This is the official code repository for Machine Learning with TensorFlow.
Get started with machine learning using TensorFlow, Google's latest and greatest machine learning library.
Ch 2️⃣ - 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
- Listing 2-4:
types.py - Listing 5-6:
main.py - Listing 7:
interactive_session.py - Listing 8:
logging.py - Listing 9:
spikes.py - Listing 10:
saving_vars.py - Listing 11:
loading_vars.py - Listing 12-15:
moving_avg.py
Ch 3️⃣ - Regression
- Concept 1: Linear regression
- Concept 2: Polynomial regression
- Concept 3: Regularization
- Listing 1-2:
simple_model.py - Listing 3:
polynomial_model.py - Listing 4-5:
regularization.py - Listing 6:
data_reader.py
Ch 4️⃣ - Classification
- Concept 1: Linear regression for classification
- Concept 2: Logistic regression
- Concept 3: 2D Logistic regression
- Concept 4: Softmax classification
- Listing 1-3:
linear_1d.py - Listing 4:
logistic_1d.py - Listing 5:
logistic_2d.py - Listing 6-10:
softmax.py
Ch 5️⃣ - Clustering
- Concept 1: Clustering
- Concept 2: Segmentation
- Concept 3: Self-organizing map
- Listing 1-4:
audio_clustering.py - Listing 5-6:
audio_segmentation.py - Listing 7-12:
som.py
Ch 6️⃣ - Hidden markov models
- Concept 1: Forward algorithm
- Concept 2: Viterbi decode
- Listing 1-6:
forward.py - Listing 7-11:
hmm.py
Ch 7️⃣ - Autoencoders
- Concept 1: Autoencoder
- Concept 2: Applying an autoencoder to images
- Concept 3: Denoising autoencoder
Ch 8️⃣ - Reinforcement learning
- Concept 1: Reinforcement learning
- Listing 1-10:
rl.py
Ch 9️⃣ - Convolutional Neural Networks
- Concept 1: Using CIFAR-10 dataset
- Concept 2: Convolutions
- Concept 3: Convolutional neural network
Ch 🔟 - Recurrent Neural Network
- Concept 1: Loading timeseries data
- Concept 2: Recurrent neural networks
- Concept 3: Applying RNN to real-world data for timeseries prediction