This course is an advanced version of ID2223 (level 2 course), Large Scale Machine Learning and Deep Learning. In addition to the course content covered in ID2223, every participant should find their own relevant research literature, read and analyze its contributions, give a presentation on the material, as well as write a short report on the paper.
Information for research students about course offerings
Yearly, during period 2.
Content and learning outcomes
This course is a graduate course that will cover both the basics and recent research
in the area of Large Scale Machine Learning and Deep Learning. The course topics are:
Machine Learning Principles
Using Scalable Data Analytics Frameworks to parallelize machine learning algorithms
Distributed Linear Regression
Distributed Logistic Regression
Linear Algebra, Probability Theory and Numerical Computation
Feedforward Deep Networks
Regularization in Deep Learning
Optimization for Training Deep Models
Sequence Modelling: Recurrent and Recursive Nets
Generative Adverserial Networks
Deep Reinforcement Learning
Applications of Deep Learning
Intended learning outcomes
On successful completion of the course, the student will:
* be able to re-implement a classical machine learning algorithm as a scalable machine learning algorithm
* be able to design and train a layered neural network system
apply a trained layered neural network system to make useful predictions or classifications in an application area
* be able to elaborate the performance tradeoffs when parallelizing machine learning algorithms as well as the limitations in different network environments
* be able to identify appropriate distributed machine learning algorithms to efficiently solve classification and pattern recognition problems.
* be able to discuss, analyze, present, and critically review the very latest research advancements in the areas of Large Scale Machine Learning and Deep Learning and make connections to knowledge in related fields.
Literature and preparations
Enrolled as a doctoral student.
The student should have the general knowledge in Distributed Systems or Machine Learning.
Examination and completion
If the course is discontinued, students may request to be examined during the following two academic years.
- EXA1 - Examination, 7.5 credits, grading scale: P, 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.
Other requirements for final grade
The course will be assessed with a Pass/Fail grade, based on attaining a passing grade in both the coursework and the exam.
Opportunity to complete the requirements via supplementary examination
Opportunity to raise an approved grade via renewed examination
- 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.
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.Course web FID3020