Think AI: Explore the flavours of Machine Learning, Neural Networks, Computer Vision and NLP with powerful python libraries
- Length: 274 pages
- Edition: 1
- Language: English
- Publisher: BPB Publications
- Publication Date: 2022-06-28
- ISBN-10: 9355513194
- ISBN-13: 9789355513199
- Sales Rank: #0 (See Top 100 Books)
Develop AI based real-world Applications
Key Features
- Provides a practical understanding of AI, including its concepts, tools and techniques.
- Includes step-by-by-step instructions for implementing machine learning and deep learning algorithms and features.
- Complex datasets and examples are used to expose mathematical illustrative and pseudo-coded examples.
Description
“Think AI” is a rapid-learning book that covers a wide range of Artificial Intelligence topics, including Machine Learning, Deep Learning, Computer Vision, and Natural Language Processing. Most popular Python libraries and toolkits are applied to develop intelligent and thoughtful applications.
With a solid grasp of python programming and mathematics, you may use this book’s statistical models and AI algorithms to meet AI needs and data insight issues. Each chapter in this book guides you swiftly through the core concepts and then directly to their implementation using Python toolkits. This book covers the techniques and skill sets required for data collection, pre-processing, installing libraries, preparing data models, training and deploying the models, and optimising model performance.
The book guides you through the OpenCV toolkit for real-time picture recognition and detection, allowing you to work with computer vision. The book describes how to analyse linguistic data and conduct text mining using the NLTK toolbox and provides a brief overview of NLP ideas. Throughout the book, you will utilise major Python libraries and toolkits such as pandas, TensorFlow, scikit-learn, and matplotlib.
What you will learn
- Work with Jupyter and various Python libraries, including scikit-learn, NLTK, and TF.
- Build and implement ML models and neural networks using TensorFlow and Keras.
- Utilize OpenCV for real-time image processing, face detection, and face recognition.
- Know how to interact and process textual data using NLTK toolkit.
- Deep dive on Exploratory Data Analysis (EDA) with pandas, matplotlib and seaborn.
Who this book is for
Whether you’re a student, newbie or an existing AI developer, this book will help you get up to speed with various domains of AI, including ML, Deep Learning and NLP. Knowing the basics of python and understanding mathematics will be beneficial.
Cover Page Title Page Copyright Page Dedication Page About the Author About the Reviewer Acknowledgement Preface Errata Table of Contents 1. Introducing Artificial Intelligence Structure Objective About Artificial Intelligence Human Intelligence versus Artificial Intelligence Making machines think like humans Turing test Need of AI Applications of AI Stages of AI AI vs ML/DL Agent and environment in AI AI agent Structure of an agent Building rational agent Intelligent agent Characteristics of intelligent agent Task environment Conclusion Points to remember 2. Essentials of Python and Data Analysis Structure Objective AI and Python Python vs R Setting up Python environment Anaconda navigator Python quick review Flow control statements if, elif, and else statement Loops Data structures in Python Lists Dictionary NumPy: an AI building block NumPy arrays Creating a vector Creating initialized arrays Accessing array elements Accessing multiple values through array slicing Working with N-dimensional arrays Array broadcasting Array reshaping Array operations Use case NumPy array in image processing Exploratory data analysis Data analysis with Pandas Working with series Working with DataFrames Filtering Data visualization Matplotlib Plotting with Seaborn library Python seaborn plotting functions Conclusion Points to remember 3. Data Preparation and Machine Learning Structure Objective Machine Learning Traditional programming and Machine Learning Types of ML Supervised learning Unsupervised learning Reinforcement learning Machine Learning workflow Supervised learning with classification and regression Building a regressor Linear regression Performance evaluation for regression Estimating chances of admission using linear regression Data collection Data preparation Splitting the database into feature variables (x) and output variable (y) Train the model Evaluation of the model Prediction of the result and model deployment Classification Classification algorithms Logistic regression classification Naïve Bayes classifier Support vector machine classification Decision tree algorithm K-Nearest Neighbor Algorithm (KNN) Classification performance evaluation Predicting loan eligibility using classification algorithms Selection of algorithm Unsupervised learning with clustering Clustering Types of clustering Clustering vs classification Clustering properties and evaluation metrics Clustering the data with K-Means algorithm Clustering bank customers using of K-Means algorithms Conclusion Points to remember 4. Computer Vision Using OpenCV Structure Objective Computer Vision Working of Computer Vision Representation of an image in computer Need for image processing OpenCV Installing OpenCV Basic operations in OpenCV Reading an image Viewing the image Image properties Resizing image Image edge detection Color spaces Converting images to different colorspaces Capturing the video from Webcam Detecting faces Cascade concept Haar cascade Face detection implementation Face recognition OpenCV recognizer Local binary patterns histograms (LBPH) face recognizer Implementation Conclusion Points to remember 5. Fundamentals of Neural Networks and Deep Learning Structure Objective Introduction Comprehending deep learning Rise of deep learning Approaching toward deep learning from traditional machine learning Neural networks and deep learning Activation function Neural networks learning mechanism through forward and backward propagation Forward propagation Backpropagation Types of neural networks in deep learning Deep learning frameworks Installing TensorFlow Use case of handwriting detection using deep learning using TensorFlow Conclusion Points to remember 6. Natural Language Processing Structure Objective Introduction Applications of NLP Exploring the features of NLTK Getting started with NLTK Downloading NLTK Understanding NLP pipeline Text preprocessing Tokenization Stop words removal Text normalization POS tagging Named entity recognition Feature extraction with bag of words (BoW) model Bag of words model example Managing vocabulary Implementing BoW with sklearn library Modeling Use case for building a sentiment analyzer Feature engineering Model training Prediction Conclusion Points to remember Index
Donate to keep this site alive
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.