Arno Solin
Photo: Henrik Helenius / Hel Tech

Teaching

I have been teaching on courses related to artificial intelligence, machine learning, statistics, signal processing, software tools, and mathematics. During my basic studies, I served as a TA on courses in first-year engineering mathematics, which then gradually turned into teaching on more advanced courses in statistical signal processing during my doctoral studies.

As a faculty member at Aalto University, I have been responsible for designing and lecturing the course ‘Introduction to Artificial Intelligence’ which is intended as a primer in AI/ML and open for all students in the university (including students in arts and business).

I have also been invited to give conference tutorials and lectures in summer schools, most notably the ICML 2020 3-hour tutorial Machine Learning with Signal Processing and the Gaussian Process Summer School 2019.

ICML 2020 Tutorial

Machine Learning with Signal Processing

Abstract

Many ML tasks share practical goals and theoretical foundations with signal processing (consider, e.g., spectral and kernel methods, differential equation systems, sequential sampling techniques, and control theory). Signal processing methods are an integral part of many sub-fields in ML, with links to, for example, Reinforcement learning, Hamiltonian Monte Carlo, Gaussian process (GP) models, Bayesian optimization, and neural ODEs/SDEs.

This tutorials aims to cover aspects in machine learning that link to both discrete-time and continuous-time signal processing methods. Special focus is put on introducing stochastic differential equations (SDEs), state space models, and recursive estimation (Bayesian filtering and smoothing) for Gaussian process models. The goals are to (i) teach basic principles of direct links between signal processing and machine learning, (ii) provide an intuitive hands-on understanding of what stochastic differential equations are all about, (iii) show how these methods have real benefits in speeding up learning, improving inference, and model building---with illustrative and practical application examples. This is to show how ML can leverage existing theory to improve and accelerate research, and to provide a unifying overview to the ICML community members working in the intersection of these methods.

GPSS 2019 Lecture

State Space Methods for Temporal GPs

Courses

  • 2021 / spring CS-C1000 3 cr
    Introduction to Artificial Intelligence
    Target audience level: BSc/MSc. Introductory course in AI and ML.
  • 2021 / spring CS-E4075 Special Course in Machine Learning, Data Science and Artificial Intelligence 3-5 cr
    Gaussian processes - Theory and applications
    Target audience level: MSc/PhD. Lecturers: Dr Markus Heinonen, Prof Arno Solin, Prof Harri Lähdesmäki, Prof Aki Vehtari, Dr Vincent Adam, Dr William Wilkinson, Dr Charles Gadd.
  • 2020 / summer EEA-EV Course with Varying Content 5 cr
    Applied Stochastic Differential Equations
    Target audience level: MSc/PhD. Lectured together with Dr. Simo Särkkä.
  • 2020 / spring CS-C1000 3 cr
    Introduction to Artificial Intelligence
    Target audience level: BSc/MSc. Introductory course in AI and ML.
  • 2019 / autum CS-C3160 5 cr
    Data Science
    Target audience level: BSc/MSc. Lectured together with Dr. Pekka Marttinen and Dr. Rohit Babbar. Around 800 students.
  • 2019 / spring CS-C1000 3 cr
    Introduction to Artificial Intelligence
    Target audience level: BSc/MSc. Introductory course in AI and ML.
  • 2019 / spring CS-E4070 Special Course in Machine Learning and Data Science 3-5 cr
    Gaussian processes - Theory and applications
    Target audience level: MSc/PhD. Lectured together with Dr. Michael Riis Andersen and Dr. Markus Heinonen.
  • 2018 / autumn CS-EV/EEA-EV Course with Varying Content 5 cr
    Applied Stochastic Differential Equations
    Target audience level: MSc/PhD. Lectured together with Dr. Simo Särkkä.
  • 2016 / autumn EEA-EV Course with Varying Content 5 cr
    Applied Stochastic Differential Equations
    Target audience level: MSc/PhD. Lectured together with Dr. Simo Särkkä. Given simultaneously at Aalto University and Tampere University of Technology.
  • 2016 / spring ELEC-E8105 5 cr
    Non-Linear Filtering and Parameter Estimation
    Target audience level: MSc/PhD. TA. Lectured by Dr. Simo Särkkä.
  • 2015 Becs-114.4610 Special Course in Bayesian Modelling 5 cr
    Bayesian Estimation of Time-Varying Systems
    Target audience level: MSc/PhD. TA. Lectured by Dr. Simo Särkkä.
  • 2014 Becs-114.4202/Mat-1.C Special Course in Computational Engineering II 3 cr
    Applied Stochastic Differential Equations
    Target audience level: MSc/PhD. TA. Lectured by Dr. Simo Särkkä.
  • 2013 Becs-114.4610 Special Course in Bayesian Modelling 5 cr
    Bayesian Estimation of Time-Varying Systems
    Target audience level: MSc/PhD. TA. Lectured by Dr. Simo Särkkä.
  • 2013 SCI-A0000/ENG-A1004 cr
    Introduction to Studies/Data Systems
    Target audience level: BSc. Swedish-speaking lecturer.
  • 2012 T-106.1111 cr
    Introduction to Studies and Data Systems
    Target audience level: BSc. Swedish-speaking lecturer.
  • 2009–2012 (once a year) Mat-1.1510 10 cr
    Grundkurs i matematik 1
    Target audience level: BSc. TA. Basic course in mathematics, lecturer prof. Gustaf Gripenberg, taught in Swedish.
  • 2010–2012 (once a year) Mat-1.1520 10 cr
    Grundkurs i matematik 2
    Target audience level: BSc. TA. Basic course in mathematics, lecturer Dr. Georg Metsalo, taught in Swedish.