Course contents *

• Learning of representations from raw data: images and text
• Principles of supervised learning
• Elements for different methods for deep learning: convolutional networks and recurrent networks
• Theoretical knowledge of and practical experience of training networks for deep learning including optimisation using stochastic gradient descent
• New progress in methods for deep learning
• Analysis of models and representations
• Transferred learning with representations for deep learning
• Application examples of deep learning for learning of representations and recognition

Intended learning outcomes *

After the course, you should be able to:

• explain the basic the ideas behind learning, representation and recognition of raw data
• account for the theoretical background for the methods for deep learning that are most common in practical contexts
• identify the practical applications in different fields of data science where methods for deep learning can be efficient (with special focus on computer vision and language technology)

in order to:

• be able to solve problems connected to data representation and recognition
• be able to implement, analyse and evaluate simple systems for deep learning for automatic analysis of image and text data
• receive a broad knowledge enabling you to learn more about the area and read literature in the area

Course Disposition

No information inserted

Specific prerequisites *

Non-programme students: 90 university credit points including 45 credits in mathematics or informatics

Recommended prerequisites

No information inserted

Equipment

No information inserted

Literature

Ian Goodfellow, Aaron Courville, and Yoshua Bengio "Deep Learning"

Material produced at the department

If the course is discontinued, students may request to be examined during the following two academic years.

Grading scale *

A, B, C, D, E, FX, F

Examination *

• LAB1 - Laboratory work, 4.5 credits, Grading scale: A, B, C, D, E, FX, F
• TEN1 - Examination, 3.0 credits, Grading scale: A, B, C, D, E, FX, F

Based on recommendation from KTH’s coordinator for disabilities, the examiner will decide how to adapt an examination for students with documented disability.

The examiner may apply another examination format when re-examining individual students.

By making an optional project assignment the students can improve their final grade.

Opportunity to complete the requirements via supplementary examination

No information inserted

Opportunity to raise an approved grade via renewed examination

No information inserted

Examiner

Josephine Sullivan

Ethical approach *

• All members of a group are responsible for the group's work.
• In any assessment, every student shall honestly disclose any help received and sources used.
• In an oral assessment, every student shall be able to present and answer questions about the entire assignment and solution.

Course web

Further information about the course can be found on the Course web at the link below. Information on the Course web will later be moved to this site.

Offered by

EECS/Intelligent Systems

Main field of study *

Computer Science and Engineering

Education cycle *

Second cycle

Add-on studies

No information inserted

Contact

Josephine Sullivan (sullivan@kth.se)

Supplementary information

In this course, the EECS code of honor applies, see:
http://www.kth.se/en/eecs/utbildning/hederskodex