Data Mining and Deep Learning (DAT550)

Content

• Unsupervised learning

  • Data cleansing, transformation and preparation
  • Clustering
  • Dimensionality reduction, SVD, PCA

• Supervised learning

  • Classification
  • Neural Networks and Deep learning
  • Recommendation systems

Learning outcome

Knowledge

Candidate:

• has advanced knowledge in the field and specialized in the theory and practice of data preparation, selection and mining.
• has in-depth knowledge of the scientific or art theory of the subject area and methods to gain insight from large data collections.
• can apply knowledge in new areas of data mining and deep learning
• can analyze knowledge extraction issues on the basis of data mining and deep learning

Skills

Candidate can:

• Be able to analyze and critically relate to various sources of information and use these to structure and formulate professional reasoning for various data mining tasks
• Be able to analyze existing theories, methods and interpretations within the area of data mining and deep learning and work independently with problem-solving on data mining and deep learning tasks
• Be able to use relevant data mining methods such as clustering, classification, graph, stream mining, frequent pattern mining, association rule mining, deep learning for research and professional application development
• Be able to carry out an independent, limited research or development project under supervision and in accordance with current research ethics standards which involves preparing data mining pipelines, evaluation, and tune parameters for various data mining models and deep learning using state-of-the-art tools.

General competencies

Candidate:

• can analyze relevant professional, research and ethical issues in data mining and deep learning
• can apply their knowledge and skills in new areas to carry out advanced tasks and projects
• can provide extensive independent work on data mining and deep learning issues
• can communicate about data mining and deep learning issues, analyzes and conclusions within the subject area, both with specialists and to the general public.
• can contribute to research and innovation in data mining and deep learning.
• identify the theoretical and practical issues behind various data mining and deep learning techniques. Being able to list and describe strengths, limitations and trade-offs among various data mining techniques and choose the appropriate techniques for solving data science problems for various applications.

Required prerequisite knowledge

Recommended prerequisites

Exam

Coursework requirements

Three mandatory graded (A-F) exercises/programming assignments amounting to 3/20 (15%) of the final grade.

All programming exercises must be passed to attend for the written exam and to get project approved. Completion of mandatory lab assignments are to be made on time. Absence due to illness or for other reasons must be communicated as soon as possible to the laboratory personnel. One cannot expect that provisions for completion of the lab assignments at other times are made unless prior arrangements with the laboratory personnel have been agreed upon. Failure to complete the assigned labs on time or not having them approved will result in barring from taking the exam of the course.

Course teacher(s)

Course coordinator:

Course teacher:

Head of Department:

Method of work

Open for

Course assessment

Literature