Syllabus
============================


## Course Description

The course "Hands-on Artificial Intelligence (AI) for Physics" is a project-based upper division course aimed to provide practical  skills to perform research with neural networks.
We will survey the fundamentals of learning in Artificial Neural Networks (ANN) and describe the underlying principles making neural networks generic computing frameworks. We will then build computational skills for training different types of neural networks, such as Convolutional networks, Recurrent Neural Network, Generative Neural Network. 
Students will learn how to apply the state-of-the-art AI and data science tools on cutting-edge research problems in interdisciplinary fields in physics including particle physics, condensed matter physics and astronomy.


## Classroom Format

* Experience-based learning: 
  * Work out a set of in-class exercise during lectures

* Post-lecture `Lab`:
  * Carry out hands-on assignments (homework)

* Final project
  * Apply machine learning techniques on data provided by instructors

* For in-class exercise and labs: work in groups of three assigned by instructors; rotate every week.
  * Submit one homework for three people


* For final project: find your own teammate (2 people/team). 
  * At least two teams will be working on the same project
  * A kaggle competition will be setup for each project
  * An oral presentation (in English) for each team. Both members have to speak.

<!-- This is an evidence-based learning course. Students are expected to study recorded lecture videos and answer on-line quizzes before coming to the class. Students will work out a set of in-class quizzes during lecture time to enhance their understanding of course materials. Students need to carry out hands-on assignments in the Software lab guided by teaching assistants. Finally, each student needs to carry out a final project by using their own research data or open data provided by the instructor.
 -->

## Logistics

* Course: 11120PHYS591000, National Tsing hua University
* Lecture Time:  10:10-11:00 Thu
* In-class exercise/Lab Time: 11:10-13:00 Thu
* Location: Phys Building Room 208
* Total People: 24
* Credit: 3 credits, graded


## Requirements
* Basic Computer Science and Programming Skills (Python preferred)
* Linear Algebra
* Basic Machine Learning and Statistical concepts (optional)


## Grading 

* Class Participation - 10%
* Lab/Homework - 60%
  * 10-12 sets of assignments
  * Due: Noon on Saturdays (No late submissions)
* Final Project - 30%
  * Oral presentation: 15%
  * Final project results: 15%

* ```Note: 10 points (10% of final grades) off for absence without permission for the following events```
  * Final project discussions (Week 16 05/31)
  * Final project oral presentations (Week 17 06/07)

<!-- ## Project

Two people will be teammed up to work on a project.
The bulk of the first half of the project will focus on the task of feature explorations.
The latter-half of the project will introduce you to further topics to inform possible avenues for further research.

The written report can be produced in a 4-page 2-column Physical Review Letters (PRL) format. 
The LaTeX package (RevTeX) can be found here: <https://journals.aps.org/revtex>
More information can be found here: <https://journals.aps.org/prl/authors>

 -->



<!-- ## Section Participation

Participation in the weekly discussion section is *mandatory*. 
Each week, you are responsible for doing the reading/task assigned in the [schedule](schedule.md). 
Come to section prepared to ask questions about and discuss the results of these tasks.

Each week, turn in answers to the weekly questions to Kaggle. 
These questions are meant to focus your work for the week and help prepare you for discussion. 
If you have questions about your work, please ask them in section or office hours.

You are responsible for the entire weekly reading/task, even if portions are not covered in the weekly questions.
The weekly tasks are the building blocks for the project proposals/assignments due at the end of the quarter. -->