IITM MLT Week 12 Questions
Neural Networks and Loss Functions
Week 12 question PDF
Practice evaluating neural network outputs from stated weights, biases and activations. The collection also includes graphical loss-function questions and numerical exercises on network calculations.
The complete question statements, options, numerical data and any supporting graphs or tables are in the PDF. Numbered comprehension questions can include several subquestions. Answer keys are included for checking your attempt; these are not full worked solutions.
Topics covered in this collection
- Neural network layers, weights and biases
- Sigmoid and linear activations
- Forward propagation
- Classification losses and convex surrogates
How to approach these questions
- Compute the weighted sum and bias first, then apply the specified activation function.
- Carry sufficient precision through hidden-layer calculations before rounding the requested output.
- Use the labels and axes of loss-function plots when identifying the corresponding loss.
Attempt the questions using the assumptions and notation stated in each problem. For short-answer questions, round only at the final step to the requested precision. Check the provided key after solving and revisit the relevant concept when an answer differs.