Helsinki University of Technology → Faculty of Information and Natural Sciences →
Department of Information and Computer Science → Teaching →
T-61.3050 Machine Learning: Basic Principles → Relation to the old T-61 courses

Relation to the old T-61 courses - T-61.3050

In curriculum and for the purposes of the degree requirements, this course, T-61.3050 Machine Learning: Basic Principles, replaces the old course T-61.3030 (and T-61.261) Principles of Neural Computing.

This course (T-61.3050) was established beginning the 2007-2008 semester, together with the courses T-61.5130 Machine Learning and Neural Networks and T-61.5140 Machine Learning: Advanced Probabilistic Methods, to replace the old courses T-61.3030 Principles of Neural Computing, T-61.5040 Learning Models and Methods and T-61.5030 Advanced Course in Neural Computing. The purpose of the change was to increase the weight of the principles and probabilistic methods of machine learning and decrease the weight of the neural networks in the basic studies of the Computer and Information Science. This course is also a response to the student feedback, according to which one could have more weight on principles instead of the number of machine learning methods in the basic courses of the Computer and Information Science.

The new courses, combined with T-61.5060 Algorithmic methods of data mining, give a solid overview of the fields of machine learning and data mining.

This course (T-61.3050), together with the new course T-61.5140 Machine Learning: Advanced Probabilistic Methods, overlaps with the old course T-61.5040 Learning Models and Methods. The contents of this course (T-61.3050) have very little overlap with the old course T-61.3030 Principles of Neural Computing. The course T-61.5130 Machine Learning and Neural Networks is essentially a composite of the old courses T-61.3030 Principles of Neural Computing and T-61.5030 Advanced Course in Neural Computing.

Summarizing, in the curriculum and for the purposes of the degree requirements, the correspondences are:

Correspondences in degree requirements

Old course (before Autumn 2007)	New course
T-61.3030 Principles of Neural Computing	T-61.3050 Machine Learning: Basic Principles
T-61.5030 Advanced Course in Neural Computing	T-61.5130 Machine Learning and Neural Networks
T-61.5040 Learning Models and Methods	T-61.5140 Machine Learning: Advanced Probabilistic Methods

The topical correspondences are as roughly as follows. Please however note that the topical correspondences are very approximate. The unions of topics covered by the old and new courses differ. Also, the new courses have more weight in the principles and probabilistic methods of machine learning and less weight in neural networks.

Approximate topical correspondeces

Old course (before Autumn 2007)	New course
T-61.5040 Learning Models and Methods	T-61.3050 Machine Learning: Basic Principles
	T-61.5140 Machine Learning: Advanced Probabilistic Methods
T-61.3030 Principles of Neural Computing	T-61.5130 Machine Learning and Neural Networks
T-61.5030 Advanced Course in Neural Computing

The last examinations and exercise work deadlines of the old courses will take place in semester 2007-2008 after about one year has passed from the end of the respective courses in semester 2006-2007. Please see the web sites of the old courses, as well as the examination schedule, for more information.

Relation to T-61.3020 Principles of Pattern Recognition

The difference between this course and the continuing course T-61.3020 Principles of Pattern Recognition is that the Principles of Pattern Recognition aims to introduce several methods of machine learning (pattern recognition uses the methods of machine learning), however, without discussing the motivations and principles of these methods in great depth. The emphasis of this course, on the other hand, is on principles behind the methods, such as probability theory and algorithmics, and how to apply these principles in the practical data analysis (for example, how to asses the performance of the algorithm). Understanding these principles should make it easier also to understand and apply new concepts and methods that build on the topics covered in this course.