Backprop, with the maths
Describe neurons, activation functions and the mathematics of backpropagation precisely enough to answer the follow-ups.






























A twelve-hour interview course built around how networks train: neurons, activation functions and the mathematics of backpropagation, then the optimizers SGD, RMSProp, Adam and AdamW and the gradient problems they address.
Regularization gets two modules: dropout, L1 and L2, batch and layer normalization, then weight decay and the curse of dimensionality. It ends by pulling the material together and practising question-and-answer tactics.
Describe neurons, activation functions and the mathematics of backpropagation precisely enough to answer the follow-ups.
Compare SGD, RMSProp, Adam and AdamW, and use them to deal with vanishing and exploding gradients.
Apply dropout, L1 and L2 penalties, and batch and layer normalization to curb overfitting and steady training.
Analyze why a model fails, choose fixes such as weight decay and dropout, and explain the curse of dimensionality.
The core concepts of deep learning and the essentials of neural networks, as the base for the questions that follow.
Neurons, activation functions and the mathematics of backpropagation, explained precisely enough to answer in an interview.
A comparison of SGD, RMSProp, Adam and AdamW, and how they deal with gradient problems such as vanishing and exploding gradients.
Dropout, L1 and L2 regularization, and batch and layer normalization, used to prevent overfitting and stabilize training.
Analyze why models fail, apply weight decay and dropout, and work through tactics for the curse of dimensionality.
Pull the course together and practise question-and-answer tactics for a demanding interview.

Instructor · LUNARTECH
Vahe Aslanyan is the CTO of LUNARTECH, and has helped hundreds of developers make sense of complex AI and data science and build better software with it.
Start from neurons and activations, then step through the mathematics of backpropagation.
Set SGD, RMSProp, Adam and AdamW side by side, and see which gradient problems each answers.
Use dropout, L1 and L2, normalization and weight decay, then practise explaining each choice.
Before you start
A 3-day free trial opens a selection of the content. Your card is only charged once it ends.
While you learn
Stuck on a concept? Reach out to a mentor whenever you need help.
While you learn
On the yearly plan, one-on-one sessions give you dedicated support.
Any time
Write to info@lunartech.ai at any point, from your trial onwards. If your employer is funding you, we’ll set it up with them directly.
All the way through
After the last lesson
Your alumni network stays with you: ongoing support, opportunities and industry insight.
Tailored coaching helps you decide where to aim and how to get there.
Hands-on projects become work you can show, not just claim.
Personalized refinement, so what you send says what you can actually do.
Preparation for the questions that decide it, so you walk in ready.
Connections with industry leaders, and an alumni network that stays with you.
LUNARTECH Academy has been the most empowering learning experience of my life, giving me a clear, structured path from the absolute basics to building real-world AI systems with confidence.
Your page is fantastic. As a bachelor’s student in Data Science now accepted for a master’s at UConn, your work has been a real source of motivation.
The programme’s clear, bite-sized content and practical projects dramatically improved my speed from fuzzy idea to MVP and my ability to communicate AI value. I followed the system, and it works.
I really appreciate your teaching style and the way you break down complex topics. It has been incredibly helpful.
After years working mainly with R for econometrics, I found your Python machine learning course a refreshing and engaging way to learn Python.
As a Data Science graduate, I want to thank you for the effort you put into making videos to support growing data scientists.
I’ve been following your work since taking your machine learning course, and I’m impressed by your practical approach to applying AI.
One standard behind every course, from the first lesson to long after the last.
Apply every idea to real problems, so it becomes something you have used, not only seen.
We keep courses current with the tools, techniques and skills the field asks for.
Study at your own pace, from anywhere, at any hour.
Finish the course and earn a certificate that shows what you have learned.
Personalized learning plans and support structures carry you through the hard parts.
Stay connected after you finish, with ongoing support, opportunities and industry insight.
Finish the course and it is issued in your name, under our signature. There is no other way to get one.
Certificate of completion
One membership opens every course, certification, workshop and masterclass in the Academy. Every plan starts with a 3-day free trial.
3 days free, then $29.97 a month. Your card is only charged once the trial ends.
Included in every plan
Every role uses all six modules. Here’s where each one leans hardest, and where its work ends up.
Picks the optimizer and fixes a loss that won’t fall. Adds regularization when a model overfits.
Optimizers, Regularization, Overfitting
Machine learning teams
Works through the mathematics of backpropagation. Compares optimizers on how they treat gradients.
Backprop, Optimizers
Research labs
Stabilizes training with batch normalization. Guards image models against overfitting.
Regularization, Overfitting
Computer vision
Uses layer normalization in sequence models. Handles exploding gradients in deep text models.
Regularization, Optimizers
Language technology
Picks the optimizer and fixes a loss that won’t fall. Adds regularization when a model overfits.
Over 10,000 students trust LUNARTECH
Understand systems all the way down. Build the ones others rely on.
Understand what the data says. Build models that hold up.
Understand the papers. Build on them, and take the work further.
+340%growth in open roles requiring AI skills
Open roles: Built In, Greenhouse, LinkedIn.
Typical salaries: Glassdoor, Levels.fyi, Payscale, Indeed, Ravio, JobRise, U.S. BLS. Military: 2026 U.S. basic pay, drone officers with aviation incentive pay.
Updated November 2026.
Need help? These answers cover most of what people ask before they start.
SGD, RMSProp, Adam and AdamW, with a focus on how they handle vanishing and exploding gradients.
Our 3-day free trial gives you access to a selection of content in the bootcamps, courses and materials, so you can experience the value of our content first-hand. This includes comprehensive learning materials and interactive sessions. You won’t be charged during this period, though we require your credit card details at the start to ensure a seamless transition should you choose to continue.
Yes, entering your credit card details is a necessary step to begin your free trial. The process is entirely secure, and we ask for it to provide a seamless transition to a paid subscription if you decide to continue beyond the trial. You will only be charged after the trial period ends, with full access to our content based on the plan you choose.
After your 3-day free trial you gain access to the full breadth of our content, depending on the subscription plan you choose. We offer free trials for our monthly, bi-annual and annual plans, and each plan provides a different scope of access and benefits.
If your employer has agreed to fund your learning, in part or in full, please contact us at info@lunartech.ai. We’ll work with you and your employer to set up everything needed for your subscription.
Yes. Our support remains strong both during your free trial and after you subscribe. Reach the team at info@lunartech.ai with any question, whether you’re onboarding, navigating your trial, or need help as a member. Subscribers to the yearly plan also receive dedicated support in one-on-one sessions.
You can upgrade your plan at any time during your subscription. Downgrading is not available for bi-annual or annual plans, but you can cancel and then choose a new plan that suits you better. For bi-annual and annual plans we also offer payment in instalments; please reach out to learn more.
Twelve hours on backpropagation, optimizers and regularization, then practice answering questions on them. Begin with a free lesson, or enroll in the full course.