Study Guide

Objective

The course will provide students with an overview of recent developments in artificial intelligence with emphasis on machine learning and reinforcement learning. We will study especially deep learning, and its applications in areas such as predicting from multidimensional data, performing image recognition, text analysis, and image and text generation. Deep learning will also be applied in reinforcement learning to understand how we can construct agents that interact with their environment in an intelligent manner by, for example, learning to play Atari games in level that surpasses human performance.

Content

Some of the technical/mathematical concepts covered during the course are:
- Deep networks, linear and logistic regression, deep network activation functions, loss functions, optimization by stochastic gradient descent and other methods.
- Convolutional networks for image pattern recognition, using transfer learning and data augmentation to improve efficiency.
- Text processing and analysis with word embeddings.
- Recurrent neural networks (LSTM, GRU) to capture structures in sequential data.
- Autoencoders and Generative Adversarial Networks (GANs) for mapping input data to latent space.
- Object recognition and YOLO algorithm, facial recognition.
- Markov decision processes, value and Q functions and optimization. Using deep networks as function approximators in reinforcement learning.

Practical work will be based on frameworks available in Python environment, such as Numpy and Keras.

Prerequisites

No prerequisites

Assessment criteria, satisfactory (1)

The student has achieved the course objectives fairly. The student is able to identify, define and use
the course subject area’s concepts and models. The student has completed the required learning
exercises in minimum required level. His/her competences have developed in a way that he/she may
increase his/her knowledge in the given field of technology and finally work in job positions related to
this field of technology.

Assessment criteria, good (3)

The student has achieved the course objectives well, even though the knowledge and skills need to
be enhanced on some areas. The student has completed the required learning exercises in good or
satisfactory level. The student is able to define the course concepts and models and is able to justify
the analysis. The student is able to apply the knowledge of the course in study and work situations.

Assessment criteria, excellent (5)

The student has achieved the objectives of the course with excellent marks. The student master
commendably the course subject area’s concepts and models. The student has completed the
required learning exercises in good or excellent level. The student is able to make justified and fluent
analysis and to present concrete development measures. The student is well prepared to apply the
knowledge of the course in the study and work situations.