• kth.se
  • Student web
  • Intranet
  • kth.se
  • Student web
  • Intranet
Login
WASP Autonomous Systems 1 VT18
Module1 - final - A3 - Neural Network Training with Tensorflow
Skip To Content
Dashboard
  • Login
  • Dashboard
  • Calendar
  • Inbox
  • History
  • Help
Close
  • Min översikt
  • WASP Autonomous Systems 1 VT18
  • Assignments
  • Module1 - final - A3 - Neural Network Training with Tensorflow
  • Home
  • Syllabus
  • Modules
  • Assignments
  • Pages
  • Files
  • Quizzes
  • Media Gallery

Module1 - final - A3 - Neural Network Training with Tensorflow

  • Due Mar 28, 2018 by 3pm
  • Points 10
  • Submitting a file upload
  • File Types ppt, pptx, pdf, and zip

cifar_preview.png

 

This exercise Download This exercise

will let you investigate the training of a convolutional network on an image classification task: Images should be classified into 10 different categories. You will get some almost working code to start with. Download these files Download these files
to get started.

You will also need these image datafiles Links to an external site. (>150MB), mentioned in the assignment.

It is helpful if you know some basics about neural networks and machine learning (layers, overtraining, training sets/test sets, learning rate) but it should be possible to do even if you are inexperienced.

The best performing code will get a prize.

Please see these instructions for information about what to submit and about the peer-review.

Leaderboard in a google speadsheet Links to an external site.

1522242000 03/28/2018 03:00pm
Please include a description
Additional Comments:
Rating max score to > pts
Please include a rating title

Rubric

 
 
 
 
 
 
 
     
Can't change a rubric once you've started using it.  
Find a Rubric
Find Rubric
Please include a title
Title
You've already rated students with this rubric. Any major changes could affect their assessment results.
Title
Criteria Ratings Pts
Edit criterion description Delete criterion row
This criterion is linked to a Learning Outcome Description of criterion
threshold: 5 pts
Edit rating Delete rating
5 to >0 pts
Full Marks
blank
Edit rating Delete rating
0 to >0 pts
No Marks
blank_2
This area will be used by the assessor to leave comments related to this criterion.
pts
  / 5 pts
--
Additional Comments
Edit criterion description Delete criterion row
This criterion is linked to a Learning Outcome Description of criterion
threshold: 5 pts
Edit rating Delete rating
5 to >0 pts
Full Marks
blank
Edit rating Delete rating
0 to >0 pts
No Marks
blank_2
This area will be used by the assessor to leave comments related to this criterion.
pts
  / 5 pts
--
Additional Comments
Total Points: 5 out of 5