of multi-layer restricted Boltzmann machine @ mabonki0725

http://www1.m.jcnnet.jp/mabonki/doc/LT_deepL_RBM_R150805.pdf

LT frame 2: I tried using Chainer @ kenmatsu4

http://www.slideshare.net/matsukenbook/lt-chainer

• Demonstration using Python

LT frame 3: @t_furukawa

LT frame 4: DQN @oshokawa

https://speakerdeck.com/oshokawa/dqn

# 2 "Anomaly detection and change detection"

http://ide-research.net/book/support.html#kodansha Corrigendum

chapter 1 & 2: Basic concept of anomaly detection / change detection, anomaly detection by the T ^ 2 method of hoteling @at_grandpa

http://www.slideshare.net/at_grandpa/5-chapter-1-2 http://at-grandpa.hatenablog.jp/entry/2015/08/21/220430

chapter 3: Anomaly detection by the simple Bayes method @a_macabee

http://www.slideshare.net/beeEaMa/mlprofessional

chapter 4: Anomaly detection by neighbor method @ kenmatsu4

http://www.slideshare.net/matsukenbook/4-53640134

• Demonstration using Python

chapter 5: Sequential update type anomaly detection by mixture distribution model @t_tetsuma

http://www.slideshare.net/tetsumatada/5-54726998

chapter 6: Anomaly detection by support vector data description method @g_votte

http://www.slideshare.net/shotarosano5/in-54205735

chapter 7: Direction data anomaly detection @nakano_tomofumi

http://www.slideshare.net/nakanotomofumi/7-54766192

chapter 8: Anomaly detection by Gaussian process regression @ healthy55five

Coming soon... :smile:

chapter 9: Change point detection by subspace method @ hagino3000

http://www.slideshare.net/hagino_3000/9-55242143

chapter 10: Anomaly detection by sparse structure learning @natsu_xxxxxxxx

http://www.slideshare.net/natsup/anomaly-detection-char10

chapter 11: Anomaly detection by density ratio estimation @oshokawa

https://speakerdeck.com/oshokawa/mi-du-bi-tui-ding-niyoruyi-chang-jian-zhi

chapter 12: Change detection by density ratio estimation ErikaFujita

http://www.slideshare.net/ErikaFujita/ss-55958414