Curriculum • 5 Units • ~24 min aggregate runtime • Self-Paced with Marginalia

Learning Artificial Neural Networks — From First Principles

Understand how artificial neural networks work from the ground up — starting with the mathematics and building toward implementing your own neural network.

Tuition / Access Terms
₹ 399 One-time Settlement
Direct peer-to-peer UPI transfer • Zero tracking • Lifetime access
What Is Included
  • • Signed 1080p video lectures with dedicated playback
  • • Comprehensive technical marginalia & code proofs
  • • Interactive concept verification checkpoints

Course Overview & Thesis

Learning Artificial Neural Networks — From First Principles

I'm not here to teach you how to use AI. I want to understand how it works. And I want to build it.

There's something interesting about neural networks.

We can use libraries, write a few lines of code, train a model, and get an output. But how much do we actually understand about what's happening underneath?

What is a neuron doing? Why does it need weights and biases? How does a network learn from its mistakes? And how do mathematical operations eventually become something that can learn patterns from data?

These are the kinds of questions I want to explore through MADE FOR NOTHING.

I'm learning AI by going back to the fundamentals, understanding the ideas behind the code, experimenting with them, and trying to build things myself. As I learn, I want to document what I discover and share it with others who are curious about the same things.

That's what this course is: a step-by-step journey into artificial neural networks, starting from the basics and working toward building one ourselves.

So, where do we start?

Not with a complicated model. Not with a framework that does everything for us.

We start with the things we need to understand.

We'll explore the mathematics behind neural networks, including functions and derivatives. Then we'll use those ideas to understand what an artificial neuron actually calculates.

From there, we'll gradually work toward the bigger picture:

  • How neurons use inputs, weights, and biases.
  • What activation functions do.
  • How information moves through a network.
  • How a neural network measures its errors.
  • How derivatives and gradients help us understand changes.
  • How gradient descent and backpropagation help a network learn.
  • How to connect the mathematics to code and build a neural network from scratch.

Some ideas will be simple. Others will take more time to understand. That's fine. I'd rather understand one concept properly than rush through ten concepts and remember none of them.

The mathematics isn't here just to make the course look technical. It's here because it helps us understand what the network is actually doing.

What I want you to get out of this

I don't want you to finish this course having memorized a collection of formulas.

I want you to start looking at a neural network differently.

When you see an equation, I want you to have an idea of what it represents. When you see a piece of code, I want you to understand the operation behind it. And when something doesn't work as expected, I want you to have enough understanding to investigate why.

Eventually, the goal is to build a neural network ourselves—not as a magic box that happens to produce an output, but as something we can reason about, piece by piece.

And perhaps, along the way, understanding how these systems learn will also make you think differently about learning itself.

Who is this for?

Curious people. That's it.

You don't need a fancy title. You don't need to be a computer science student. You don't need to be someone who already knows everything about mathematics or AI.

Maybe you've used AI tools and wondered what makes them work. Maybe you've seen neural network code but never understood what was happening behind it. Maybe you simply enjoy taking things apart, understanding how they work, and putting them back together.

If you want to go beyond using AI and start understanding how it works, you'll probably find something worthwhile here.

You don't have to know everything before you start. You just have to be willing to learn.

Why is there a price?

The course costs ₹399 as a one-time payment.

Putting this together takes time: working through concepts, preparing explanations, producing videos, writing notes, and maintaining the platform where everything lives.

The price helps support that work. I'm not asking you to pay because I claim to know everything. I'm asking you to pay for the material I've put together and the effort involved in making it available.

If you're curious about neural networks and want to explore them from the ground up, you're welcome to join me.

Let's stop treating neural networks as black boxes. Let's open one up and understand what's inside.

— MADE FOR NOTHING

Read. Experiment. Research. Build. Explain.

Theoretical & Engineering Mastery

  • The mathematics we need to understand neural networks.
  • What functions are and why they matter.
  • What derivatives actually mean, beyond a formula.
  • Why understanding change becomes important when a neural network learns.
  • What an artificial neuron does with an input.
  • How weights and biases affect a neuron's calculation.
  • What activation functions contribute.
  • How information travels through a neural network.
  • How forward propagation turns inputs into calculated values.
  • How a network measures the difference between a prediction and the target.
  • What gradients tell us about changing a network's parameters.
  • How gradient descent helps improve a network.
  • What backpropagation does and why it matters.
  • How the different pieces fit together during training.
  • How mathematics translates into actual code.
  • How to work toward building a neural network from scratch.
  • How to investigate what's happening inside a model instead of blindly trusting the output.

The bigger goal: To understand the ideas well enough that you're not just following instructions. You're beginning to reason about neural networks for yourself.

Note: These are the topics the course is intended to work toward. The currently published curriculum contains the first three introductory lessons, and not every topic listed above is available yet.

Target Audience & Prerequisites

Who is this for?

Curious ones. Simple as that.

People who don't just want to use something, but want to understand how it works.

People who see a neural network and wonder what's happening inside it.

People who are willing to ask basic questions, work through unfamiliar mathematics, make mistakes, and try again.

You don't need to be an expert before you start. You don't need a certificate at the end to make the learning worthwhile.

You just need curiosity and a willingness to explore.

If that sounds like you, you're in the right place.

Curriculum Architecture & Syllabus

Structured sequential lectures with dedicated video, proofs, and verification checkpoints.

5 Structured Units
01

Math Foundations for Neural Networks

2m runtime

Build the basic mathematical foundation needed to understand neural networks. This lesson introduces the essential ideas of variables, constants, expressions, equations, functions, graphs, and mathematical notation that we will use throughout the course.

🔒 Enroll
02

Derivatives — Understanding How Things Change

2m runtime

Build an intuitive and mathematical understanding of derivatives. Learn what a derivative actually represents, how it measures the rate of change of a function, how slopes and tangent lines connect to derivatives, and why derivatives become essential for understanding how neural networks learn.

🔒 Enroll
03

Feedforward — How a Single Neuron Calculates an Output

7m runtime

Understand how information moves through a single artificial neuron. Learn why we use algebra, how inputs are multiplied by weights, how bias is added, and how to calculate the neuron's output step by step.

🔒 Enroll
04

Feedforward Neural Networks — Multiple Neurons

4m runtime

Learn how a neural network works when it contains multiple neurons. Understand how each neuron calculates its value using weights, biases, and inputs, and how these calculations combine to produce the network's output.

🔒 Enroll
05

Loss and Weight Updates — Training a Single Neuron

7m runtime

Learn how to measure the error of a single neuron's prediction using a loss function, and how to update its weight to improve the prediction. This introduces the basic idea behind training a neural network.

🔒 Enroll

Frequently Addressed Inquiries

8 Common Questions
1. Is this a course about using AI tools?

Not really. This course is about understanding artificial neural networks and how they work underneath the tools we use. Rather than focusing on how to use an existing AI product, we'll explore the mathematics, calculations, and ideas behind neural networks, with the goal of eventually building one ourselves.

2. Do I need to know advanced mathematics?

No advanced background is assumed, but we will work with mathematics. We'll start with the foundations we need and introduce concepts when they become useful. Some topics, especially derivatives and gradients, take time to understand, so you'll need some patience and a willingness to work through them. The goal isn't to avoid mathematics. It's to understand why we're using it.

3. Do I need programming experience?

Programming will become important as we connect the concepts to implementation. The course is being developed progressively, starting with the underlying ideas before moving further into building a neural network. If you're completely new to programming, you may need to learn some basic coding alongside the course as the practical material develops.

4. Will I build a neural network from scratch?

That's the goal of the broader course journey. We'll work from the basic calculations of a single neuron toward understanding how the pieces of a network fit together, learn, and get implemented in code. To be clear, the currently published curriculum contains three introductory lessons. A complete from-scratch implementation is part of the intended progression, not something these three lessons alone deliver.

5. Why are we learning mathematics instead of jumping straight into code?

Because I want to understand what the code is doing. If a line of code calculates a weighted sum, I want to know what that sum represents. If a network changes its parameters, I want to understand why. And if derivatives help us understand those changes, I want to know how they work. The mathematics is a way to see inside the black box—not a hurdle we have to get out of the way.

6. Why should I pay if you're learning too?

That's a fair question. You're not paying for a claim that I know everything. You're paying for the lessons, explanations, notes, production, and platform I've put together to make the learning process more structured and accessible. Explaining something clearly takes work. So does producing the material and maintaining the place where it's available. The idea is to share that work with others who want to explore these concepts too.

7. How much does the course cost?

The current one-time price is **₹399**. There is no recurring course subscription. Check the enrollment page for the current payment and access terms.

8. Will I receive a certificate?

The focus here is on understanding and building, not collecting certificates. The purpose of the course is to help you develop an understanding of neural networks and work toward implementing one yourself. Please enroll for the learning experience, not for a credential.

Instructor & Research Ethos

A little about who's putting this together

I'm learning AI, just like many of you might be.

I don't want to learn by memorizing formulas, copying code, and hoping everything works. I want to understand the ideas behind what I'm building.

So I read, experiment, research, write code, make mistakes, and try to explain what I've learned.

Eventually, I realized I wanted a place to put all of this work together. Somewhere I could document what I'm learning, build projects around it, and share the process with people who are curious about the same things.

That's how MADE FOR NOTHING fits into this journey.

Read → Experiment → Research → Build → Explain

This course follows that same approach.

We start with the fundamentals because I want to understand the building blocks before relying on tools that hide them. We explore mathematics when it helps explain a concept. We connect the theory to code instead of leaving it on a page.

I'm not claiming to have all the answers. I'm building my understanding, and this course is part of that work.

One thing I believe: if you want to understand something deeply, try building it yourself. And try explaining it to someone else.

That's what I'm trying to do here.

A note about the curriculum: This is an ongoing learning project. The three published lessons are the beginning of a larger journey, not a claim that the entire roadmap has already been completed. I'll keep the distinction between what's available and what I'm working toward clear.

If you're learning too, I hope this gives you a useful place to start—or another way to look at something you've been trying to understand.

Laboratory Curriculum

Learning Artificial Neural Networks — From First Principles

Immediate lifetime access to all 5 lecture units, marginalia proofs, and conceptual checkpoints. Zero third-party trackers.