Machine Learning with TensorFlow
[Summary] - Developing on Jupyter notebook for interactive computing
[Chapter 1] - Mathematical Foundations
- Concept 1: Linear Algebra
- Concept 2: Calculus
- Concept 3: Probability
- Concept 4: Formulation (Learning, Optimization)
- Concept 5: Topics (Dimensionality Reduction, Regularization)
[Chapter 2] - TensorFlow Basics
- Concept 1: Defining tensors
- Concept 2: Evaluating ops
- Concept 3: Interactive session
- Concept 4: Session loggings
- Concept 5: Variables
- Concept 6: Saving variables
- Concept 7: Loading variables
- Concept 8: TensorBoard
[Chapter 3] - Regression
- Concept 1: Linear regression
- Concept 2: Polynomial regression
- Concept 3: Regularization
[Chapter 4] - Classification
- Concept 1: Linear regression for classification
- Concept 2: Logistic regression
- Concept 3: 2D Logistic regression
- Concept 4: Softmax classification
[Chapter 5] - Clustering
- Concept 1: Clustering
- Concept 2: Segmentation
- Concept 3: Self-organizing map
[Chapter 6] - Hidden markov models
- Concept 1: Forward algorithm
- Concept 2: Viterbi decode
[Chapter 7] - Autoencoders
- Concept 1: Autoencoder
- Concept 2: Applying an autoencoder to images
- Concept 3: Denoising autoencoder
[Chapter 8] - Reinforcement learning
- Concept 1: Reinforcement learning
[Chapter 9] - Convolutional Neural Networks
- Concept 1: Using CIFAR-10 dataset
- Concept 2: Convolutions
- Concept 3: Convolutional neural network
[Chapter 10] - Recurrent Neural Network
- Concept 1: Loading timeseries data
- Concept 2: Recurrent neural networks
- Concept 3: Applying RNN to real-world data for timeseries prediction
[Chapter 11] - Seq2Seq Model
- Concept 1: Multi-cell RNN
- Concept 2: Embedding lookup
- Concept 3: Seq2seq model
[Chapter 12] - Ranking
- Concept 1: RankNet
- Concept 2: Image embedding
- Concept 3: Image ranking
[Chapter 13] - Natural Language Processing
- Concept 1: Vector Space Model
- Concept 2: Vector Representation of Words
- Concept 3: Word2Vector
- Concept 4: Applying Recurrent Neural Networks with NLTK framework
[Chapter 14] - Unsupervised Learning
- Concept 1: Boltzmann Distribution
- Concept 2: Markov Chain Monte Carlo Methods for Sampling
- Concept 3: PCA and ZCA Whitening
- Concept 4: Recommendation - Collaborative Filtering Using Restricted Boltzmann Machines