Prof. Dipak Ghosal and I are doing a major revamp of ECS 256. The formal change process may take a while, but I will be teaching 256 next quarter (Winter 2014) according to the new version of the course.

Details are given below. Let me know if you have any questions.

Norm Matloff
**Title:** Probablistic Modeling in Computer Science

**Prerequisites:** Calculus-based undergraduate course
in probability modeling, such as ECS 132 or STA 131A; knowledge of
matrix algebra, as in MAT 22A; some familiarity with R programming.

**Catalog Description:** Probabilistic and statistical
models useful in data science. Applications to networks, business,
bioinformatics, data mining, machine learning, software engineering,
algorithms and so on. Advanced R programming.

**Grading:** Letter grade. Based on group homework,
with interactive grading. No exams.

**Textbook:** N. Matloff,
*
From Algorithms to Z Scores: Probablistic and
Statistical Modeling in Computer Science
*
(open source, available
online);
coverage of Chapters 6,
8, 10, 15, 16, 18, 19, 21.

** Topical Coverage:**

- Review of undergrad probability (densities, properties of expected value and variance, famous discrete and continuous distribution families) and of R programming.
- Discrete- and continuous-time Markov chains; Hidden Markov models; Markov Chain Monte Carlo; basic queuing models. Discrete-event simulation.
- Hazard functions; with applications to system reliability, including software engineering.
- Prediction, especially with nonparametric (machine learning) methods.
- Statistical issues with Big Data.
- Advanced R programming, especially regarding high-performance R.