Course Code

MDA-250

Semester

2nd Semester

ECTS Credits

7,5

Type of Course

Mandatory

Deep Learning and Artificial Intelligence

Objective

This course aims at introducing advanced methodologies of machine learning, pertaining to learning decision processes, enhancement of effectiveness and combined usage of basic algorithms, and analysis and preparation of available data for their effective exploitation. The course’s learning outcome includes deep understanding of the performance of machine learning methodologies, the ability of combining them for solving demanding problems and the ability of data analysis and preprocessing for aligning the data effectively with an appropriate methodology.

Course Contents

Introduction

Introduction to artificial intelligence and machine learning, types of problems, supervised learning, unsupervised learning, reinforcement learning, application domains.

Neural Networks I

Introduction to neural networks, models and architectures of neural networks, perceptron, linear and non-linear separapability, multilayer perceptron, training algorithms.

Neural Networks ΙI

Evaluation of the performance of the neural networks, genelization, applications of neural networks, case-study.

Clustering Ι

Definitions, clustering categories, distance measures, similarity functions, partitioning, k-means algorithm.

Clustering ΙΙ

Hierarchical clustering, clustering evaluation and validation, clustering applications, case-study.

Deep Learning and Convolutional Neural Networks I

Introduction in Deep Learning, Convolution and pooling, Deep Learning Architectures, Training Deep Neural Networks.

Deep Learning and Convolutional Neural Networks II

Recurrent Neural Networks, Generative Models, Detection and Segmentation, Visualizing and Understanding, Transfer Learning.

Deep Learning Lab

Deep Learning Examples, Recognition with pretrained networks, transfer learning, training and evaluation.

Multidimensional Data Processing

Multidimensional Vision, Feature Extraction, Recognition, Classification, Video Analysis.

Machine learning in Biomedical Data

Biomedical Data representation, Extracting Knowledge, Event recognition and Anomaly detection in medical history, machine learning for diagnosis and health strategies.

Recommended Readings

  • T. Mitchell. Machine Learning. McGraw-Hill (International Edition), 1997.
  • C. Bishop. Pattern Recognition and Machine Learning. Springer, 2007.
  • W. McKinney. Python for Data Analysis. O’Reilly, 2012.
  • S. Raschka. Python Machine Learning. Packt Publishing, 2015.
  • I. H. Witten, E. Frank, M. A. Hall. Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, 3rd edition, 2011.
  • Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, http://www.deeplearningbook.org, 2016