- Executors
-
Learn
Learn Python Runnable examples, NumPy, pandas, and more Learn AI / Machine LearningNeural networks, ML and LLMs from scratch Learn C & C++ Pointers, memory, STL, and modern C++ Learn C#C# basics, OOP, LINQ, async, and .NET exercises Learn MatplotlibLine, bar, scatter and pie charts with live visualizers Learn RustOwnership, traits, error handling, and threads Learn GoSlices, interfaces, goroutines, and channels Python Algorithms Search, sorting, recursion, and visualizers O(n) C & C++ Algorithms Compare algorithms implemented in C and C++ Coding for Kids Learn to code by playing!
- QuizzesNew
- ChallengesNew
- For TeachersNew
- Updates
- Buy me a coffee
AI & Machine Learning Training Deep Networks Quiz
This hard quiz is about what actually goes wrong when you train deep networks and how to fix it. It covers learning rates, dropout, batch normalization, vanishing and exploding gradients and early stopping, using situations you will meet in practice and in interviews.
Sample question
Question 1 of 10Training loss keeps falling, but validation loss reaches its lowest point at epoch 12 and rises after that. What is happening and what is a sensible response?
Show the answer
C. Overfitting; keep the weights from epoch 12 (early stopping) or add regularization After epoch 12 the model memorises the training data instead of learning patterns that generalise. Early stopping keeps the best validation checkpoint; dropout, weight decay or more data also help.
What this quiz covers
- Spotting overfitting and stopping early
- Dropout and batch norm at training vs inference time
- Vanishing and exploding gradients, clipping and their fixes
- Learning rate choice and schedules
- Weight decay and other regularization
Questions people ask
Do I need an account?
No. Anyone can play. Sign in to keep your XP, streak, badges and history.
Can I retake it?
Yes. Your best score is kept, and the questions and answers are shuffled each time.