Machine learning for signal processing and time series analysis. Temporal neural networks 2016

Course Description

This course is dedicated to Machine learning in the context of signals and time series. First, we will study effect of resampling, linear filtering, Fourier transform etc. Then we will explore convolutional neural networks and deep learning for tasks of signal recognition.
We will also consider time series prediction, nonlinear system identification and control as well as recurrent neural networks solving these tasks. We will propose also a case study of disaggregation problem in household power supply networks .

Course topics

Signal processing, time series analysis, prediction, system identification, recurrent and temporal neural networks.

Course tools

Python, Theano, Keras, Tensor flow, Matlab/Octave

Prerequisits

Basics of linear algebra

Lecturer

Dr. Dimitri Nowicki
Computational neuroscientist–expert in AI and Neural Networks 

Affiliation: Institute of Cybernetics of NASU, Ukraine/ Univ of Massachusetts CS dept.

Computational neuroscientist–expert in AI and Neural Networks – PhD (Université de Toulouse, 2004), MSc in applied mathematics, Moscow Institute of Physics and Technology (2000). Worked in France (Toulouse, Grenoble), USA (Univ. of Massachusetts, Harvard University). Associate Research Professor at the Institute of Cybernetics of NASU

Fields of interests: computational neuroscience, bioinformatics, recurrent networks and associative memory, optimization etc

Contacts

[email protected]
www.facebook.com/dimitri.nowicki