Data Science & Artificial Intelligence

Introduction

This book will introduce the fields of data science and artificial intelligence (AI).

It will include a review of core concepts and fundamentals, and students will develop skills in using tools for data analysis as well as implementing AI techniques.

Objectives

• Understand the basic concepts of data science and artificial intelligence.
• Formulate problems that can be addressed using data science/AI methods.
• Use tools to perform exploratory analysis on datasets.
• Implement various machine learning algorithms based on given requirements.

Table of contents

Module One: Introduction to Data Science and Artificial Intelligence:

-Overview of data science, AI,

-Types of algorithms used in each field (rules-based systems, statistics models etc.)

-Machine learning, deep learning, and their applications.

-Overview of tasks performed in each field (data mining, machine learning, predictive analytics etc.)

– using tools for data analysis as well as implementing AI techniques.

-Introduces the related technologies such as Python, R, SQL and TensorFlow.

-Introduction to data management related to data science and AI

concepts.

–Basics of computer programming, storage systems, architectures, networks etc.

– Problems that can be addressed using data science/AI methods.

Module Two: Exploratory Data Analysis

-Use tools to perform exploratory analysis on datasets.

-Data wrangling techniques such as cleaning, transforming, and combining datasets

-Visualizing data for various types of patterns

-Exploratory plotting techniques

– Basics understanding of statistics

-Working with big datasets.

Module Three: Data Pre-Processing:

-How to use various datasets for data pre-processing techniques including cleansing, formatting, and normalizing.

-Different methods to handle missing values or outliers in the dataset.

Module Four: Supervised Learning:

-Understand supervised learning algorithms like linear regression, logistic regression, neural network models and decision trees.

-Exploring different methodologies used for hyperparameter tuning in supervised models.

Module Five: Unsupervised Learning: 

-Introduction to unsupervised methods such as k-means clustering and dimensionality reduction techniques including Principal Component Analysis (PCA).

-Clustering techniques

-Reinforcement Learning

-Generative Adversarial Networks (GANs)

-Discriminative algorithms.

-Application of various unsupervised learning algorithms on a given dataset.

Module Six: Deep Learning Fundamentals:   

-Learn about fundamental concepts of neural networks structures such as artificial neural networks (ANN)

-Convolutional neural networks (CNN).

-Understanding advanced deep learning concepts such as natural language processing with LSTMs

-Auto encoders & reinforcement learning algorithms etc.

Module Seven: Applied AI & Machine Learning Projects:    

-Practice solving real world problems using machine learning/AI tools with open-source datasets publicly available online.

-Developing a project leveraging various components of ML/AI for skill enhancement purposes.