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: |
| Summary: |
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 learning applications. Deep Learning with Applications Using Python covers topics such as chatbots, natural language processing, and face and object recognition. The goal is to equip you with the concepts, techniques, and algorithm implementations needed to create programs capable of performing deep learning. This book covers intermediate and advanced levels of deep learning, including convolutional neural networks, recurrent neural networks, and multilayer perceptrons. It also discusses popular APIs such as IBM Watson, Microsoft Azure, and scikit-learn. You will: Work with various deep learning frameworks such as TensorFlow, Keras, and scikit-learn. Build face recognition and face detection capabilities Create speech-to-text and text-to-speech functionality Make chatbots using deep learning. |
|---|---|
| Item Description: |
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. 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 learning applications. Deep Learning with Applications Using Python covers topics such as chatbots, natural language processing, and face and object recognition. The goal is to equip you with the concepts, techniques, and algorithm implementations needed to create programs capable of performing deep learning. This book covers intermediate and advanced levels of deep learning, including convolutional neural networks, recurrent neural networks, and multilayer perceptrons. It also discusses popular APIs such as IBM Watson, Microsoft Azure, and scikit-learn. You will: Work with various deep learning frameworks such as TensorFlow, Keras, and scikit-learn. Build face recognition and face detection capabilities Create speech-to-text and text-to-speech functionality Make chatbots using deep learning. |
| Physical Description: |
1 online resource. |
| ISBN: |
9781484235164 1484235169 9781484235171 1484235177 9781484240519 1484240510 |