We are developing advanced machine learning-based approaches to clinically relevant problems, such as estimating the left ventricular ejection fraction using echocardiogram video, detecting paroxysmal atrial fibrillation from sinus-rhythm electrocardiogram, and predicting which atrial fibrillation patients are good candidates for ablation.
We explore the use of novel deep LSTM and other architectures for predicting asset prices, in conjunction with trading strategies that generate profits based on the networks' predictions. Our work takes advantage of the fact that the effectiveness of any prediction model is inherently coupled to the trading strategy it is used with (and vice versa) which makes the design of models and strategies which are jointly optimal especially challenging. Our architectures far outperform market benchmarks when trading on major US stock indices.
Using the process via which ants optimize their trails when traversing previously unknown terrain, we are developing algorithms for solving challenging trajectory optimization problems in settings where the environment is time-varying and contains moving obstacles or other dynamic "no-go" regions.
We are exploring stochastic and Markov-based models of the process via which economic agents (e.g. small businesses or corporations) make tax-related decisions, including whether or not to keep from disclosing income, where conditions allow. Using techniques from optimal control and machine learning, we are developing computational tools for evaluating tax policies and for examining the effects of proposed changes in the tax code, before they are adopted in vivo.
Introduction to Mathematical Analysis. Sequences and Series. Convergence. Taylor series. Derivatives. Differentiation of multi-variable functions. Multivariable optimization. Optimization with an equality constraint. Optimization with interval bounds. Introduction to differential and difference equations. Solving linear ODEs and difference equations. Second-order systems.
Course WebsiteThe course is part of the department's newest MS program in Artificial Intelligence and Data Analytics (AIDA), and covers the background necessary to successfully navigate the program; Probability, discrete belief networks, inference; Parameter estimation, hidden variable models, dynamic hidden variable models; Entropy, mutual information, Kullback-Leibler divergence; Approximate inference methods, E-M algorithm, sampling methods.
Course websiteLinear vector spaces, multi-variable optimization, linear programming, the Simplex algorithm, duality, sensitivity analysis. Nonlinear programming, Lagrange multipliers, KKT problems. Numerical methods. Integer programming, Branch-and-Bound method.
Course websiteIntroduction to Decision Making in structured and semi-structured settings. Decision Trees. Utility Theory. Introduction to discrete-time dynamical systems. Dynamic Programming. Markov-based models, Value iteration, Policy iteration. Optimal stopping problems. Real-world decision making and factors that affect human decisions.
Course websiteFunctions, limits, continuity, derivatives. Optimization of single-variable functions. Probability and random variables. Descriptive statistics. Discrete and continuous distributions. Probabilistic inference.
Course description @HOUdcv @ uom.edu.gr
+30 2310 891 721
