Practice Labs: Deep Learning Interviews (Kashani)
Source PDF: 2201.00650v2.pdf Book: Deep Learning Interviews by Shlomo Kashani (2nd Edition)
This book covers mathematical foundations and interview-style problems for deep learning. Labs below are organized by the book’s progressive difficulty levels.
Use this folder as a compact practice layer when you want to sharpen deep-learning intuition quickly. It works well as reinforcement for interviews, revision, or a short math-to-implementation bridge.
Labs
| Lab | Topic | Book Chapter | Difficulty |
|---|---|---|---|
| Lab 01 | Logistic Regression from Scratch | Part II: Logistic Regression | Kindergarten |
| Lab 02 | Information Theory & Entropy | Part III: Information Theory | High School |
| Lab 03 | Calculus, Gradients & Backpropagation | Part III: Calculus, Algorithmic Differentiation | High School |
| Lab 04 | Probability & Bayesian Deep Learning | Part II: Probabilistic Programming & Bayesian DL | Kindergarten |
| Lab 05 | Neural Network Ensembles | Part IV: NN Ensembles | Bachelors |
| Lab 06 | CNN Feature Extraction & Deep Learning | Part IV: CNN Feature Extraction + Deep Learning | Bachelors |
How to Use
- Each lab is a Jupyter notebook with theory (markdown) and fully implemented code cells
- Read the theory cells, study the implementations, and run each cell
- Open in Jupyter:
jupyter notebook lab_01_logistic_regression.ipynb
Prerequisites
- Python 3.8+
- NumPy
- Matplotlib
- SciPy (for Lab 04)
Suggested Order
- Lab 01 - Logistic Regression (foundational)
- Lab 04 - Probability & Bayesian DL (builds on probability basics)
- Lab 02 - Information Theory (entropy, KL divergence)
- Lab 03 - Calculus & Backpropagation (core for training NNs)
- Lab 06 - CNN Feature Extraction (applies NN concepts)
- Lab 05 - Ensemble Methods (advanced techniques)
How To Use This Folder Well
- Treat these labs as short, focused reinforcement rather than a full standalone curriculum.
- Use them when you want to turn abstract neural-network math into concrete coding exercises.
- Revisit the relevant foundational or neural-network phases whenever a lab exposes a deeper gap.
What Comes Next
- Continue to ../foundational/README.md if you need broader math support.
- Continue to ../../06-neural-networks/README.md if you want the main deep-learning phase.
- Continue to ../../24-advanced-deep-learning/README.md if these labs confirm you want deeper theory.
Last updated on