Computer Science / BCS 530

Methods in Data-Enabled Research

Fall 2018

Syllabus

10/8 Intro
10/10 Lab
10/22 Power Laws Clauset et al., 2007 HW 1 due
10/24 Lab
10/29 Backprop backprop tutorial HW 2 due
10/31 Lab
11/5 Optimization Ruder 2016 HW 3 due
11/7 Lab
11/12 HW 4 due

Homework 1, Due 10/15 10am

Plot rank vs. frequency on a log-log scale, and fit parameters for the generalized power law.

Data are in: /u/cs248/data/mt/training.eng on the instructional network.

Homework 2, Due 10/29 10am

Use the Kolmogorov-Smirnov statistic to fit x_min and alpha for the data from the previous assignment. Discuss how the values compare with the results of HW 1, and plot both models against the data.

Homework 3, Due 11/5 10am

Implement a feed-forward neural net.

Homework 4, Due 11/12 10am

Implement backprop.

For accounts, visit: https://accounts.csug.rochester.edu/

To turn in: /u/cs530/TURN_IN dir_name


gildea @ cs rochester edu
October 24, 2018