---
title: SCMA30019 - Week 2 AS
tags: SCMA30019
GA: G-77TT93X4N1
---

# Week 2 Assignment

- **Due:** September 17 at 10:10 AM
- **Submission:** Please submit your work to your GitHub repository under the folder `week_2`.
- **Format:** You may use any format you prefer (PDF, JPG, or MD). However, if you upload a photo, please make sure it is clear and readable.
- **Policy Reminder:** Be mindful of our grading policy, especially regarding Academic Integrity and the Use of Tools. 👉 Refer to the course syllabus for details.

---

## ✍️ Written assignment

1. Read [Deep Learning: An Introduction for Applied Mathematicians](https://epubs.siam.org/doi/10.1137/18M1165748). Consider a network as defined in (3.1) and (3.2). Assume that $n_L=1$, find an algorithm to calculate $\nabla a^{[L]}(x)$.

2. There are unanswered questions during the lecture, and there are likely more questions we haven't covered. Take a moment to think about them and write them down here.

## 👨🏻‍💻 Programming assignment

1. Use a neural network to approximate the Runge function
$$
f(x) = \frac{1}{1+25x^2}, \quad x\in[-1, 1].
$$
Write a short report (1–2 pages) explaining method, results, and discussion including
* Plot the true function and the neural network prediction together.
* Show the training/validation loss curves.
* Compute and report errors (MSE or max error).