Intelligent Projects Using Python电子书

Title Page

Copyright and Credits

Intelligent Projects Using Python

About Packt

Why subscribe?

Packt.com

Contributors

About the author

About the reviewer

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

Code in action

Conventions used

Get in touch

Reviews

Foundations of Artificial Intelligence Based Systems

Neural networks

Neural activation units

Linear activation units

Sigmoid activation units

The hyperbolic tangent activation function

Rectified linear unit (ReLU)

The softmax activation unit

The backpropagation method of training neural networks

Convolutional neural networks

Recurrent neural networks (RNNs)

Long short-term memory (LSTM) cells

Generative adversarial networks

Reinforcement learning

Q-learning

Deep Q-learning

Transfer learning

Restricted Boltzmann machines

Autoencoders

Summary

Transfer Learning

Technical requirements

Introduction to transfer learning

Transfer learning and detecting diabetic retinopathy

The diabetic retinopathy dataset

Formulating the loss function

Taking class imbalances into account

Preprocessing the images

Additional data generation using affine transformation

Rotation

Translation

Scaling

Reflection

Additional image generation through affine transformation

Network architecture

The VGG16 transfer learning network

The InceptionV3 transfer learning network

The ResNet50 transfer learning network

The optimizer and initial learning rate

Cross-validation

Model checkpoints based on validation log loss

Python implementation of the training process

Dynamic mini batch creation during training

Results from the categorical classification

Inference at testing time

Performing regression instead of categorical classification

Using the keras sequential utils as generator

Summary

Neural Machine Translation

Technical requirements

Rule-based machine translation

The analysis phase

Lexical transfer phase

Generation phase

Statistical machine-learning systems

Language model

Perplexity for language models

Translation model

Neural machine translation

The encoder–decoder model

Inference using the encoder–decoder model

Implementing a sequence-to-sequence neural translation machine

Processing the input data

Defining a model for neural machine translation

Loss function for the neural translation machine

Training the model

Building the inference model

Word vector embeddings

Embeddings layer

Implementing the embeddings-based NMT

Summary

Style Transfer in Fashion Industry using GANs

Technical requirements

DiscoGAN

CycleGAN

Learning to generate natural handbags from sketched outlines

Preprocess the Images

The generators of the DiscoGAN

The discriminators of the DiscoGAN

Building the network and defining the cost functions

Building the training process

Important parameter values for GAN training

Invoking the training

Monitoring the generator and the discriminator loss

Sample images generated by DiscoGAN

Summary

Video Captioning Application

Technical requirements

CNNs and LSTMs in video captioning

A sequence-to-sequence video-captioning system

Data for the video-captioning system

Processing video images to create CNN features

Processing the labelled captions of the video

Building the train and test dataset

Building the model

Definition of the model variables

Encoding stage

Decoding stage

Building the loss for each mini-batch

Creating a word vocabulary for the captions

Training the model

Training results

Inference with unseen test videos

Inference function

Results from evaluation

Summary

The Intelligent Recommender System

Technical requirements

What is a recommender system?

Latent factorization-based recommendation system

Deep learning for latent factor collaborative filtering

The deep learning-based latent factor model

SVD++

Training model with SVD++ on the Movie Lens 100k dataset

Restricted Boltzmann machines for recommendation

Contrastive divergence

Collaborative filtering using RBMs

Collaborative filtering implementation using RBM

Processing the input

Building the RBM network for collaborative filtering

Training the RBM

Inference using the trained RBM

Summary

Mobile App for Movie Review Sentiment Analysis

Technical requirements

Building an Android mobile app using TensorFlow mobile

Movie review rating in an Android app

Preprocessing the movie review text

Building the model

Training the model

The batch generator

Freezing the model to a protobuf format

Creating a word-to-token dictionary for inference

App interface page design

The core logic of the Android app

Testing the mobile app

Summary

Conversational AI Chatbots for Customer Service

Technical requirements

Chatbot architecture

A sequence-to-sequence model using an LSTM

Building a sequence-to-sequence model

Customer support on Twitter

Creating data for training the chatbot

Tokenizing the text into word indices

Replacing anonymized screen names

Defining the model

Loss function for training the model

Training the model

Generating output responses from the model

Putting it all together

Invoking the training

Results of inference on some input tweets

Summary

Autonomous Self-Driving Car Through Reinforcement Learning

Technical requirements

Markov decision process

Learning the Q value function

Deep Q learning

Formulating the cost function

Double deep Q learning

Implementing an autonomous self-driving car

Discretizing actions for deep Q learning

Implementing the Double Deep Q network

Designing the agent

The environment for the self-driving car

Putting it all together

Helper functions

Results from the training

Summary

CAPTCHA from a Deep-Learning Perspective

Technical requirements

Breaking CAPTCHAs with deep learning

Generating basic CAPTCHAs

Generating data for training a CAPTCHA breaker

Captcha breaker CNN architecture

Pre-processing the CAPTCHA images

Converting the CAPTCHA characters to classes

Data generator

Training the CAPTCHA breaker

Accuracy on the test data set

CAPTCHA generation through adversarial learning

Optimizing the GAN loss

Generator network

Discriminator network

Training the GAN

Noise distribution

Data preprocessing

Invoking the training

The quality of CAPTCHAs during training

Using the trained generator to create CAPTCHAs for use

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think