Tab 1

AI/ML Beginner-friendly Free Resources

Introduction

Welcome! I'm Pixie, and I’m thrilled you're beginning your journey into the exciting world of
Machine Learning. Whether you're entirely new or have some programming background, I've
tailored this guide to help you smoothly grasp foundational concepts and confidently tackle
advanced topics. The resources, projects, and tips shared here have significantly shaped my
learning experience and I hope they inspire and assist you as much as they did for me. Let's get
started on this amazing adventure.

Originally created to help out my college’s freshers, it remains useful for anyone beginning their
journey in the world of ML.

Curated by:
Pixie Perceptron

Connect with the author:

LinkedIn: http://www.linkedin.com/in/snehaaroychowdhury
X: https://x.com/pixieperceptron

Prerequisites
None, but the basics of Python would help you to understand the concepts better.

Link:https://youtube.com/playlist?list=PLu0W_9lII9agwh1XjRt242xIpHhPT2llg&si=6UvdWEYv4
LF_GdwN
Watch videos 1-55 to understand the basics. The videos are really short, so 10 videos/day
(during the summer/winter break, or even in the metro xD) can be easily watched if you’re not
familiar with this language.

Requirements
Laptop or Computer. We will be using Google Colab/Kaggle notebooks for the
implementation, so VS Code, Jupyter notebooks, or a device with a good GPU isn’t required.

Platform Suggestions:
●​ Google Colab (Primary)
●​ Kaggle Kernels (Offers longer GPU hours and powerful machines—recommended for
bigger projects and competitions)

SCHEDULE

SESSION 1 - INTRODUCTION TO PYTHON AND OOP CONCEPTS

●​ Introduction to the basics of Python programming.

●​ Understanding object-oriented programming (OOP) principles.
●​ Practice with classes, objects, inheritance, and polymorphism.

If you missed the class, then go through them:

1.​ Python Basics - https://youtu.be/rfscVS0vtbw?si=p5knn6OF7yTMG2VK

2.​ OOPS Basics - https://youtu.be/Ej_02ICOIgs?si=WIoGPd1GzV4FIl1e

SESSION 2 - DATA ANALYSIS WITH NUMPY, PANDAS, AND DATA VISUALIZATION WITH
MATPLOTLIB

●​ Essentials of data manipulation using Numpy and Pandas.

●​ Techniques for data preprocessing and cleaning.
●​ Introduction to data visualization using Matplotlib.
●​ Practical exercises to manipulate and visualize datasets.

If you missed the class, then go through this: https://youtu.be/r-uOLxNrNk8?si=cIRirgoihjHshu24

SESSION 3 - UNDERSTANDING LINEAR, LOGISTIC, AND POLYNOMIAL REGRESSION

●​ Introduction to regression and its importance.

●​ Understanding the concepts of linear, logistic, and polynomial regression.

If you missed the class/wish to understand further, watch them:

 1.​ Linear Regression: https://youtu.be/4b4MUYve_U8?si=ZnSdjbGCyi0P9Zmz
2.​ Logistic Regression: https://youtu.be/het9HFqo1TQ?si=eHoUO4tp5MmrAqAa
3.​ Polynomial Regression: https://youtu.be/BNWLf3cKdbQ?si=dZNJMC201r7Lm_BA

SESSION 4 - EXPLORING KNN, SVM, AND NAIVE BAYES

●​ Deep dive into K-nearest neighbors (KNN), support vector machines (SVM), and Naive
Bayes classifiers.
●​ Understanding the mathematical foundations and applications of these algorithms.
●​ Practical implementation of KNN, SVM, and Naive Bayes using Python.
●​ Analyzing the performance of different classifiers.

If you missed the class/wish to understand further, watch them:

1.​ KNN: https://youtu.be/abnL_GUGub4?si=7qFPNIdCoxzkiS6c

2.​ SVM: https://youtu.be/ugTxMLjLS8M?si=m9M4cMd1bDt3dJJG
3.​ Naive Bayes: https://youtu.be/O2L2Uv9pdDA?si=htx7QCu8HwHouOzk

SESSION 5 - DECISION TREES, ENSEMBLE METHODS, AND RANDOM FOREST

●​ Introduction to decision trees and their working principles.

●​ Exploring ensemble methods like bagging and boosting.
●​ Detailed study of the Random Forest algorithm.
●​ Build and evaluate decision trees and random forests to compare performance.

If you missed the class/wish to understand further, watch them:

1.​ Decision Trees: https://youtu.be/_L39rN6gz7Y?si=oXCbqWrvV2vL3r-6

2.​ Ensemble Methods: https://youtu.be/bHK1fE_BUms?si=K6B0Dl-vObzEyRvN
3.​ Random Forests: https://youtu.be/gkXX4h3qYm4?si=Guj3C9NBhoswKjD4

SESSION 6 - INTRODUCTION TO DEEP LEARNING, NEURAL NETWORKS, AND

PYTORCH BASICS

●​ Overview of deep learning and its significance.

●​ Understanding neural networks and their architectures.
●​ Introduction to Pytorch and its fundamental concepts.
●​ Building simple neural networks using Pytorch.

If you missed the class/wish to understand further, watch them:

1.​ Deep Learning Basics: https://youtu.be/O5xeyoRL95U?si=flJMP1XSZq1lvwTD

2.​ Neural Networks:

⭐⭐⭐⭐
https://youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi&si=lsH
9rZprZv6Uj8n6 Pixie Recommended
 3.​ Neural Networks (Andrej Karpathy playlist):

⭐⭐⭐⭐
https://youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ&si=mHvo76
80O9Tt4fB2 Pixie Recommended
4.​ PyTorch: https://youtu.be/V_xro1bcAuA?si=Kf062cUdYx1bZ3Jg

SESSION 7 - OPTIMIZERS, REGULARIZATION, NORMALIZATION, AND BATCH GRADIENT

DESCENT

●​ Exploring various optimization techniques for neural networks.

●​ Understanding regularization and normalization methods.
●​ Implementing batch gradient descent.
●​ Data preprocessing techniques for deep learning models.

If you missed the class/wish to understand further, watch them:

1.​ Optimizers:
https://youtube.com/playlist?list=PLKnIA16_RmvYhD5pqAeVu3j_jTjnTJIW2&si=MnLi-6X
UeRqRgaB2
2.​ Regularization: https://youtu.be/EehRcPo1M-Q?si=mxxslpuPfqa3jcwf
3.​ Normalization: https://youtu.be/eBrGyuA2MIg?si=DXOwSWHcY-Tp6h8c
4.​ Bath Gradient Descent: https://youtu.be/Jyo53pAyVAM?si=EGi64mdWhSIAjW1m

SESSION 8 - CONVOLUTIONAL NEURAL NETWORKS (CNN)

●​ Introduction to Convolutional Neural Networks (CNN) and their applications.

●​ Theory behind CNNs, including convolutional layers, pooling layers, and fully connected
layers.
●​ Example Implementation of CNNs.

If you missed the class/wish to understand further, watch them:

1.​ CNN: https://youtu.be/bNb2fEVKeEo?si=cRr6wU1_-PFaWaxV

SESSION 9 - NATURAL LANGUAGE PROCESSING (NLP)

●​ Basics of Natural Language Processing (NLP).

●​ Understanding text preprocessing techniques, such as tokenization and stemming.
●​ Introduction to RNNs and LSTMs
●​ Practical implementation of NLP models using Python libraries.

If you missed the class/wish to understand further, watch them:

1.​ NLP Playlist:

https://youtube.com/playlist?list=PLoROMvodv4rOaMFbaqxPDoLWjDaRAdP9D&si=yGg
1kXHnTjBwZsBW
2.​ RNN: https://youtu.be/AsNTP8Kwu80?si=3uKI1gliLEJeN0ge
 3.​ LSTM: https://youtu.be/YCzL96nL7j0?si=aK6zr8hc8yaCFtvu

FAQs
1.​ Will the sessions be recorded?
Yes, you can access the recordings if you accidentally miss a session, but you need to be
regular in the classes to ask live doubts and fulfil the attendance criteria to receive the
certificate.
2.​ Will we receive the study material and codes?
Yes, it will be shared in the group.
3.​ Will the attendance be taken?
Yes, and you need to fulfil the attendance criteria and submit the projects before the deadlines
to receive the certificate.
4.​ What is the criteria to receive the certificate?
Same as above.
5.​ Would there be any project(s)?
Yes, we would be doing hands-on sessions to help you understand the implementation of the
concepts.
6.​ Is it going to be beginner-friendly?
Yes, but we still recommend you to watch Code Harry’s playlist (link shared above) to
understand the concepts better.
7.​ How to ask doubts?
You can ask it during the session itself, preferably towards the end of it and ask it in the group. It
is NOT recommended to personally DM the mentors if you’re not facing a serious issue.
8.​ Will it help to win hackathons?
The concepts you learn here would most definitely help you build up the basics and also make
beginner-friendly projects. If you gain further interest, the mentors would share additional
resources for you to excel the concepts further, which would eventually be very useful for the
hackathons.

Additional Resources (if you want to go a step further…)

1.​ Basics of AI (Harvard CS50): https://youtu.be/5NgNicANyqM?si=naKRSgSH2M-uJBkG
2.​ Maths for Machine Learning -
https://www.coursera.org/specializations/mathematics-machine-learning
Audit it to watch it for free or just go through the following topics from your Sem 1 and
Sem 2 coursework -
Linear Algebra, Multivariable Calculus, Probability and Statistics (preferably in this
order only).
3.​ Machine Learning Specialization by Andrew NG (YouTube):
https://youtube.com/playlist?list=PLkDaE6sCZn6FNC6YRfRQc_FbeQrF8BwGI&si=B9h1
WV-qcjWT7byY
 OR
4.​ Machine Learning Specialization by Andrew NG (Coursera - get Financial Aid for free

⭐⭐⭐⭐
access): https://www.coursera.org/specializations/machine-learning-introduction
(3-course series - takes around a month to complete) Pixie Recommended
5.​ Deep Learning Specialization by Andrew NG (Coursera - get Financial Aid for free

⭐⭐⭐⭐⭐
access): https://www.coursera.org/specializations/deep-learning (5-course series - takes
around 3 months to complete) Pixie recommended
OR
6.​ Deep Learning Specialization by Andrew NG/Coursera (YouTube):
i) Course 1:
https://youtube.com/playlist?list=PLkDaE6sCZn6Ec-XTbcX1uRg2_u4xOEky0&si=gY7X
MYxyEZLow3YZ
ii) Course 2:
https://youtube.com/playlist?list=PLkDaE6sCZn6Hn0vK8co82zjQtt3T2Nkqc&si=-180Wjv
2a6wNxADV
iii) Course 3:
https://youtube.com/playlist?list=PLkDaE6sCZn6E7jZ9sN_xHwSHOdjUxUW_b&si=fnDn
AHmGIydVktx7
iv) Course 4:
https://youtube.com/playlist?list=PLkDaE6sCZn6Gl29AoE31iwdVwSG-KnDzF&si=8yxrG
kMS5wT4R15c

7.​ Refer to Python’s documentations, Medium articles and read as many research papers
as you can for a better understanding - go through their source codes on Github and try
to implement it by yourself using ChatGPT, Gemini, etc. Try to refer to research papers
from A* conferences of IEEE, Springer - especially the recent ones since if you try to
read old papers and implement them, their source codes might give you dependency
conflicts while running.
8.​ Try to participate in Kaggle competitions when you gain further interest. Good ranks in
those competitions would be great for your resume.
9.​ Some resources to learn ML by Indian YouTubers if you prefer learning in Hindi - Krish

⭐⭐⭐⭐⭐
Naik and CampusX
10.​Neural Networks (Honestly the best on YouTube): Pixie Recommended
https://youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi&si=YX
wf8Z97sPOSeHgk
11.​Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools,

⭐⭐⭐⭐
and Techniques to Build Intelligent Systems (If you love books, then you can get a free
pdf online) Pixie Recommended
https://www.amazon.in/Hands-Machine-Learning-Scikit-Learn-TensorFlow/dp/935542198
2/ref=asc_df_9355421982/?tag=googleshopdes-21&linkCode=df0&hvadid=7098818386
84&hvpos=&hvnetw=g&hvrand=13550192749485985716&hvpone=&hvptwo=&hvqmt=&
hvdev=c&hvdvcmdl=&hvlocint=&hvlocphy=9302611&hvtargid=pla-1932407392071&psc
=1&mcid=0d3ab58ae8e0312f8272d8a4526ce7a5&gad_source=1
 12.​Stanford Online Lectures (great for learners who enjoy Math and would love to learn
every concept in-depth, can be difficult for ones who don’t have the Math prerequisites;

⭐⭐⭐⭐
in that case either stick to the Coursera courses, or go through the Mathematics for ML
course by Coursera first - links already shared above) Pixie Recommended
https://youtube.com/playlist?list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU&si=hYo6
63RsjK5K0kw4
13.​Machine Learning for Engineers - NPTEL - IIT Madras Lectures
https://youtube.com/playlist?list=PLyqSpQzTE6M-SISTunGRBRiZk7opYBf_K&si=iB9ZE
bEoHKafcGzP
14.​Deep Learning Playlist - NPTEL - IIT Madras Lectures
https://youtube.com/playlist?list=PLZ2ps__7DhBZVxMrSkTIcG6zZBDKUXCnM&si=PF9
qopTUgVEO4UpV
15.​Book - Intro to Statistical Learning, with Applications in Python (ISLP)
16.​Easy ML projects -
https://youtube.com/playlist?list=PL9ooVrP1hQOFx3U6DNqm-IwbWARdw2iEB&si=PlIm
dkgYpm968i8C

Important: Essential ML Architectures to Explore:

1.​ CNN Architectures:
○​ LeNet (Classification): Medium, Video
○​ VGGNet (Classification): Medium, Video

⭐⭐⭐⭐⭐ ⭐
○​ YOLO (Object Detection): Medium, Video
2.​ Transformers & Attention: Pixie Recommended
○​ Attention is All You Need: Paper, Medium, Video

Kaggle Competitions (Beginner-friendly): Pixie Recommended ⭐⭐⭐⭐

1.​Titanic - Machine Learning from Disaster: https://www.kaggle.com/competitions/titanic
(Excellent starting point to understand classification, missing data handling, and basic
feature engineering.)

2.​House Prices - Advanced Regression Techniques:

https://www.kaggle.com/competitions/house-prices-advanced-regression-techniques
(Great for mastering regression analysis, feature selection, and data visualization.)

Useful Resources for LLMs/Gen AI:

Author note: It’s slightly tricky in the beginning, and it’s recommended that you study the basics
of Machine Learning, Deep Learning and Computer Vision first - with a special emphasis on
Transformers and NLP including the Math portion, before diving into LLMs and Gen AI, since
you wouldn’t be able to understand it well otherwise.

1.​ LLMs: https://github.com/Hannibal046/Awesome-LLM (This repo contains all the useful

resources related to LLMs. Andrej Karpathy’s videos and Github is pretty useful and
standard too.)
2.​ Gen AI: https://youtu.be/mEsleV16qdo?si=VWkhDS5Ak5Srqeis

Changes made:
1.​ Added Pixie Recommended with stars. These are the resources which Pixie referred to
the most while learning, and the ratings are personal.
2.​ Added ML Architectures
3.​ Kaggle comps - beginner-friendly
4.​ Added resources for LLMs and Gen AI
5.​ Enhanced visuals

If you liked this content, then do make sure to leave your comments, suggestions,
reviews, repost to share your opinion, or share any additional resource(s) you would like
me to add to it. Constructive criticism will be appreciated :)
https://x.com/pixieperceptron/status/1940334359560790167

Thanks a lot for reaching here. I really appreciate your efforts towards learning and
curiosity. All the best for your goals!

Will add more content later, so save this link somewhere.

Happy Learning!
Pixie Perceptron :)