TIES4911 Deep-Learning for Cognitive Computing for Developers (8–10 cr)

Study level:
Advanced studies
Grading scale:
0-5
Language:
English
Responsible organisation:
Faculty of Information Technology
Curriculum periods:
2024-2025, 2025-2026, 2026-2027, 2027-2028

Tweet text

Please note that beginning of the academic year 2019-2020, the course will award 8-10 ECTS

Description

Assessment details

More information is available at the course web-page: http://users.jyu.fi/~olkhriye/ties4911

Learning outcomes

By any measure, the past few years have been landmark years for the discussion around Artificial Intelligence and its potential impact on business and society. Being based on Artificial Intelligence, Cognitive Computing Systems are "systems that learn at scale, reason with purpose and interact with humans naturally". Cognitive Computing solutions encompass Machine Learning, Reasoning, Natural Language Processing, Deep Learning, Speech and Vision, Human-Computer Interaction and more. The course aims to provide practical view to the domain of Cognitive Computing and Machine Intelligence. Sstudents will learn how to build Machine Intelligence based solutions using corresponding open-source software libraries (e.g. TensorFlow). At the same time, students will be capable to design and build own services and apps using cloud-based Cognitive Services of such big competing player in this field as IBM, Google, Microsoft, etc.

Additional information

Description of prerequisites

There are no specific requirements. However, the course is practical and requires at least basic skills in programming (Python is the main programming languages of the course). It would be easier to follow the course having at least a basic knowledge of SOA and Cloud Computing, Data Mining, Artificial Intelligence, Knowledge Engineering and Natural Language Processing.

Study materials

All the study related materials are available from the course web-page: http://users.jyu.fi/~olkhriye/ties4911

Completion methods

Method 1

Description:
Completion of 100% course tasks (given during the lectures and demo sessions) brings 8 credits. Extra 2 credits will be given for completion of optional Mini Project.
Evaluation criteria:
Final evaluation is based on evaluations of the tasks given during the lectures and demo sessions. Task specific evaluation criteria are mentioned in corresponding task descriptions.
Select all marked parts
Parts of the completion methods
x

Completion of course tasks/assignments (8–10 cr)

Type:
Independent study
Grading scale:
0-5
Evaluation criteria:
Final evaluation is based on evaluations of the tasks given during the lectures and demo sessions. Task specific evaluation criteria are mentioned in corresponding task description.
Language:
English
Study methods:

Lectures and Demo Sessions. Assignments/tasks to be completed individualy and in groups.  

Study materials:

Lecture materials are available from the course webpage.

Teaching