nach oben

2018 | Buch

Kapitel lesen Erstes Kapitel lesen

Deep Learning with Applications Using Python

Chatbots and Face, Object, and Speech Recognition With TensorFlow and Keras

verfasst von: Navin Kumar Manaswi

Verlag: Apress

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

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.
What You Will Learn 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

Who This Book Is For
Data scientists and developers who want to adapt and build deep learning applications.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Basics of TensorFlow

Abstract

This chapter covers the basics of TensorFlow, the deep learning framework. Deep learning does a wonderful job in pattern recognition, especially in the context of images, sound, speech, language, and time-series data. With the help of deep learning, you can classify, predict, cluster, and extract features. Fortunately, in November 2015, Google released TensorFlow, which has been used in most of Google’s products such as Google Search, spam detection, speech recognition, Google Assistant, Google Now, and Google Photos. Explaining the basic components of TensorFlow is the aim of this chapter.

Navin Kumar Manaswi

Chapter 2. Understanding and Working with Keras

Abstract

Keras is a compact and easy-to-learn high-level Python library for deep learning that can run on top of TensorFlow (or Theano or CNTK). It allows developers to focus on the main concepts of deep learning, such as creating layers for neural networks, while taking care of the nitty-gritty details of tensors, their shapes, and their mathematical details. TensorFlow (or Theano or CNTK) has to be the back end for Keras. You can use Keras for deep learning applications without interacting with the relatively complex TensorFlow (or Theano or CNTK). There are two major kinds of framework: the sequential API and the functional API. The sequential API is based on the idea of a sequence of layers; this is the most common usage of Keras and the easiest part of Keras. The sequential model can be considered as a linear stack of layers.

Navin Kumar Manaswi

Chapter 3. Multilayer Perceptron

Abstract

Before you start learning about multilayered perceptron, you need to get a big-picture view of artificial neural networks. That’s what I’ll start with in this chapter.

Navin Kumar Manaswi

Chapter 4. Regression to MLP in TensorFlow

Abstract

People have been using regression and classifiers for a long time. Now it is time to switch to the topic of neural networks. A multilayered perceptron (MLP) is a simple neural network model where you can add one or more hidden layers between the input and output layers.

Navin Kumar Manaswi

Chapter 5. Regression to MLP in Keras

Abstract

You have been working on regression while solving machine learning applications. Linear regression and nonlinear regression are used to predict numeric targets, while logistic regression and other classifiers are used to predict non-numeric target variables. In this chapter, I will discuss the evolution of multilayer perceptrons.

Navin Kumar Manaswi

Chapter 6. Convolutional Neural Networks

Abstract

A convolutional neural network (CNN) is a deep, feed-forward artificial neural network in which the neural network preserves the hierarchical structure by learning internal feature representations and generalizing the features in the common image problems such as object recognition and other computer vision problems. It is not restricted to images; it also receives state-of-the-art results in natural language processing problems and speech recognition.

Navin Kumar Manaswi

Chapter 7. CNN in TensorFlow

Abstract

This chapter will demonstrate how to use TensorFlow to build a CNN model. A CNN model can help you build an image classifier that can predict and classify the images. In general, you create some layers in the model architecture with initial values of weight and bias. You will learn how to code in TensorFlow for building CNN models. Then you tune weight and bias with the help of a training data set. There is another approach that involves using a pretrained model such as InceptionV3 to classify the images. You can use this transfer learning approach where you add some layers on top of layers of pretrained models. Here, you will learn how to build an object detector.

Navin Kumar Manaswi

Chapter 8. CNN in Keras

Abstract

This chapter will demonstrate how to use Keras to build CNN models. A CNN model can help you build an image classifier that can predict and classify the images. In general, you create some layers in the model architecture with initial values of weight and bias. Then you tune the weight and bias variables with the help of a training data set. You will learn how to code in Keras in this context. There is another approach that involves using pretrained models such as InceptionV3 and ResNet50 that can classify the images.

Navin Kumar Manaswi

Chapter 9. RNN and LSTM

Abstract

This chapter will discuss the concepts of recurrent neural networks (RNNs) and their modified version, long short-term memory (LSTM). LSTM is mainly used for sequence prediction. You will learn about the varieties of sequence prediction and then learn how to do time-series forecasting with the help of the LSTM model.

Navin Kumar Manaswi

Chapter 10. Speech to Text and Vice Versa

Abstract

In this chapter, you will learn about the importance of speech-to-text and text-to-speech conversion. You will also learn about the functions and components needed to do this type of conversion.

Navin Kumar Manaswi

Chapter 11. Developing Chatbots

Abstract

Before you start learning about multilayered perceptron, you need to get a big-picture view of artificial neural networks. That’s what I’ll start with in this chapter.

Navin Kumar Manaswi

Chapter 12. Face Detection and Recognition

Abstract

Face detection is the process of detecting a face in an image or video.

Navin Kumar Manaswi

Backmatter

Titel: Deep Learning with Applications Using Python
verfasst von: Navin Kumar Manaswi
Verlag: Apress
Electronic ISBN: 978-1-4842-3516-4
Print ISBN: 978-1-4842-3515-7
DOI: https://doi.org/10.1007/978-1-4842-3516-4