DeepLearning
╠═1 Tensorflow
║░╠═1 install by docker
║░╚═2 Example
║░░░╠═1 1st : Multi Variable Linear Regression with manually
║░░░╠═2 2nd : Multi Variable Linear Regression with Matrix
║░░░╠═3 3rd : Multi Variable Linear Regression with file
║░░░╠═4 4th : Multi Variable Linear Regression with fileQueue
║░░░╚═5 5th : Multi Variable Linear Regression with Hattrick KP
╠═2 Reinforcement by Python and Keras
║░╠═1 Install
║░║░╠═1 Install PyCharm
║░║░╠═2 Create VirEnv
║░║░╠═3 Avoid AVX-Error
║░║░╚═4 Check Version of Packages
║░╚═2 Book
║░░░╠═1 ch02 MDP and BE
║░░░║░╠═1 Agent
║░░░║░╠═2 State
║░░░║░╠═3 Actions
║░░░║░╠═4 Reward
║░░░║░╠═5 Time
║░░░║░╠═6 Policy
║░░░║░╠═7 Reward in MDP
║░░░║░╠═8 Flow in MDP
║░░░║░╠═9 State Transition Probability
║░░░║░╠═10 Discount Factor
║░░░║░╠═11 Return
║░░░║░╠═12 ValueFunction
║░░░║░╚═13 QFunction
║░░░╠═2 ch03 Grid World and Dynamic Programming
║░░░║░╠═1 Policy Iteration
║░░░║░╚═2 Value Iteration
║░░░╠═3 ch04 Grid World and Reinforcement Learning
║░░░║░╠═1 SARSA
║░░░║░╚═2 QLearning
║░░░╚═4 ch05 Grid World and RL + DL
║░░░░░╠═1 DeepSARSA
║░░░░░╚═2 Polish Gradient
╠═3 Python DeepLearning Keras with Blocks
║░╠═1 Install
║░║░╠═1 Install by docker
║░║░╚═2 Check Version of Packages
║░╚═2 Book
║░░░╠═1 part 02 DeepLearning Concept
║░░░║░╠═1 ch1 Train Validation DataSet
║░░░║░╠═2 ch2 BatchSize and Epochs
║░░░║░╠═3 ch3 history by fit
║░░░║░╠═4 ch3 history by tensorboard
║░░░║░╠═5 ch3 history bu user defined callbacks
║░░░║░╠═6 ch4 OverFitting
║░░░║░╠═7 ch4 EarlyStopping
║░░░║░╠═8 ch4 EarlyStopping with patience=10
║░░░║░╠═9 ch5 Evaluation for Model of Classfication
║░░░║░╠═10 ch5 Evaluation for Model of Search or Detection
║░░░║░╠═11 ch5 Evaluation for Model of Split
║░░░║░╚═12 ch6 Model view, save, load
║░░░╚═2 part 03 Layer Concept
║░░░░░╠═1 ch01 Multi Perceptron Layer
║░░░░░╠═2 ch02 Multi Perceptron Layer for Pigma Indians Diabetes
║░░░░░╠═3 ch03 Convolution Layer
║░░░░░╠═4 ch03 MaxPooling Layer
║░░░░░╠═5 ch03 Flatten Layer
║░░░░░╠═6 ch03 Conv2D MaxPooling2D Flatten Example
║░░░░░╠═7 ch03 icrawler on Google Image
║░░░░░╚═8 ch03 Duplicate Data by ImageDataGenerator
╚═4 DeepLearning from Scratch : Code, typo
░░╠═2 ch2. Perceptron : Definition, example for AND, NAND, OR, XOR
░░╠═3 ch3 Artificial_Neural_Network
░░║░╠═1 From Perceptron to ANN
░░║░╠═2 Activate Function : Step, Sigmoid, Hyperbolic Tangent, Linear
░░║░╠═3 Calculation of multidimensional arrays
░░║░║░╠═1 array shape ndim
░░║░║░╠═2 matrix dot product
░░║░║░╚═3 ANN dot product
░░║░╠═4 3rd Layer ANN
░░║░║░╠═1 notaion of ANN weight
░░║░║░╚═2 implement signal of each layer
░░║░╠═5 Design output layer of ANN
░░║░╚═3.6 손글씨 숫자 인식
░░║░░░╠═3.6.1 MNIST dataset
░░║░░░╠═3.6.2 신경망의 추론 처리
░░║░░░╚═3.6.3 배치 처리
░░╚═4 신경망 학습
░░░░╠═4.2 손실 함수
░░░░║░╠═1 평균 제곱 오차
░░░░║░╠═2 교차 엔트로피 오차
░░░░║░╠═3 미니 배치 평균 제곱 오차
░░░░║░╚═4 CEE with mini batch
░░░░╠═4.3 수치 미분 Numerical Differentiation
░░░░║░╠═4.3.1 (해석적) 미분 (Analytic) Differentiation
░░░░║░╚═4.3.2 [수치 미분의 예](04_DeepLearning_from_Scratch/4_신경망_학습/3_Numerical_differentiation/4.3.2 수치 미분의 예.ipynb)
░░░░╚═4.4 Slope
░░░░░░╠═1 Gradient descent
░░░░░░╚═2 Slope of ANN
( ║ ╠ ═ ╚ ░)