- 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 Forward Pass & Loss Functions Quiz
This quiz follows a batch of data through a neural network layer and into the loss. You will work out shapes and parameter counts, compute softmax and cross-entropy with small numbers and choose the right loss for the task.
Sample question
Question 1 of 10A dense layer takes 4 inputs and has 3 neurons. How many trainable parameters does it have?
Show the answer
C. 15 Each of the 3 neurons has 4 weights and 1 bias: 4 * 3 + 3 = 15. 12 forgets the biases.
What this quiz covers
- Shapes in a dense layer
X @ W + b - Counting weights and biases
- Softmax, logits and numerical stability
- Cross-entropy and binary cross-entropy by hand
- Averaging the loss over a batch
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.