"Balaton AI" artificial intelligence educational center, taking into account the high demand of the market, announces a new course in parallel with the course conducted jointly with the "Institute of Geophysics and Engineering Seismology of the National Academy of Sciences of the Republic of Armenia", the purpose of which is to establish education-science, artificial intelligence-research connections.
Artificial intelligence and machine learning (ML) - driven by the availability of exceedingly large amounts of data - have led to a rapid acceleration in tech and science breakthroughs. ML is not only useful for google-searches and movie selections on Netflix but also for fault mapping, earthquake detection, phase picking, elastic stress calculations, failure predictions, aftershock forecasting and much more. The course developed by "Balaton AI" center includes:
The goal of this class is to expose students to the newest developments in machine learning and applications in engineering and science. We will discuss basics of unsupervised and supervised learning, classification and regression problems, model training and performance evaluation as well as ensemble and deep learning.
Course Description +
Intro to MATLAB and Python, data I/O, multivariate statistics, earthquake catalog analysis, time series and waveform analysis with obspy, spectral analysis of fault roughness, pressure recession analysis and model fitting, regression models, predictive modeling with artificial neural networks
Course Description +
Topics covered: IDEs, functions and modules, root finding, optimization problems, numerical integration, ODEs, PDEs, introduction to machine learning
Course Description +
Topics covered: plate tectonics, faults and friction, seismic waves, strong ground motions, seismic hazard, earthquake probabilities, tsunamis, induced earthquakes, early warning and earthquake preparedness, Cascadia Subduction Zone and San Andreas fault earthquakes
Course Description +
Topics covered: data I/O, plotting and animations, derivatives and numerical integration, solving systems of equations, statistical analysis, least-squares and MLE, ODEs and PDEs, intro to machine learning classification with MLPs
Course Description +
Topics covered: Object oriented programming, Python modules, Data handling, matlab
Course Description +