Mobile Artificial Intelligence Projects电子书

Dedication

About Packt

Why subscribe?

Packt.com

Contributors

About the authors

About the reviewers

Packt is searching for authors like you

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Download the color images

Conventions used

Get in touch

Reviews

Artificial Intelligence Concepts and Fundamentals

AI versus machine learning versus deep learning

Evolution of AI

The mechanics behind ANNs

Biological neurons

Working of artificial neurons

Scenario 1

Scenario 2

Scenario 3

ANNs

Activation functions

Sigmoid function

Tanh function

ReLU function

Cost functions

Mean squared error

Cross entropy

Gradient descent

Backpropagation – a method for neural networks to learn

Softmax

TensorFlow Playground

Summary

Further reading

Creating a Real-Estate Price Prediction Mobile App

Setting up the artificial intelligence environment

Downloading and installing Anaconda

Advantages of Anaconda

Creating an Anaconda environment

Installing dependencies

Building an ANN model for prediction using Keras and TensorFlow

Serving the model as an API

Building a simple API to add two numbers

Building an API to predict the real estate price using the saved model

Creating an Android app to predict house prices

Downloading and installing Android Studio

Creating a new Android project with a single screen

Designing the layout of the screen

Adding a functionality to accept input

Adding a functionality to consume the RESTful API that serves the model

Additional notes

Creating an iOS app to predict house prices

Downloading and installing Xcode

Creating a new iOS project with a single screen

Designing the layout of the screen

Adding a functionality to accept input

Adding a functionality to consume the RESTful API that serves the model

Additional notes

Summary

Implementing Deep Net Architectures to Recognize Handwritten Digits

Building a feedforward neural network to recognize handwritten digits, version one

Building a feedforward neural network to recognize handwritten digits, version two

Building a deeper neural network

Introduction to Computer Vision

Machine learning for Computer Vision

Conferences help on Computer Vision

Summary

Further reading

Building a Machine Vision Mobile App to Classify Flower Species

CoreML versus TensorFlow Lite

CoreML

TensorFlow Lite

What is MobileNet?

Datasets for image classification

Creating your own image dataset using Google images

Alternate approach of creating custom datasets from videos

Building your model using TensorFlow

Running TensorBoard

Summary

Building an ML Model to Predict Car Damage Using TensorFlow

Transfer learning basics

Approaches to transfer learning

Building the TensorFlow model

Installing TensorFlow

Training the images

Building our own model

Retraining with our own images

Architecture

Distortions

Hyperparameters

Image dataset collection

Introduction to Beautiful Soup

Examples

Dataset preparation

Running the training script

Setting up a web application

Summary

PyTorch Experiments on NLP and RNN

PyTorch

The features of PyTorch

Installing PyTorch

PyTorch basics

Using variables in PyTorch

Plotting values on a graph

Building our own model network

Linear regression

Classification

Simple neural networks with torch

Saving and reloading data on the network

Running with batches

Optimization algorithms

Recurrent neural networks

The MNIST database

RNN classification

RNN cyclic neural network – regression

Natural language processing

Affine maps

Non-linearities

Objective functions

Building network components in PyTorch

BoW classifier using logistic regression

Summary

TensorFlow on Mobile with Speech-to-Text with the WaveNet Model

WaveNet

Architecture

Network layers in WaveNet

The algorithm's components

Building the model

Dependencies

Datasets

Preprocessing the dataset

Training the network

Testing the network

Transforming a speech WAV file into English text

Getting the model

Bazel build TensorFlow and quantizing the model

TensorFlow ops registration

Building an Android application

Requirements

Summary

Implementing GANs to Recognize Handwritten Digits

Introduction to GANs

Generative versus discriminative algorithms

How GANs work

Understanding the MNIST database

Building the TensorFlow model

Training the neural network

Building the Android application

Digit classifier

Summary

Sentiment Analysis over Text Using LinearSVC

Building the ML model using scikit–learn

Scikit-learn

The scikit-learn pipeline

LinearSVC

Building the iOS application

Summary

What is Next?

Popular ML–based cloud services

IBM Watson services

Microsoft Azure Cognitive Services

Vision APIs

Speech APIs

Knowledge APIs

Search APIs

Language APIs

Amazon ML

Vision services

Chat services

Language services

Google Cloud ML

Building your first ML model

The limitations of building your own model

Personalized user experience

Providing better search results

Targeting the right user

Summary

Further reading

Other Books You May Enjoy

Leave a review - let other readers know what you think