MICRO-573 / 3 credits

Teacher: Psaltis Demetri

Language: English

Withdrawal: It is not allowed to withdraw from this subject after the registration deadline.


Summary

This course will focus on the practical implementation of artificial neural networks (ANN) using the open-source TensorFlow machine learning library developed by Google for Python.

Content

After a brief introduction to deep neural networks, the course will focus on the use and functionality of TensorFlow, and how it can be used to build models of different complexity for different types of optical imaging applications. Models will range from simple linear regression to convolutional neural networks (CNN)  for image classification and mapping. The course will be assessed through coursework and group projects where the students will apply TensorFlow  to specific machine learning applications.

Keywords

Deep learning, TensorFlow, Artificial neural networks, Imaging

Learning Prerequisites

Required courses

Proficiency in Python, basic optics

Recommended courses

MICRO-421 Imaging Optics

Important concepts to start the course

Python familiarity, linear systems, basic optics

Learning Outcomes

By the end of the course, the student must be able to:

  • Implement
  • Choose
  • Demonstrate
  • Apply

Teaching methods

2 hours/week  lecture

1 hour/week interactive artificial neural network develoment for selected problems

 

Resources

Websites

Moodle Link

In the programs

  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Deep learning for optical imaging
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 1 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Deep learning for optical imaging
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 1 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Deep learning for optical imaging
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 1 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Deep learning for optical imaging
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 1 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Deep learning for optical imaging
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 1 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Deep learning for optical imaging
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 1 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Deep learning for optical imaging
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 1 Hour(s) per week x 14 weeks
  • Type: optional
  • Exam form: During the semester (summer session)
  • Subject examined: Deep learning for optical imaging
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 1 Hour(s) per week x 14 weeks
  • Type: optional

Reference week

Related courses

Results from graphsearch.epfl.ch.