Artificial Intelligence

Self-Starter Handbook

Build Your Own Roadmap

2nd edition

Revised & Extended

This is still work in progress, kindly provide your feedback on

alt text

Questions answered in this book:

Proposed Framework:

Ch0: About the Handbook

0.1 Why this Handbook?

Too many resources for starters

Mostly low quality material

No end-to-end view

Money minting courses

Beginners’ FAQs

0.2 What this Handbook covers?

Not a typical concept or hands-on book

Focuses on effective utilization of existing resources

Equivalent to a guide

0.3 Who this handbook is for?

Literally everyone

Ch1: Understanding the Big Picture

1.1 Navigating the landscape

1.2 End-to-end AI Project

1.3 Working on building blocks

1.4 Utilizing the resources

1.5 Building your portfolio

1.6 Networking & landing the job

1.7 Switching to an AI Role

1.8 Leading AI Initiatives

1.9 Making your career future-proof


Ch2: Navigating the Landscape

2.1 Why is AI Important?

2.2 What is AI?

2.3 Brief History of AI

2.4 Different Approaches/Methods

2.5 Relation with Other Fields

2.6 Academics Vs Industry

2.7 Limitations of AI

2.8 Disadvantages of AI

2.9 Current State of AI

Ch3: Real-World AI Projects

3.1 End-to-end Process

Identify & Assess the Use-cases

Define the Problem & KPIs

Collect & Understand the Data

Clean & Prepare the Data

Build & Evaluate Models

Deploy & Monitor KPIs

3.2 Different Roles

AI/ML Engineer

Data Engineer

Data Analyst

Software Engineer

Product Owner

Business Owner

BI Engineer

DevOps Engineer

3.3 Hackathons Vs Real World

Identify & Assess the Use-cases

Define the Problem

Collect & Understand the Data

Prepare the Data

Build & Evaluate Models

Deploy & Monitor


Ch4: Working on Building Blocks

4.1 Pre-requisites



Data Literacy

4.2 Core Concepts

Machine Learning

Natural Language Processing

Deep Learning

General Adversarial Networks

Reinforcement Learning

4.3 Peripheral Concepts

Data Engineering

Cloud Computing

Solution Architecture


Enterprise AI

Explainable AI

4.4 Tools to Master






Ch5: Utilizing the Resources

5.1 Books to Refer

5.2 Courses to Attend

5.3 Blogs to Follow

5.4 Influencers to Connect

5.5 Podcasts to Listen

5.6 Channels to Subscribe


Ch6: Building your Portfolio

6.1 Work on Public Data-sets

6.2 Participate in Hackathons

6.3 Publish projects on Git-Hub

6.4 Guide the Beginners

6.5 Start a Blog/Padcast/Channel

Ch7: Networking & Landing the Job

7.1 Network on LinkedIn

7.2 Attend Meetups

7.4 Search, Filter & Apply

7.3 Fine-Tune your CV

7.5 Crack the Interview


Ch8: Switching to an AI Role

8.1 Build your Skills

8.2 Identify AI Use cases

8.3 Solve & Share

8.4 Launch your Profile

8.5 Look the Role Outside

Ch9: Leading AI Initiatives

9.1 Identify the Use Cases

9.2 Execute Low-hanging Fruits

9.3 Build & Train Team

9.4 Develop AI Strategy

9.5 Execute the Projects

9.6 Reflect on the Outcomes

Ch10: Making Your Career Future-Proof

10.2 Build ‘Evolve’ Mindset

10.3 T-shaped Skill-set

10.4 Hone Soft Skills

10.5 Maintain Digital Portfolio

10.6 Expand Network Globally

Ch11: Putting it All Together

11.1 Master the Basics

11.2 Avoid Being a Junkie

11.3 Learn to Solve

11.4 Just Enough Approach

11.5 Handle Data Like a Pro

11.6 Focus on Context

11.7 Conclusion


A. Mathematics for AI



Linear Algebra

Multivariate Calculus

B. Machine Learning

Machine Learning Concepts

Gradient Descent

Batch Gradient Descent, Stochastic Gradient Descent, Mini-batch Gradient Descent

Performance Measures

Error Analysis

Computational Complexity

Types of Machine Learning

Supervised & Unsupervised Learning, Batch & Online Learning, Instance-based Vs Model-based Learning

Ensemble Learning

Bagging, Boosting, Stacking

Challenges in Machine Learning

Insufficient Data, Nonrepresentative Data, Poor-Quality Data, Irrelevant Features, Overfitting & Underfitting

Machine Learning Algorithms

Linear Regression

Logistic Regression

kNN Algorithm

Naive Bayes

Decision Trees & Random Forests

Support Vector Machines

Neural Networks

Dimensionality Reduction

kMeans Algorithm

Associative Learning

Anomaly Detection

C. Natural Language Processing

NLP Concepts

Lexical Processing

Regex, Tokenization, Bag of Words, Tf-Idf, Canocalization, Stemming, Lemmatization

Syntactical Processing

POS Tagging, Markov Chain, Information Extraction, Named Entity Extraction

Semantic Processing

Entity, Arity, Latent Semantic Analysis, Topic Modelling

NLP Techniques

D. Deep Learning

DL Concepts

Artificial Neuron, Perceptron & MLP, Forward & Backpropogation, Fine Tuning Hyperparameters, Vanishing & Exploding Gradients, Reusing Pretrained Models, Faster Optimizers, Regularization

DL Frameworks


Convolution Layer, Pooling Layer, CNN Architectures, Classification & Localization, Object Detection, Semantic Segmentation


Recurrent Neurons, Memory Cells, Long Sequences, Short-Term Memory Problem, Stateful RNN, Masking, Bidirectional RNNs, Beam Search, Attendtion Mechanism


Linear Encoders, Stacked Encoders, Convolutional Autoencoders, Recurrent Autoencoders, Denoising Autoencoders, Sparse Autoencoders, Variational Autoencoders


Generative models, Generative Matching Networks, Generative Adversarial Networks, Generator and Discriminator

E. Data Engineering

F. Cloud Computing

G. DevOps & MLOps

H. AI Tool-Box