Deep learning with applications using Python chatbots and face, object, and speech recognition with TensorFlow and Keras /
Build deep learning applications, such as computer vision, speech recognition, and chatbots, using frameworks such as TensorFlow and Keras. This book helps you to ramp up your practical know-how in a short period of time and focuses you on the domain, models, and algorithms required for deep learnin...
| Main Author: | Manaswi, Navin Kumar. |
|---|---|
| Other Authors: | SpringerLink (Online Service) |
| Format: | eBook |
| Language: | English |
| Published: |
[Berkeley, CA] :
Apress,
2018.
|
| Physical Description: |
1 online resource. |
| Subjects: |
Table of Contents:
- Intro; Table of Contents; Foreword; About the Author; About the Technical Reviewer; Chapter 1: Basics of TensorFlow; Tensors; Computational Graph and Session; Constants, Placeholders, and Variables; Placeholders; Creating Tensors; Fixed Tensors; Sequence Tensors; Random Tensors; Working on Matrices; Activation Functions; Tangent Hyperbolic and Sigmoid; ReLU and ELU; ReLU6; Loss Functions; Loss Function Examples; Common Loss Functions; Optimizers; Loss Function Examples; Common Optimizers; Metrics; Metrics Examples; Common Metrics; Chapter 2: Understanding and Working with Keras.
- Major Steps to Deep Learning ModelsLoad Data; Preprocess the Data; Define the Model; Compile the Model; Fit the Model; Evaluate Model; Prediction; Save and Reload the Model; Optional: Summarize the Model; Additional Steps to Improve Keras Models; Keras with TensorFlow; Chapter 3: Multilayer Perceptron; Artificial Neural Network; Single-Layer Perceptron; Multilayer Perceptron; Logistic Regression Model; Chapter 4: Regression to MLP in TensorFlow; TensorFlow Steps to Build Models; Linear Regression in TensorFlow; Logistic Regression Model; Multilayer Perceptron in TensorFlow.
- Chapter 5: Regression to MLP in KerasLog-Linear Model; Keras Neural Network for Linear Regression; Logistic Regression; scikit-learn for Logistic Regression; Keras Neural Network for Logistic Regression; Fashion MNIST Data: Logistic Regression in Keras; MLPs on the Iris Data; Write the Code; Build a Sequential Keras Model; MLPs on MNIST Data (Digit Classification); MLPs on Randomly Generated Data; Chapter 6: Convolutional Neural Networks; Different Layers in a CNN; CNN Architectures; Chapter 7: CNN in TensorFlow; Why TensorFlow for CNN Models?
- TensorFlow Code for Building an Image Classifier for MNIST DataUsing a High-Level API for Building CNN Models; Chapter 8: CNN in Keras; Building an Image Classifier for MNIST Data in Keras; Define the Network Structure; Define the Model Architecture; Building an Image Classifier with CIFAR-10 Data; Define the Network Structure; Define the Model Architecture; Pretrained Models; Chapter 9: RNN and LSTM; The Concept of RNNs; The Concept of LSTM; Modes of LSTM; Sequence Prediction; Sequence Numeric Prediction; Sequence Classification; Sequence Generation; Sequence-to-Sequence Prediction.
- Time-Series Forecasting with the LSTM ModelChapter 10: Speech to Text and Vice Versa; Speech-to-Text Conversion; Speech as Data; Speech Features: Mapping Speech to a Matrix; Spectrograms: Mapping Speech to an Image; Building a Classifier for Speech Recognition Through MFCC Features; Building a Classifier for Speech Recognition Through a Spectrogram; Open Source Approaches; Examples Using Each API; Using PocketSphinx; Using the Google Speech API; Using the Google Cloud Speech API; Using the Wit.ai API; Using the Houndify API; Using the IBM Speech to Text API.