Solution: Forward Pass for a Tiny Network
Exercise: Forward Pass for a Tiny Network
Solution
z1 has shape (5,4), h has shape (5,4), and y_hat has shape (5,1). Matrix dimensions are the quickest neural-network sanity check.Takeaways
- State the assumption that makes the method valid before trusting the result.
- Connect the computation back to the finance workflow, not only to the code.
- Check whether the result depends on average-case behaviour, validation design, or numerical safeguards.