Teaching‎ > ‎Zimowy 2018-2019‎ > ‎

Neural Networks 18

This is the main website for the Fall 2018 course on Neural Networks and Deep Learning. Please come back for announcements.

Lectures: Wednesdays 8:15-10:00 room 119

Assignments and lecture notes: https://github.com/janchorowski/nn_assignments

Course rules: course rules

Final exam: Tue, 5 Feb 2019 at 9:30 in room 119

Grade thresholds for the assignments are:
102 total (62 assignments + 40 project): 90: 5.0, 80: 4.5, 70: 4.0, 60: 3.5, 50: 3.0

I thank Google for awarding the class GCE credits under the Google Cloud Platform Education Grants. 

Project submissions and exam grades

posted Feb 8, 2019, 1:22 PM by Jan Chorowski

I will post exam grades on Thursday 14.02.18.

I will host extra office hours on Thursday 14.02 and Friday 15.02 for you to hand in projects. If you want, you can schedule an appointment here (if you don't, you'll have to wait longer).

Lecture 15

posted Jan 30, 2019, 4:36 AM by Jan Chorowski

I've uploaded review slides from the last lecture. 

Lecture 14

posted Jan 23, 2019, 8:21 AM by Jan Chorowski

The notebooks are on GitHub: autoencoders, VAE.

Lectures 12 and 13 are on GitHub

posted Jan 22, 2019, 11:20 PM by Jan Chorowski

During lecture 12 we spoke about neural networks for natural language processing and about the transformer architecture (using Lukasz Kaiser slides).
Lecture 13 was about K-Means, Kohonen maps, and EM algorithm.

Makeup Lecture

posted Jan 7, 2019, 6:46 AM by Jan Chorowski

The slides for the make-up lecture on LSTMs are on Github, along with a demo. Please go through the ESN demo as well.

Makeup lectures, exam, HW5

posted Dec 19, 2018, 4:17 AM by Jan Chorowski

We will host 4h makeup lecture on Saturday, 5.1.19 from 10am-2pm in 119. There will be food.
The final exam is scheduled for Tuesday, 5.2.19 9am-12pm in 119 (the hours were adjusted to match classroom availability).

I've updated convolutional networks slides in GitHub.
I've posted Homework 5, the due date is the last lab session before or on Wednesday, 09.01.19.

Information about final projects

posted Dec 13, 2018, 5:07 AM by Jan Chorowski

Dear students,

the end of the semester is approaching and I would like you to choose your final projects during the week 17-21.12.19. 

Information common to both kinds of projects:
- you can work in groups of no more than 3 students
- before you start a project, please prepare a 1-2 paragraph long description about how your are going to approach it. This is especially important if you want to work on your own idea. Please discuss this during lab sessions.

There are two options for you:
  1. You can work on the ICLR reproducibility challenge in which you will work on reproducing some experiments from submissions to the ICLR 2019 conference. Please note that the scope of the project depends on the provided resources - for some papers, the authors may provide code and data, in which case you can verify that it works as described and try applying the same principle to another problem. On the other extreme, a paper may not provide code nor data and your reproducibility effort may go towards implementing baselines or validating the idea in a limited setup. 
    If you choose to work on the reproducibility, please follow the procedure at the challenge website. Don't worry about the January 7 deadline - our course timeline is not well aligned with ICLR reviewing period and while your reports will not affect the acceptance process, they will benefit the scientific community nevertheless!
    To help you choose a paper to reproduce I've selected a few papers in this spreadsheet. You can of course select any other paper, e.g. using this list to browse by reviewer scores.
  2. You can work on you own idea - maybe you have a cool application project in mind, or would want to apply neural networks to some task? You can definitely do so during the project, but please consult with us and have your project accepted - we will try to keep the burden similar to the reproducibility track.
It is important to select the projects before the Christmas break, please think over them and prepare propositions for next lab sessions.

Lecture 8 and class disruptions

posted Nov 29, 2018, 3:53 AM by Jan Chorowski

I've uploaded materials for the last lecture to Github.

I am traveling over the next two weeks, next lecture is on 19.12, my labs are canceled until 19.12, Jakub's labs are happening. Fill the two doodles: https://doodle.com/poll/548uv7fxzpqakf3q https://doodle.com/poll/kq3r9iu4gcyn9gub and if you need to speak with me use https://goo.gl/mcAvyq

Lecture notes 5, 6 & HW4

posted Nov 14, 2018, 2:05 PM by Jan Chorowski

I've posted to GitHub slides for lect 5 and 6, along with homework 4 - the first two problems are due in two weeks, the remaining ones in three weeks.

Lecture notes 3, 4 and HW3

posted Oct 31, 2018, 6:44 AM by Jan Chorowski

Dear students,

lecture 4 finished the logistic regresson notebook from lecture 3.

I have also posted to Github Assignment #3.

1-10 of 13