MachineLearning & DeepLearning

Optimizer

CartPole(OpenAI Gym) with DQN

Deep Q-Learning

Q-Learning(GridWorld)

GridWorld(OpenAI Gym)

OpenAI Gym

RL Algorithm

Bellman Equation

RL terms

Markov Decision Process, MDP

Reinforcement Learning, RL

GAN Applications

about GAN

Training DCGAN model(detail)

Training DCGAN model(WGAN-GP)

Wasserstein-1(WGAN)

DCGAN Generator & Discriminator

Transposed Convolution & Batch Normalization(DCGAN)

Training GAN model(detail)

Training GAN model

Data Preprocess

GAN Generator & Discriminator

Google Colaboratory

Generator / Discriminator & value function

Auto encoder & Generative model

save & load

Transformer model

Language modeling 3_evaluate

Language modeling 2_RNN model

Language modeling 1_preprocess

Haar Cascades

Sentiment Analysis(IMDb) 4_SimpleRNN

Sentiment Analysis(IMDb) 3_LSTM

Unknown Face Classifier

OpenCV

Sentiment Analysis(IMDb) 2_embedding

tf.py_function()

Sentiment Analysis(IMDb) 1_preprocess

LSTM

Output recurrent & Hidden layer recurrent

BPTT

Recurrent & Convolutional & Recursive

Back propagation

CNN backpropagation

RNN for Sequential data

Sequential data

CNN model for Celeb_a dataset

Celeb_a dataset(self making)

Celeb-A dataset preprocess(CNN)

CNN with Tensorflow(MNIST)

Loss Functions

Loss Function for Classified

Drop-out(Regulation)

Multi inputs & Color Channel

CNN, output size

Padding & SubSampling(pooling)

Discrete convolution

CNN Structure(details)

CNN Structure

kerase Model to Estimator

MNIST Classfier with Estimator

BoostedTreeRegressor(with Estimator)

Tensorflow Estimator(train & evaluate & predict)

Auto MPG

Tensorflow Estimator(feature_column)

XOR data

Users set Keras layers(build Layers)

Model class(build model) & train_step

Functional API(build model)

XOR classified(mlxtend)

Sequential API(build model)

Automatic differentiation & GradientTape

Tensorflow Variables

Function decoration

Tensorflow Computing Graph(v1 & v2)

activation functions

Activation function(ReLU)

Activation function(Hyperbolic tangent)

Activation function(Sigmoid & Softmax)

TensorBoard

Keras callback

MLP with iris datasets(keras.Sequential)

Linear Regression(with Keras.models)

TensorFlow neural modeling(with tf.keras)

tensor-datasets(load)

Celeb_a(self making)

tensor-datasets(builder)

image to Dataset

Build Dataset(preprocess, transform)

Using TensorFlow

TensorFlow

Models(Tricks) not covered in Books

NeuralNetMLP(details explain)

NeuralNetMLP

MNIST

Handwriting Classification(MNIST)

Forward Propagation

With MLP, function modeling

Spectral clustering(Graph-based clustering)

DBSCAN

Hierarchical clustering

FCM(Soft clustering)

Simple clustering data

elbow method & silhouette plot(evaluate method)

Clustering type

k-means & k-means++

SVM regressor(Kernel for Un-linear)

Bagging & Boosting

Decision & Random Forest Regressor(Un-Linear)

PolynomialFeatures Regression(Un-Linear)

Regulation

Linear Regression Model Evaluate

RANSAC Regressor(omit outlier)

Linear least squares

House data

Analyzing House data set

Linear Regression

Distribute Application(pythonAnywhere)

Movie Review Web Application

Web data Collect(WTForms)

Web Application(Flask)

Saved data(SQLite)

Save Trained estimator(with pickle)

Topic Modeling

out-of-core learning

Naver Movie Review Classfier

Text Classified with Logistic Regression

text Preprocessing

BoW model

IMDb text data

Sentiment analysis & Get Data

Gradient boosting(boosting)

Boosting(AdaBoost, Adaptive Boosting)

Bootstrap aggregating(Bagging)

Ensemble evaluate & tunning

Majority voting & Plurality voting

Ensemble learning

Multiple & imbalanced classified

ROC

REC & PRE

confusion Matrix

Nested cross-validation

Grid search CV

KFold vs StratifiedKFold

Algorithm Debuging(model evaluate)

Model evaluation

Wisconsin Dianostic Breast Cancer(WDBC)

Pipeline

Kernel Principle Component Analysis, KPCA(feature extraction) 2

Kernel Principle Component Analysis, KPCA(feature extraction) 1

Linear Discriminant Analysis, LDA(feature extraction)

plot_decision_regions

Principal Component Analysis, PCA(feature extraction)

Feature importances(with random forest)

Dimensionality(feature selection)

Regularization

Feature scaling

Wine data

Classify train data & test data

One-Hot Encoding

Categorical data

Data preprocessing(NaN)

parametric model & nonparametric model

K-Nearest Neighbor

Random forest(Decision Tree)

Iris data

Decision Tree

Kernel SVM

Soft margin classification

Support Vector Machine

Overfitting

Logistic regression

Scikit-learn

ADALINE(with SGD)

BGD & SGD & MSGD

ADALINE

Perceptron

Python tool for Machine Learning

Pipeline of Machine Learning

Basic Term

Machine Learning