A. I. Cuza University of IaşiStochastic Processes
| Course name | Stochastic Processes | Code | CS3210O1 |
| Class | Undergraduate, 2008 - 2011 | Package | 5 | ||||
| Level | Licenţă | Year | 3 | Semester | 2 | Status | Optional |
| Hours per week | Total hours per semester | Total hours of individual work | Credits | Evaluation type | Teaching language | |||
| C | S | L | Pr | |||||
| 5 | ||||||||
| Taught by | Academic and scientific title, name |
|
Lecturer, PhD,
Anca Vitcu
|
| Required courses |
| Objectives | Ability to model and solve complex problems associated to phenomena with random evolution; the focus will be on studding Markov processes (one of the most important stochastic processes) which are widely applied in fields like: computer science, economy, finance, biology, medicine, genetics and physics. |
| General thematics | Basic concepts on probability and statistics – discrete random variables (Bernoulli, binomial, geometric, Poisson), continuous random variables (exponential, hyperexponential, Erlang-k, hipoexponential, Gamma, generalized Erlang, Cox, Weibull, Pareto, lognormal), multiple random variables ( independent, dependent, conditional probability, central limit theorem), transformation of random variables (z, Laplace), inferential statistics (parametric estimation: method of moments, linear regression, MLE); stochastic processes (definition, classification, examples); Markov chains; Poisson processes; iterative methods for linear systems; Hidden Markov Models; Markov decision processes; Applications – Queuing theory, performance analysis (analytical models, simulations). Study cases: HMM word and phrase alignment, searching engines (Google), multiprocessor systems, client-server systems, image/voice recognition, social network analysis, client classification, etc. |
| Seminary / Laboratory thematics | Gauss-Markov processes, stochastic algorithms; MCMC (Markov Chain Monte Carlo) Case studies from: bioinformatics, machine learning, epidemiology, biology, communications, finance, economy. |
| Teaching methods | Slides with course items; seminar themes; projects’ issues; electronic version of the course |
| Bibliography | Bhar Ramaprasad, Hamori Shigeyuki, (2004). Hidden Markov Models Applications to Financial Economics, Kluwer, Boston. Bolch Gunter ?, (2006). Queueing Networks and Markov Chains:Modeling and Performance Evaluation with Computer Science Applications, 2nd edition, Wiley, NJ. Ching Wai-Ki, Ng Michael K., (2006). Markov Chains: Models, Algorithms and Applications, Springer, NY. Kimmel Marek, Axelrod David E., (2002). Branching Processes in Biology, Springer, NY. Marsland Stephen, (2009). Machine Learning: An Algorithmic Perspective, Chapman & Hall/CRC Press. Koski T., (2001). Hidden Markov Models for Bioinformatics, Kluwer Academic Publisher, Dordrecht. Olive Joseph, Christianson Caitlin, McCary John (Ed.), (2011) – Handbook of Natural Language Processing and Machine Translation, Springer. Wasserman S., Faust K., (1994). Social Network Analysis: Methods and Applications, Cambridge University Press, Cambridge. Waterman M., (1995). Introduction to Computational Biology, Chapman & Hall, Cambridge. White D (1993) Markov Decision Processes, Wiley, Chichester. |
| Evaluation | conditions | Seminars’ activity, participation to tutorial hours for clarifying the issues regarding project elaboration |
| criterias | Seminar activity, a project (prepared by a team composed of max 3 students and supervised by the professor in charge) | |
| modes | Mixed (during the semester and examination) | |
| formula | 60% evaluation during semester, 40% final exam (project evaluation) |