Special Course in Information Technology
This course provides an introduction to deep learning. Students taking this course will learn the theories, models, algorithms, implementation and recent progress of deep learning, and obtain empirical experience on training deep neural networks. The course starts with machine learning basics and some classical deep models (including convolutional neural network, and auto-encoder), followed by optimization techniques for training deep neural networks, implementation of large scale deep learning, multitask deep learning, transferred deep learning, recurrent neural networks, applications of deep learning to typical computer vision problems, and understanding why deep learning works. After this course, students will learn to implement, train and debug their own neural networks and gain a understanding of cutting-edge research in computer vision.
Dr. Li Liu (firstname.lastname@example.org)
Dr. Jie Chen (email@example.com)
Khanh Tran (Khanh.Tran@oulu.fi)
Yante Li (Yante.Li@oulu.fi TS334)
From Weboodi, the number of registered students is 61, which is much more than expected. In addition, we have students who cannot register at the moment but are willing to take this course. Therefore, the estimated number of students is about 65. For the exercise class (the second class), we have to reserve computer room (such as TS 137), which has only 25 computers. Then we have to divide students into groups and will teach the second class several times. In order to make arrangements, we require that you talk to the instructor (sign your name and leave your email address) or email us (firstname.lastname@example.org) after the first class you attend, to finally confirm if you will take the course or not. Based on this, we will group you into two or three groups for the second exercise class. We will notice you in which group you are via email. After that, if you find there is some conflicts to your other course, please let us know (email to email@example.com). We will make changes.
It is important that you check the course webpage before you go to class.
Due to the number of registered students is much more than expected, we have to change to a bigger classroom. Now the first lecture will be given in L5.
Proficiency in Python
All class assignments will be in TensorFlow (we provide a class for TensorFlow introduction here for those who aren’t as familiar with TensorFlow). If you have a lot of programming experience but in a different language (such as C, C++ and Matlab) you will probably be fine.
You should be comfortable taking derivatives and understanding matrix vector operations and notations.
Basic Probability and Statistics, Linear Algebra.
You should know basics of probabilities, Gaussian distributions, mean, standard deviation, etc.
If you have knowledge of Machine Learning course and digital image processing course, it will help you a lot in taking this course.
We will be formulating cost functions, taking derivatives and performing optimization with gradient descent.
We will be using recognition examples in computer vision.
All students must complete all assignments during the course. More detailed instruction can be found from "Assignments" subpage (on the left)
Course Project Details
In addition to the assigments, all students must complete a project work during the course. More detailed instructions can be found from "Project" subpage.
Course Project Details: https://noppa.oulu.fi/noppa/kurssi/521149s/project
Assignment #1: 16%
Assignment #2: 10%
Assignment #3: 10%
Assignment #4: 10%
Assignment #5: 14%
Final Project: 40%
Note: There is only one exercise. As there are too many students, we divid our students into two groups. You just need to take one. And we will inform you the group division result before the exercise. If you have problems, you can e-mail us.
1. Tensorflow introduction
Tuesday 07.11. at 16:15-18:00 (hall TS 137, Group 1)
Tuesday 09.11. at 16:15-18:00 (hall TS 137, Group 2)
5 ETC points
Will this course be continued in 2018?
This course will be given in autumn 2018.
Can I audit or sit in?
In general we are very open to sitting-in guests if you are a member of the University of Oulu (registered student, staff, and/or faculty). Right now the number of registered students is 57, which is much more than expected. Out of courtesy, we would appreciate that you email us (Yante.Li@oulu.fi) after the first class you attend, to finally make up your mind if you will take the course or not. This is important for us to make arrangements. If the class is too full and we’re running out of space, we would ask that you please allow registered students to attend.
I have a question about the class. What is the best way to reach the course staff?
Please contact the teaching assistants first by email.
How can I find a platform for the final project using TensorFlow?
CSC (Finnish Center for Scientific Computing) offers now Jupyter Notebook service that includes also TensorFlow. The service can be found from https://notebooks.csc.fi/ and you can log in with the university account. The right environment is Jupyter ML Blueprint. This could be an alternative for the students to complete the assignments.
News (3 most recent)
|21 Dec 17||Final project of deep learning|
|19 Dec 17||Example code for DL assignment 2,3,4|
|29 Nov 17||Problems in Assignment 3|
In coming events