# COMP 150-01 Machine Learning for Ecology and Sustainability

## Instructor

## Class times and location

M 1:30-2:45, Collaborative Learning and Innovation Complex 204

## Office hours:

T 4:00 - 5:00, F 3:00 - 4:00

## Syllabus & Notes

The syllabus and notes of the course.

## Description & Objective:

Data analysis provides important scientific support for environmental protection and sustainability. At the same time, ecological data also pose interesting problems for machine learning.

This course will focus on machine learning methods for data analysis problems arising from ecological study. We will cover the following topics: data collection and interpretation with learning system, species distribution modeling, trajectory modeling, and capture-recapture model. In this course, we will mainly read papers from related fields after a short tutorial of machine learning.

At the end of the course, a successful student should be able to understand the machine learning techniques discussed in the course and identify possible learning techniques when solving a data analysis problem.

## Prerequisites:

One of MATH 0162 (Statistics), COMP 135 (Introduction to Machine Learning), or COMP 136 (Statistical Pattern Recognition), or the permission of the instructor.

## Expectation:

We will start with a tutorial of related machine learning models, and then we will read papers of one topic – usually 2 papers – per week. On each topic, I will give a short tutorial of techniques in the papers and then lead the discussion of the paper. The detailed schedule is

listed below.

The student is required to write summaries of five topics. The summary is due before the class one week after the topic discussion. For example, if the second discussion of a topic happens on Oct 23, then the due time of the summary is on Oct 30 before the class.

The students will work on course projects during the course. At most three students can form a team to work on one project. In the project, the students are encouraged to work on a problem that is not studied in the literature. The project proposal is due on Oct 16.

The presentation is on the day of final exam (12/15/2017, 12pm - 1pm). The project report is due on Dec 15.

## Grading Policy:

discussion participation (10%), summaries (20%), project proposal (10%), project report (50%), project presentation (10%). The project is graded based on the workload and final results.

## Detailed Schedule and Bibliography:

Here is our schedule, and here is a full list of papers.

## Policy for Late Submissions:

Unless specified otherwise, the due time is 5pm on the due date. If your submission is one day late, you will get 50% of the credits you normally get. If your submission is two days late, the percentage is 25%. You will get no credit for a submission two days after the due time. In case of documented illness or family emergency, the due date can be postponed accordingly at the request of the student.

## Academic Integrity Policy:

This course will strictly follow the Academic Integrity Policy of Tufts University. Students are expected finish their course work independently, and their work should truthfully represent the time and effort applied. Please refer to the Academic Integrity Policy at

https://students.tufts.edu/student-affairs/student-life-policies/academic-integrity-policy

## Accessibility:

Tufts and the instructor of COMP 150-1 in Fall 2017 strive to create a learning environment that is welcoming students of all backgrounds. Please see the detailed accessibility policy at

\noindent https://students.tufts.edu/student-accessibility-services .