Please note! Course description is confirmed for two academic years, which means that in general, e.g. Learning outcomes, assessment methods and key content stays unchanged. However, via course syllabus, it is possible to specify or change the course execution in each realization of the course, such as how the contact sessions are organized, assessment methods weighted or materials used.
LEARNING OUTCOMES
Intended as follow-up for CS-EJ3211 Machine Learning with Python.
Credits: 2
Schedule: 09.09.2020 - 18.12.2020
Teacher in charge (valid 01.08.2020-31.07.2022): Alex Jung
Teacher in charge (applies in this implementation): Alex Jung
Contact information for the course (valid 04.08.2020-21.12.2112):
alex.jung@aalto.fi
CEFR level (applies in this implementation):
Language of instruction and studies (valid 01.08.2020-31.07.2022):
Teaching language: English
Languages of study attainment: English
CONTENT, ASSESSMENT AND WORKLOAD
Content
Valid 01.08.2020-31.07.2022:
In this course, you will learn how to use state-of-the-art deep learning methods with the programming language Python.
We will discuss key concepts of deep learning, such as artificial neural networks, data augmentation and transfer learning in a hands-on fashion. The grading is based on coding assignments and student projects.Applies in this implementation:
The course discusses how artificial neural networks (ANN) can be used to represent and learn predictor maps that accurately predict label values from a large number of input features. We will use the Python library keras to design and train deep ANNs on a given dataset. Students will learn basic methods for regularizing the training process, such as data augmentation and dropout. The course also teaches how to implement transfer learning by fine-tuning a pre-trained ANN on a (small) target dataset.
Assessment Methods and Criteria
Applies in this implementation:
The grading will be based on different tasks from which the students can choose freely. These tasks include multiple-choice questions and small data analysis tasks.
Workload
Applies in this implementation:
The estimated average course workload is 2 credits (approx. 54 hours or work).
DETAILS
Study Material
Applies in this implementation:
The course material consists of Python notebooks.
Additional Reading:
- F. Chollet, "Deep Learning with Python", 2017. available at https://aalto.finna.fi/Record/alli.833878
- A. Jung, "Machine Learning: Basic Principles", 2018. available at https://arxiv.org/abs/1805.05052,
Prerequisites
Valid 01.08.2020-31.07.2022:
Machine Learning with Python or equivalent.