Messages
Hi all, thanks for your contributions in the final week of the course! I have assembled everybody's papers into a "proceedings" for the course.
You'll have to be logged in or on the UiO network to access it.
Hi everybody,
We're all looking forward to seeing the progress on your papers next week, so the schedule will have fewer lectures from us academics, and more presentations from you student researchers!
There's three critical things to prepare for next week:
- Those who have yet to do a paper presentation will do so, starting with 4 on Monday (10 minutes each).
- Each group will do a final presentation of their project. You'll have...
Hi all,
We would like at least one member of each group to give an 8-10min presentation of your project progress on Monday 15/10 starting at 15:15.
Your presentation can have 5 slides or less (PDF only) OR we can just project your early draft paper.
We'd like you to tell us the following things about your work so far (if applicable):
- What is the main objective of your project?
- What is the method?
- What is the training data?
- What experiments/training have you done?
- How has your overall experience with your research project been so far---both good and bad! :-)
Please...
Hi all, here's the schedule for the second lecture week. We are trying to hold as many sessions as possible in larger rooms this time.
This week we will have lectures from Charles on Mixture Density Networks, Zia on computer vision and deep learning, and Renan (via video from Brazil) on mobile robotics.
We will also have paper presentations from half of you and project updates. I've assigned paper presentations and project reports to sessions below and via email.
Looking forward to seeing it all!
Monday 15/10 - Room: 3437 Seminarrom C (level 3)
1415: welcome back
1430: Charles: Mixture Density Networks - slides, jupyter noteb...
Here's some information for producing your early-draft paper (due Friday, October 5). Here's some guidelines for formatting and what we would expect in your paper so far:
- Use Latex and IEEE Proceedings Template: https://www.ieee.org/conferences/publishing/templates.html
- Use Bibtex for references
- Overleaf good for collaboration, can sync with a GitHub repo. IEEE template available: https://www.overleaf.com/latex/templates/ieee-bare-demo-template-for-conferences/ypypvwjmvtdf
- Your paper should have:
- Title
- Abstract
- Authors + Affiliation
- A skeleton structure:
- 1. Introduction;
- 2. Background;
- 3. Methods/System Design;
- 4. Experiments/Evaluation + Results;
- 5. Con...
Here's some instructions to run a completely local Python/Keras environment on the IFI Linux workstations. These computers are great, but don't have Keras, so we need to do some extra work to set them up for our purposes.
Python installations are complicated an use lots of packages so developers often make "virtual" python environments to keep the packages they need separate from ones that are used by default in the operating system. To do this, you need the virtualenv command that can create one of these environments (this command isn't installed on the IFI Fedora systems unfortunately.
The first step is to install the virtualenv tool:
pip3 install --user virtualenv
This installs virtualenv in your home directory under ~/.local/bin/....
Here's a list of deliverables and updates for each week of the term, please copy the text into your own google doc and share with your project supervisor (with edit permission).
https://docs.google.com/document/d/1_zdb4JkP44q8odZlVPijyTUCwiAj4UMpYzc-IFXVhQI/edit?usp=sharing
Your project supervisor will look for your updates on the days listed on the sheet so make sure you fill in information about your progress and questions you might have regarding your project. In the next two lecture weeks we will ask you to give brief presentations of your progress and deliver drafts of your paper.
August 27: Course introduction video and How to Write a Scientific Paper ...
? Pick one from our list of papers (add your name to it, only one student can present a paper)
?https://docs.google.com/spreadsheets/d/1xfIJZyOcUallpB8SF14JkpkdNKisC1oa5FSUPpjxwJI/edit#gid=0
? Read and understand the paper content
? Prepare a presentation with:
– Paper title page heading
– Main motivation and idea of method in the paper
– Main results
– Assessment of strengths and weaknesses
? Give a presentation in 10 minutes (Oct or Nov)
?Preferred programming language: Python
?Preferred tool: Keras+ Tensorflow, JupyterNotebook, OpenAiGym
?Group size: 3 students
?Projectproposals:
https://docs.google.com/document/d/14LZlb0hmp7j-LPWvEwFeZpB0xV4y-z-84MduhicWuzg
?Register group here: https://docs.google.com/spreadsheets/d/1aNMQO7KCxcoRqwXmg28ehmKHm-lHpsopwpfHobpmAWw/edit#gid=0
?Register group: Tuesday at the lastest
?Register selected project: Wednesday at the latest
Thank you, all who have responded to the Doodle poll. This is very helpful for determining the best compromise on when to meet for lectures/workshop in the course. Thus, we have now decided the following schedule for the coming week:
Monday 14:15-18:00 Course into + lecture on writing research papers + initial project workshop with short descriptions of possible topics + pizza served 17:00 (mingle to form groups and discuss with project supervisors)
Tuesday 14:15-18:00 2 hours lecture (Classification, Semi-supervised learning, Unbalanced Datasets) + 2 hours project workshop (select and plan project)
Wednesday 14:15-18:00 2 hours lecture (RNNs and Generating Creative Sequences) + 2 hours project workshop (work on project)
Thursday 14:15-18:00 2 hours lecture (Convolutional Neural Networks (CNNs))+ 2 hours project workshop (work on project)...
The first teaching week would be 27–31 August, and we need to find appropriate times for lectures and meeting session. Thus, if you have been accepted for the course, please add your name and availability in the following poll:
https://doodle.com/poll/4yiyn8x78qwbc4d6
It is important that you add as much availability as possible and have a valid reason (lectures, group teacher, etc) when you leave a slot open.
In the end of the week, we will be selecting times that seem to reduce conflicts (we don?t except to avoid conflicts completely). So please check the web page again to get updates regarding the chosen schedule.
The teaching would take place in three weeks during the semester (4 hours per day in average):
27–31 August
15-19 October
19-23 November
We will try to the extent possible adapt the lecture/session times to other lectures students have.
Topics to be covered:Classification, Recurrent neural networks, Deep re-inforcement learning, Convolutional Neural Networks (CNN) applied to sensor data analysis, mobile robotics
Teaching: See the main page of the course