ZBUM - Biometrics and Machine Learning Group Site - Biometrics and Machine Learning Group

  • About
  • Group
    • A. Pacut
    • M. Trokielewicz
    • W. Gutfeter
    • E. Bartuzi
    • K. Roszczewska
    • K. Gabor
    • M. Hałoń
    • M. Azimi
    • J. N. Khirak
  • Projects
    • AMBER
    • BIOWIZ
    • yieldPlanet
  • Research
    • Databases
    • Laboratory
  • Teaching
    • Biometrics
    • CV
    • NN
  • Scientific Club
  • PhD Theses
  • Publications
    • Biometrics
    • ML

Biometrics and Machine Learning Group

Home

Latest news

We are pleased to announce that Mateusz Trokielewicz defended (with honors) his doctoral dissertation entitled „Iris Recognition Methods Resistant to Biological Changes in the Eye” , supervised by prof. Czajka and prof. Pacut, on the 18th of July, 2019.

Iris scanner can distinguish dead eyeballs from living ones: MIT Technology Review reports on our recent developements in the field of presentation attack detection for cadaver irises.

We are pleased to announce that Mateusz Trokielewicz received the EAB European Biometrics Research Award 2016 for research on iris recognition reliability including template aging, influence of eye diseases and post-mortem recognition.

Is That Eyeball Dead or Alive? Adam Czajka discusses the prevention of iris sensors accepting the use of a high-resolution photo of an iris or, in a grislier scenario, an actual eyeball. For full article, please see IEEE Spectrum.

wersja polska

Introduction to Neural Networks

back to Introduction to Neural Networks (CSE 40868/60868)

Assignments



Assignment 3: Recurrent Neural Networks in TensorFlow / Keras.
You will build the RNN and apply it to process time series data.

Things to do:

  1. Use this github repo prepared by Toan Nguyen to access the tutorial and assignment.
  2. Upload your solution (code + short report) into the 'assignment3' subfolder created in your dropbox (/afs/nd.edu/coursefa.16/cse/cse{40868.01,60868.01}/dropbox) no later than by Wednesday, Dec. 7, 11:59pm.
  3. If you have questions, ask Toan (tnguye28@nd.edu)

Grading:

  1. 20 points for a correct solution just following the assignment.
  2. 2 extra points for your additional effort.



Assignment 2: Convolutional Neural Networks in TensorFlow.
You will build the CNN and apply it to visual object recognition.

Things to do:

  1. Use this github repo prepared by Toan Nguyen to access the tutorial and assignment.
  2. Upload your solution (code + short report) into the 'assignment2' subfolder created in your dropbox (/afs/nd.edu/coursefa.16/cse/cse{40868.01,60868.01}/dropbox) no later than by Monday, Nov. 21, 11:59pm.
  3. If you have questions, ask Toan (tnguye28@nd.edu)

Grading:

  1. 25 points for a correct solution just following the assignment.
  2. 2 extra points for your additional effort (for instance visualization of learned kernels).



Assignment 1: Multilayer perceptrons in Keras.
You will build multilayer perceptrons in Keras and check their properties.

Things to do:

  1. Use this github repo prepared by Toan Nguyen to access the assignment.
  2. Upload your solution (code + short report) into the 'assignment1' subfolder created in your dropbox (/afs/nd.edu/coursefa.16/cse/cse{40868.01,60868.01}/dropbox) no later than by Wednesday, Oct. 26, 11:59pm.
  3. If you have questions, ask Toan (tnguye28@nd.edu)

Grading:

  1. 10 points for a correct solution just following the assignment.
  2. 1 extra point for your additional effort (use of additional dataset, testing NN parameters not mentioned in the assignment, etc.).

Contact us

Institute of Control
and Computation Engineering

Warsaw University of Technology
ul. Nowowiejska 15/19
00-665 Warsaw, Poland
phone: +48 (22) 234 73 97

Logowanie

  • Request new password
  • about
  • group
  • projects
  • research
  • teaching
  • scientific club
  • phd theses
  • publications