Book Image

Intelligent Projects Using Python

By : Santanu Pattanayak
Book Image

Intelligent Projects Using Python

By: Santanu Pattanayak

Overview of this book

This book will be a perfect companion if you want to build insightful projects from leading AI domains using Python. The book covers detailed implementation of projects from all the core disciplines of AI. We start by covering the basics of how to create smart systems using machine learning and deep learning techniques. You will assimilate various neural network architectures such as CNN, RNN, LSTM, to solve critical new world challenges. You will learn to train a model to detect diabetic retinopathy conditions in the human eye and create an intelligent system for performing a video-to-text translation. You will use the transfer learning technique in the healthcare domain and implement style transfer using GANs. Later you will learn to build AI-based recommendation systems, a mobile app for sentiment analysis and a powerful chatbot for carrying customer services. You will implement AI techniques in the cybersecurity domain to generate Captchas. Later you will train and build autonomous vehicles to self-drive using reinforcement learning. You will be using libraries from the Python ecosystem such as TensorFlow, Keras and more to bring the core aspects of machine learning, deep learning, and AI. By the end of this book, you will be skilled to build your own smart models for tackling any kind of AI problems without any hassle.

Related Content you might be interested in

Current Title:

Small book image
Intelligent Projects Using Python
Santanu Pattanayak
Jan, 2019 | 342 pages
Small book image
Deep Learning for Natural Language Processing
Shubhangi Hora | Karthiek Reddy Bokka | Tanuj Jain | Monicah Wambugu
Jun, 2019 | 372 pages
Small book image
Deep Learning Quick Reference
Michael Bernico
Mar, 2018 | 272 pages
Small book image
Hands-On Deep Learning Architectures with Python
Yuxi Hayden Liu | Saransh Mehta
Apr, 2019 | 316 pages
Table of Contents (12 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Foundations of Artificial Intelligence Based Systems
Foundations of Artificial Intelligence Based Systems
Neural networks
Neural activation units
The backpropagation method of training neural networks
Convolutional neural networks
Recurrent neural networks (RNNs)
Generative adversarial networks
Reinforcement learning
Transfer learning
Restricted Boltzmann machines
Autoencoders
Summary
2
Transfer Learning
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
Network architecture
The optimizer and initial learning rate
Cross-validation
Model checkpoints based on validation log loss
Python implementation of the training process
Results from the categorical classification
Inference at testing time
Performing regression instead of categorical classification
Using the keras sequential utils as generator
Summary
3
Neural Machine Translation
Neural Machine Translation
Technical requirements
Rule-based machine translation
Statistical machine-learning systems
Neural machine translation
Implementing a sequence-to-sequence neural translation machine
Summary
4
Style Transfer in Fashion Industry using GANs
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
5
Video Captioning Application
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
Creating a word vocabulary for the captions
Training the model
Training results
Inference with unseen test videos
Summary
6
The Intelligent Recommender System
The Intelligent Recommender System
Technical requirements
What is a recommender system?
Latent factorization-based recommendation system
Deep learning for latent factor collaborative filtering
SVD++
Restricted Boltzmann machines for recommendation
Contrastive divergence
Collaborative filtering using RBMs
Collaborative filtering implementation using RBM
Inference using the trained RBM
Summary
7
Mobile App for Movie Review Sentiment Analysis
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
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
8
Conversational AI Chatbots for Customer Service
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
Summary
9
Autonomous Self-Driving Car Through Reinforcement Learning
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
Results from the training
Summary
10
CAPTCHA from a Deep-Learning Perspective
CAPTCHA from a Deep-Learning Perspective
Technical requirements
Breaking CAPTCHAs with deep learning
CAPTCHA generation through adversarial learning
Summary
11
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Processing video images to create CNN features

Once we have downloaded the data from the specified location, the next task is to process the video image frames to extract features out of the last fully connected layers of a pre-trained convolutional neural network. We use a VGG16 convolutional neural network that is pre-trained on ImageNet. We take the activations out of the last fully connected layer of the VGG16. Since the last fully connected layer of VGG16 has 4096 units, our feature vector ft for each time step t is a 4096, dimensional vector that is ft ∈ R4096 .

Before the images from the videos can be processed through the VGG16, they need to be sampled from the video. We sample images from the video in such a way that each video has 80 frames. After processing the 80 image frames from VGG16, each video will have 80 feature vectors f1, f2, . . . . . ft . . . f80...

Previous Section
End of Section 6
Next Section