DD2424 Deep Learning in Data Science 7.5 credits

• Education cycle

  Second cycle

• Main field of study

  Computer Science and Engineering
  

• Grading scale

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

• Course web

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 main content

• 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

Eligibility

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

Literature

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

Material produced at the department

Examination

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

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

Offered by

CSC/Robotics, Perception and Learning

Contact

Josephine Sullivan, e-post: sullivan@kth.se

Examiner

Josephine Sullivan <sullivan@kth.se>

Version

Course syllabus valid from: Spring 2018.
Examination information valid from: Spring 2017.