Advanced Topics in Deep Learning

Course info:

Semester: 7

Elective

ECTS: 6

Hours per week: 2

Professor: T.B.D.

Teaching style: Face to face, usage of specialized software

Grading: Homework / Projects (100%)

Activity Workload
Lectures / Tutorials 24
Class assignments / Projects 58
Independent Study 68
Course total 150

Learning Results

Upon successful completion of the course, students will:

  • Have an understanding of how to choose a model to describe a particular type of data.
  • Know how to evaluate a learned model in practice.
  • Understand the mathematics necessary for constructing novel machine learning solutions.
  • Possess a critical understanding of the different characteristics, capabilities and limitations of different advanced deep learning techniques and select the appropriate ones for different cases of complex problem solving
  • Be able to follow advancements in the deep learning field and understand the state of the art in deep learning models

Skills acquired

  • Data and information retrieval, analysis and synthesis
  • Decision making
  • Individual work
  • Team work
  • New research ideas generation
  • Promotion of free, creative and inductive thinking
  • Training of deep learning architectures
  • Bayesian deep learning
  • Graph Neural Networks
  • Tensor algebra, tensor-based learning
  • Multidimensional deep learning
  • Domain adaptation, transfer learning
  • Explainability, interpretability, trustworthiness of machine learning techniques
  • Designing, building and deploying deep learning models in real-world applications
  1. Deep Learning, I. Goodfellow, Y. Bengio and A. Courville, MIT Press, 2016, http://www.deeplearningbook.org.
  2. Deep Learning with Python, F. Chollert, 2nd Edition, Manning
  3. Neural Networks and Deep Learning: A Textbook, C. Aggarwal, 2018, Springer

Related scientific journals:

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Journal of Machine Learning Research
  • IEEE Transactions on Neural Networks and Learning Systems
  • NeurIPS conference proceedings
Learning Results - Skills acquired

Learning Results

Upon successful completion of the course, students will:

  • Have an understanding of how to choose a model to describe a particular type of data.
  • Know how to evaluate a learned model in practice.
  • Understand the mathematics necessary for constructing novel machine learning solutions.
  • Possess a critical understanding of the different characteristics, capabilities and limitations of different advanced deep learning techniques and select the appropriate ones for different cases of complex problem solving
  • Be able to follow advancements in the deep learning field and understand the state of the art in deep learning models

Skills acquired

  • Data and information retrieval, analysis and synthesis
  • Decision making
  • Individual work
  • Team work
  • New research ideas generation
  • Promotion of free, creative and inductive thinking
Course content
  • Training of deep learning architectures
  • Bayesian deep learning
  • Graph Neural Networks
  • Tensor algebra, tensor-based learning
  • Multidimensional deep learning
  • Domain adaptation, transfer learning
  • Explainability, interpretability, trustworthiness of machine learning techniques
  • Designing, building and deploying deep learning models in real-world applications
Recommended bibliography
  1. Deep Learning, I. Goodfellow, Y. Bengio and A. Courville, MIT Press, 2016, http://www.deeplearningbook.org.
  2. Deep Learning with Python, F. Chollert, 2nd Edition, Manning
  3. Neural Networks and Deep Learning: A Textbook, C. Aggarwal, 2018, Springer

Related scientific journals:

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Journal of Machine Learning Research
  • IEEE Transactions on Neural Networks and Learning Systems
  • NeurIPS conference proceedings