1. Trace a neuron and its loss
TASK: Write the logit and sigmoid for two features. Explain what changes when the bias increases and what the loss measures.
Your method:
Your evidence/result:
Limitations and next action:


2. Derive and check a gradient
TASK: Run the gradient lab and compare analytic_gradient with finite_difference_gradient. Predict the direction of the loss change for a sufficiently small step.
Your method:
Your evidence/result:
Limitations and next action:


3. Separate optimization from generalisation
TASK: Write an experiment plan with partitions, a learning-rate candidate rule and a final-test boundary. Name a sign of overfitting.
Your method:
Your evidence/result:
Limitations and next action: