TensorFlow是一個(gè)采用數(shù)據(jù)流圖（data flow graphs），用于數(shù)值計(jì)算的開源軟件庫(kù)。它靈活的架構(gòu)讓你可以在多種平臺(tái)上展開計(jì)算，例如臺(tái)式計(jì)算機(jī)中的一個(gè)或多個(gè)CPU（或GPU），服務(wù)器，移動(dòng)設(shè)備等等。TensorFlow 最初由Google大腦小組（隸屬于Google機(jī)器智能研究機(jī)構(gòu)）的研究員和工程師們開發(fā)出來(lái)，用于機(jī)器學(xué)習(xí)和深度神經(jīng)網(wǎng)絡(luò)方面的研究，但這個(gè)系統(tǒng)的通用性使其也可廣泛用于其他計(jì)算領(lǐng)域。本書講述TensorFlow應(yīng)用實(shí)例。
Preface
Chapter 1： GettingStarted with TensorFlow
Introduction
How TensorFIow Works
Declaring Tensors
Using Placeholders and Variables
Working with Matrices
Declaring Operations
Implementing Activation Functions
Working with Data Sources
Additional Resources
Chapter 2： The TensorFlow Way
Introduction
Operations in a Computational Graph
Layering Nested Operations
Working with Multiple Layers
Implementing Loss Functions
Implementing Back Propagation
Working with Batch and Stochastic Training
Combining Everything Together
Evaluating Models
Chapter 3： Linear Regression
Introduction
Using the Matrix Inverse Method
Implementing a Decomposition Method
Learning The TensorFIow Way of Linear Regression
Understanding Loss Functions in Linear Regression
Implementing Deming regression
Implementing Lasso and Ridge Regression
Implementing Elastic Net Regression
Implementing Logistic Regression
Chapter 4： Support Vector Machines
Introduction
Working with a Linear SVM
Reduction to Linear Regression
Working with Kernels in TensorFIow
Implementing a Non-Linear SVM
Implementing a Multi-Class SVM
Chapter 5： Nearest Neighbor Methods
Introduction
Working with Nearest Neighbors
Working with Text-Based Distances
Computing with Mixed Distance Functions
Using an Address Matching Example
Using Nearest Neighbors for Image Recognition
Chapter 6： Neural Networks
Introduction
Implementing Operational Gates
Working with Gates and Activation Functions
Implementing a One-Layer Neural Network
Implementing Different Layers
Using a Multilayer Neural Network
Improving the Predictions of Linear Models
Learning to Play Tic Tac Toe
Chapter 7： Natural Language Processing
Introduction
Working with bag of words
Implementing TF-IDF
Working with Skip-gram Embeddings
Working with CBOW Embeddings
Making Predictions with Word2vec
Using Doc2vec for Sentiment Analysis
Chapter 8： Convolutional Neural Networks
Introduction
Implementing a Simpler CNN
Implementing an Advanced CNN
Retraining Existing CNNs models
Applying Stylenet/NeuraI-Style
Implementing DeepDream
Chapter 9： Recurrent Neural Networks
Introduction
Implementing RNN for Spam Prediction
Implementing an LSTM Model
Stacking multiple LSTM Layers
Creating Sequence-to-Sequence Models
Training a Siamese Similarity Measure
Chapter 10： Taking TensorFIow to Production
Introduction
Implementing unit tests
Using Multiple Executors
Parallelizing TensorFIow
Taking TensorFIow to Production
Productionalizing TensorFIow - An Example
Chapter 11： More with TensorFIow
Introduction
Visualizing graphs in Tensorboard
There's more．．．
Working with a Genetic Algorithm
Clustering Using K-Means
Solving a System of ODEs
Index
書單推薦
