# Project - Kyoto, baby

### AI-assisted learning for neural networks.

### Team Members:
- Karo
- Isna
- Stergios

### Core idea: 

Learning goals: 

Students will be able to implement neural network concepts. 

Research question:

- How AI-assisted interactive visualisation of neural networks improve student learning performance?

- Would learning platform with AI feedback and instructions enhance stduent learning performance?

Task Analysis:

https://playground.tensorflow.org/ clone with specific targets.

- Experimental Group (A): Users get AI assistance for the first 10 examples (clipy style), then they have 5 test cases without AI.

- Control Group (B): Users get 10 test examples they need to optimise for, with generic rules of how different parameters affect performance, then 5 test cases

Recruitment plan: 

- Master's student (Michalis's) — **Approved / Good to go**

- Master EPFL student (Mauro's)  ---> pending

We record (everything, but we focus on):

- Performance on the 5 test questions (complexity vs performance) and speed

- Engagement between clicks

- Performance on the NN assignment (post-intervention performance) — *Michalis approved*

- Self-assessment survey: AI literacy, Intrinsic motivation

### Next Meeting:
- **Date & Time:** Monday, September 28, 2026 at 11:00
- **Location:** Stergios's office