Book Image

Artificial Intelligence with Python - Second Edition

By : Alberto Artasanchez, Prateek Joshi
Book Image

Artificial Intelligence with Python - Second Edition

By: Alberto Artasanchez, Prateek Joshi

Overview of this book

Artificial Intelligence with Python, Second Edition is an updated and expanded version of the bestselling guide to artificial intelligence using the latest version of Python 3.x. Not only does it provide you an introduction to artificial intelligence, this new edition goes further by giving you the tools you need to explore the amazing world of intelligent apps and create your own applications. This edition also includes seven new chapters on more advanced concepts of Artificial Intelligence, including fundamental use cases of AI; machine learning data pipelines; feature selection and feature engineering; AI on the cloud; the basics of chatbots; RNNs and DL models; and AI and Big Data. Finally, this new edition explores various real-world scenarios and teaches you how to apply relevant AI algorithms to a wide swath of problems, starting with the most basic AI concepts and progressively building from there to solve more difficult challenges so that by the end, you will have gained a solid understanding of, and when best to use, these many artificial intelligence techniques.

Related Content you might be interested in

Current Title:

Small book image
Artificial Intelligence with Python - Second Edition
Alberto Artasanchez | Prateek Joshi
Jan, 2020 | 618 pages
Small book image
Python Machine Learning Cookbook,
Prateek Joshi | Giuseppe Ciaburro
Mar, 2019 | 642 pages
Small book image
OpenCV 3.x with Python By Example
Prateek Joshi | Gabriel Garrido Calvo
Jan, 2018 | 268 pages
Small book image
Artificial Intelligence and Machine Learning Fundamentals
Zsolt Nagy
Dec, 2018 | 330 pages
Table of Contents (26 chapters)
Preface
Preface
Who this book is for
What this book covers
What you need for this book
Get in touch
1
Introduction to Artificial Intelligence
Introduction to Artificial Intelligence
What is AI?
Why do we need to study AI?
Branches of AI
The five tribes of machine learning
Defining intelligence using the Turing test
Making machines think like humans
Building rational agents
General Problem Solver
Building an intelligent agent
Installing Python 3
Installing packages
Loading data
Summary
Free Chapter
2
Fundamental Use Cases for Artificial Intelligence
Fundamental Use Cases for Artificial Intelligence
Representative AI use cases
Digital personal assistants and chatbots
Personal chauffeur
Shipping and warehouse management
Human health
Knowledge search
Recommendation systems
The smart home
Gaming
Movie making
Underwriting and deal analysis
Data cleansing and transformation
Summary
References
3
Machine Learning Pipelines
Machine Learning Pipelines
What is a machine learning pipeline?
Problem definition
Data ingestion
Data preparation
Data segregation
Model training
Summary
4
Feature Selection and Feature Engineering
Feature Selection and Feature Engineering
Feature selection
Feature engineering
Outlier management
One-hot encoding
Log transform
Scaling
Date manipulation
Summary
5
Classification and Regression Using Supervised Learning
Classification and Regression Using Supervised Learning
Supervised versus unsupervised learning
What is classification?
Preprocessing data
Label encoding
Logistic regression classifiers
The Naïve Bayes classifier
Confusion matrixes
Support Vector Machines
Classifying income data using Support Vector Machines
What is regression?
Building a single-variable regressor
Building a multivariable regressor
Estimating housing prices using a Support Vector Regressor
Summary
6
Predictive Analytics with Ensemble Learning
Predictive Analytics with Ensemble Learning
What are decision trees?
What is ensemble learning?
What are random forests and extremely random forests?
Dealing with class imbalance
Finding optimal training parameters using grid search
Computing relative feature importance
Predicting traffic using an extremely random forest regressor
Summary
7
Detecting Patterns with Unsupervised Learning
Detecting Patterns with Unsupervised Learning
What is unsupervised learning?
Clustering data with the K-Means algorithm
What are Gaussian Mixture Models?
Finding subgroups in stock market using the Affinity Propagation model
Segmenting the market based on shopping patterns
Summary
8
Building Recommender Systems
Building Recommender Systems
Extracting the nearest neighbors
Building a K-nearest neighbors classifier
Computing similarity scores
Finding similar users using collaborative filtering
Building a movie recommendation system
Summary
9
Logic Programming
Logic Programming
What is logic programming?
Understanding the building blocks of logic programming
Solving problems using logic programming
Installing Python packages
Matching mathematical expressions
Validating primes
Parsing a family tree
Analyzing geography
Building a puzzle solver
Summary
10
Heuristic Search Techniques
Heuristic Search Techniques
Is heuristic search artificial intelligence?
What is heuristic search?
Constraint satisfaction problems
Local search techniques
Constructing a string using greedy search
Solving a problem with constraints
Solving the region-coloring problem
Building an 8-puzzle solver
Building a maze solver
Summary
11
Genetic Algorithms and Genetic Programming
Genetic Algorithms and Genetic Programming
The evolutionists tribe
Understanding evolutionary and genetic algorithms
Fundamental concepts in genetic algorithms
Generating a bit pattern with predefined parameters
Visualizing the evolution
Solving the symbol regression problem
Building an intelligent robot controller
Genetic programming use cases
Summary
References
12
Artificial Intelligence on the Cloud
Artificial Intelligence on the Cloud
Why are companies migrating to the cloud?
The top cloud providers
Amazon Web Services (AWS)
Microsoft Azure
Google Cloud Platform (GCP)
Summary
13
Building Games with Artificial Intelligence
Building Games with Artificial Intelligence
Using search algorithms in games
Combinatorial search
Installing the easyAI library
Building a bot to play Last Coin Standing
Building a bot to play Tic-Tac-Toe
Building two bots to play Connect Four™ against each other
Building two bots to play Hexapawn against each other
Summary
14
Building a Speech Recognizer
Building a Speech Recognizer
Working with speech signals
Visualizing audio signals
Transforming audio signals to the frequency domain
Generating audio signals
Synthesizing tones to generate music
Extracting speech features
Recognizing spoken words
Summary
15
Natural Language Processing
Natural Language Processing
Introduction and installation of packages
Tokenizing text data
Converting words to their base forms using stemming
Converting words to their base forms using lemmatization
Dividing text data into chunks
Extracting the frequency of terms using the Bag of Words model
Building a category predictor
Constructing a gender identifier
Building a sentiment analyzer
Topic modeling using Latent Dirichlet Allocation
Summary
16
Chatbots
Chatbots
The future of chatbots
Chatbots today
Chatbot concepts
A well-architected chatbot
Chatbot platforms
Creating a chatbot using DialogFlow
Summary
17
Sequential Data and Time Series Analysis
Sequential Data and Time Series Analysis
Understanding sequential data
Handling time series data with Pandas
Slicing time series data
Operating on time series data
Extracting statistics from time series data
Generating data using Hidden Markov Models
Identifying alphabet sequences with Conditional Random Fields
Stock market analysis
Summary
18
Image Recognition
Image Recognition
Importance of image recognition
OpenCV
Frame differencing
Tracking objects using color spaces
Object tracking using background subtraction
Building an interactive object tracker using the CAMShift algorithm
Optical flow-based tracking
Face detection and tracking
Eye detection and tracking
Summary
19
Neural Networks
Neural Networks
Introduction to neural networks
Building a Perceptron-based classifier
Constructing a single-layer neural network
Constructing a multi-layer neural network
Building a vector quantizer
Analyzing sequential data using recurrent neural networks
Visualizing characters in an optical character recognition database
Building an optical character recognition engine
Summary
20
Deep Learning with Convolutional Neural Networks
Deep Learning with Convolutional Neural Networks
The basics of Convolutional Neural Networks
Architecture of CNNs
Types of layers in a CNN
Building a perceptron-based linear regressor
Building an image classifier using a single-layer neural network
Building an image classifier using a Convolutional Neural Network
Summary
Reference
21
Recurrent Neural Networks and Other Deep Learning Models
Recurrent Neural Networks and Other Deep Learning Models
The basics of Recurrent Neural Networks
Architecture of RNNs
A language modeling use case
Training an RNN
Summary
22
Creating Intelligent Agents with Reinforcement Learning
Creating Intelligent Agents with Reinforcement Learning
Understanding what it means to learn
Reinforcement learning versus supervised learning
Real-world examples of reinforcement learning
Building blocks of reinforcement learning
Creating an environment
Building a learning agent
Summary
23
Artificial Intelligence and Big Data
Artificial Intelligence and Big Data
Big data basics
The three V's of big data
Big data and machine learning
NoSQL Databases
Summary
24
Other Books You May Enjoy
Other Books You May Enjoy
25
Index
Index

Data cleansing and transformation

Just as gas powers a car, data is the lifeblood of AI. The age-old adage of "garbage in, garbage out" remains painfully true. For this reason, having clean and accurate data is paramount to producing consistent, reproducible, and accurate AI models. Some of this data cleansing has required painstaking human involvement. By some measures, it is said that a data scientist spends about 80% of their time cleaning, preparing, and transforming their input data and 20% of the time running and optimizing their models. Examples of this are the ImageNet and MS-COCO image datasets. Both contain over a million labeled images of various objects and categories. These datasets are used to train models that can distinguish between different categories and object types. Initially, these datasets were painstakingly and patiently labeled by humans. As these systems become more prevalent, we can use AI to perform the labeling. Furthermore, there is a plethora of AI-enabled tools that help with the cleansing and deduplication process.

One good example is Amazon Lake Formation. In August 2019, Amazon made its service Lake Formation generally available. Amazon Lake Formation automates some of the steps typically involved in the creation of a data lake including the collection, cleansing, deduplication, cataloging, and publication of data. The data then can be made available for analytics and to build machine models. To use Lake Formation, a user can bring data into the lake from a range of sources using predefined templates. They can then define policies that govern data access depending on the level of access that groups across the organization require.

Some automatic preparation, cleansing, and classification that the data undergoes uses machine learning to automatically perform these tasks.

Lake Formation also provides a centralized dashboard where administrators can manage and monitor data access policies, governance, and auditing across multiple analytics engines. Users can also search for datasets in the resulting catalog. As the tool evolves in the next few months and years, it will facilitate the analysis of data using their favorite analytics and machine learning services, including:

  • Databricks
  • Tableau
  • Amazon Redshift
  • Amazon Athena
  • AWS Glue
  • Amazon EMR
  • Amazon QuickSight
  • Amazon SageMaker
Previous Section
End of Section 13
Next Section