Create AI That Sees and Understands — Master Deep Learning from Scratch
Make computers smarter — train them to recognize pictures and understand what people say
Level 2
Deep Learning
Career outcome: ML Engineer, CV Engineer, NLP Engineer
Prerequisites
- Python
- Python fundamentals
- Python data structures (lists, dictionaries, sets, tuples)
- List/dictionary comprehensions and functional programming tools
- OOP principles in Python (classes, inheritance, encapsulation)
- Virtual environments (venv, conda)
- Package management
- Git (branching, merging, pull requests)
- IDE (VSCode or another IDE of your preference)
- 15-20 hours/week commitment
- Data Science Course Knowledge
If you are unfamiliar with some of these topics or want to refresh your knowledge,
these free resources linked below cover all prerequisites
these free resources linked below cover all prerequisites
If you’re a complete beginner in programming, start with one of these:
- AI Python for Beginners course by DeepLearning.AI (~10h)
- Intro to Programming and Python courses by Kaggle (~10h)
- Python tutorial by Spark Code Hub
- A Byte of Python book by Swaroop Chitlur
- learnpython.org interactive tutorial by Ron Reiter
- Python for Beginners tutorial by Beau Carnes
- Object Oriented Programming with Python tutorial by JimShapedCoding
- Intermediate Python tutorial by Patrick Loeber
- Python Virtual Environments: A Primer by Martin Breuss
- Using Python's pip to Manage Your Projects' Dependencies by Philipp Acsany
For a basic understanding, check one of these introductory resources:
- Git & GitHub Crash Course by Kalob Taulien (Udemy)
- GitHub and Git Tutorial for Beginners by Abid Ali Awan (DataCamp)
- Pro Git book by Scott Chacon and Ben Straub (check sections: Getting Started, Git Basics, Git Branching, Distributed Git, GitHub)
- Atlassian Git tutorials (check sections: Beginner, Getting started, Collaborating workflows)
Official tutorials for Visual Studio Code:
Machine Learning Path — 3 Levels to Master AI
Machine Learning is a journey with three levels:
- Level 1: Data ScienceLearn how to understand and organize data so computers can make sense of it.
- Level 2: Classical ML MasteryTeach computers to learn from data and make smart predictions.
- Level 3: LLMs & AgentsStep into the world of modern AI, where machines can think, talk, and act on their own.
Course Program
Month 1: Entering the Matrix: Neural Networks & Deep Learning Foundations
Build neural networks from scratch and unlock the power of deep learning
Building own Neural Networks and applying them to real manufacturing problems.
Fashion-MNIST Classifier - Simple PyTorch NN
■ You'll demystify deep learning by building a simple Neural Network
with PyTorch framework to classify images of clothing.
Fashion-MNIST Classifier - PyTorch CNN Upgrade
■ You'll upgrade your classifier to use Convolutional Neural Networks
(CNNs) and see performance improvements.
PCB (printed circuit board) Defect Classification
■ You'll tackle a real manufacturing problem by building a binary
■ You'll demystify deep learning by building a simple Neural Network
with PyTorch framework to classify images of clothing.
Fashion-MNIST Classifier - PyTorch CNN Upgrade
■ You'll upgrade your classifier to use Convolutional Neural Networks
(CNNs) and see performance improvements.
PCB (printed circuit board) Defect Classification
■ You'll tackle a real manufacturing problem by building a binary
- classifier to detect defective vs normal PCBs.
Neural Network Fundamentals, Multi-Layer Perceptron (MLP),
Backpropagation, NumPy, PyTorch, Convolutional Neural Networks (CNNs), Transfer Learning.
Backpropagation, NumPy, PyTorch, Convolutional Neural Networks (CNNs), Transfer Learning.
Month 2: Where's Waldo? - Computer Vision Mastery
Master the complete computer vision pipeline
Training a high-performance object detector on your custom-labeled dataset and tackling a real-world medical image segmentation challenge.
PCB (printed circuit board) Defect Detection
■ You'll create your dataset by labeling PCB defects with bounding
boxes using CVAT, experiencing professional annotation workflows.
■ You'll train a YOLO model to localize and classify different defect types on your custom dataset.
Medical Image Segmentation
■ You'll work on pixel-level computer vision by setting up and training a U-Net model for medical image segmentation.
■ You'll create your dataset by labeling PCB defects with bounding
boxes using CVAT, experiencing professional annotation workflows.
■ You'll train a YOLO model to localize and classify different defect types on your custom dataset.
Medical Image Segmentation
■ You'll work on pixel-level computer vision by setting up and training a U-Net model for medical image segmentation.
Data Annotation, CVAT, Object Detection, YOLO Architecture, Image
Segmentation, U-Net Architecture.
Segmentation, U-Net Architecture.
Month 3: Understanding Human Language
Bridge the gap between human language and AI understanding
Diving deep into modern NLP (Natural Language Processing) with
Transformer architectures.
Transformer architectures.
Comment Toxicity Detector
You'll build a system to moderate online discussions by fine-tuning a
Transformer to detect toxic comments.
You'll build a system to moderate online discussions by fine-tuning a
Transformer to detect toxic comments.
Natural Language Processing (NLP), Tokenization, Word Embeddings,
Attention Mechanisms, Transformer Architecture, Hugging Face.
Attention Mechanisms, Transformer Architecture, Hugging Face.
🗓️ Month 1: Tabular Data Mastery & Foundations
- Focus: Mastering the data science toolkit, EDA, and core regression models.
- Project: House Prices - Advanced Regression Techniques
- You'll build models to predict home values, mastering feature engineering and regression on a complex, real-world Kaggle dataset.
- (Skills: EDA, Feature Engineering, Regression Models, XGBoost, Kaggle Competitions)
Main Project Goal: Build the v0.1 command-line version with simple, rule-based responses.
Our YouTube Channel
Learn from the Experts
250+
videos
30k+
subscribers
2+ mln
views
We believe in sharing knowledge, so on our channel, you'll find:
Student success stories
Tutorials and useful materials for aspiring QA engineers
Tips on interviews and job opportunities in the QA field
With over 1 million views, our channel has become a trusted resource for learning and growth in the QA industry.
Student Success Stories
Nothing speaks louder than real success stories. Our students come from different backgrounds, but they all have one thing in common — they successfully transitioned into QA careers after completing our program.
Reviews on Google
4.9
124 reviews
Our students work at
100% Money-Back Guarantee
If the course isn’t right for you, we offer a full refund within 14 days after the course starts.
4527 w 142 st, Hawthorne, CA, 90250
© 2025 Codemify. All rights reserved.
