Course Identification

Statistics, Algorithms and Experiment design
20231062

Lecturers and Teaching Assistants

Dr. Barak Zackay
Dotan Gazith, Jonathan Mushkin, Oryna Ivashtenko

Course Schedule and Location

2023
Second Semester
Monday, 14:15 - 16:00, Drori Auditorium
Thursday, 14:15 - 16:00, Drori Auditorium
17/04/2023
21/07/2023

Field of Study, Course Type and Credit Points

Physical Sciences: Lecture; Elective; Regular; 4.00 points
Chemical Sciences: Lecture; Elective; Regular; 4.00 points
Life Sciences: Lecture; Elective; Regular; 4.00 points
Life Sciences (Brain Sciences: Systems, Computational and Cognitive Neuroscience Track): Lecture; Elective; Regular; 4.00 points

Comments

N/A

Prerequisites

Undergrad level knowledge of linear algebra and probability theory and computer programming.

 

 

Restrictions

60

Language of Instruction

English

Attendance and participation

Expected and Recommended

Grade Type

Pass / Fail

Grade Breakdown (in %)

50%
50%

Evaluation Type

Final assignment

Scheduled date 1

N/A
N/A
-
N/A

Estimated Weekly Independent Workload (in hours)

4

Syllabus

  • Hypothesis testing (Neyman - Pearson, UMP, sufficient statistics, discrete hypotheses, complex hypotheses)
  • Matched filter, optimal weighting, least squares
  • Fourier Analysis (convolution theorem, power spectrum, autocorrelation, FFT, Linear systems, basic signal processing, noise whitening)
  • Dynamic programming (concept + 2/3 algorithms (Viterbi, Radon Transform, Kalman Filtering))
  • Basics of Bayesian inference (Several examples,  Sampling algorithms)
  • Basics of information theory (channel capacity, Fisher information, CRLB, experiment design)
  • Experimental design.

    Throughout the course, examples from astrophysics will be used.

Learning Outcomes

Student will be able to:

1) Statistically model simple experiments in a solvable fashion.

2) Detect a signal from a complex family of possible signals in colored Gaussian noise.

3) Compute the expected performance of an experiment.

4) Measure a parameter using bayesian inference.

5) Have some experience in dynamic programming and state-space methods.

 

Reading List

N/A

Website

N/A