GNR 652 - Machine Learning for Remote Sensing

 

Spring 2020

Prof. Biplab Banerjee

Author: Nakul Randad

Pre-requisite courses: None

Pre-requisite skills: Basic programming proficiency in Python/Julia saves the struggle during assignments. The following prerequisites were preferable but not mandatory: Linear Algebra, Basic Multivariable Calculus and Probability.

Course Content:

  1. Regression
  2. Classification
  3. Clustering
  4. Probabilistic methods
  5. SVMs
  6. Dimensionality Reduction
  7. Selected topics in Neural Networks (CNN, RNN etc)

Motivation to take up the course: This course gives a basic introduction to Machine Learning which includes Supervised-Unsupervised Learning, Feature Recognition, Dimensionality Reduction, Neural Networks etc.


Information about Projects/Assignments:

Coding Assignments (Individual): Application of known algorithms covered in lectures. They were fairly straight forward and took around 4-5 hours to complete. These assignments helped in understanding the implementation of the theory taught in class.

Course Project (Group): Students were required to implement a research paper of their choice and demonstrate the results in the final presentation.

Quizzes/Midsem/Endsem papers Difficulty: 3/5

Overall Course Difficulty: Moderate

Average Time Commitment: (Apart from lectures and tutorials) Between 3-6 hrs

Attendance Policy: 75% attendance was mandatory, below which there was some penalty


General funda: Going through the slides and practising a few problems suffices for the exams. Exams are more of understanding based with a bit of maths here and there

Grading stats: Check ASC.

Professor’s Teaching Style: The professor taught all theory in class with the help of slides. The pace of the lectures was quite slow, hence they were easy to follow and understand. A few tutorials were arranged wherein TAs explained the actual code implementing algorithms.

Should you do this course?: If you are interested in doing ML or wish to have a sneek-peek at it then this course is a good place to start. If you have already taken any other ML introductory course then I won’t recommend you take this course as you won’t learn anything new.