We will learn to model problems and systems using mathematics and computers. We'll be using the python computer language (which I will teach everybody at the start of the course). We'll cover statistical models, automata models, and classical applied-math models.

We'll also discuss the nature of modelling,
based on readings from Nate Silver's *Signal and the Noise*.

At the end of the course, you'll have the start of a very valuable skill set.

Canopy - python software for scientific computing that we'll make use of in class.

- Homework 1, due Friday, January 24th. Answers
- Homework 2, due Wednesday, February 5th. Answers
- Homework 3, due Wednesday, February 12th. Answers
- Homework 4, due Wednesday, February 19th. Answers
- Homework 5, due Wednesday, February 26th. Answers
- Homework 6, due Friday, March 7th. Answers
- Homework 7, due Wednesday, March 19th. Answers
- Homework 8, due Friday, March 28th. Answers
- Homework 9, due Friday, April 4th. Answers
- Homework 10, due Friday, April 11th. Answers
- Homework 11, due Friday, April 17th. Answers
- Homework 12, due Friday, April 25th. Answers

- Lab 1: Introduction to python and the command line
- Lab 2: LOGO and turtle graphics, due Monday, February 3rd.
- Example code for using log-transformed linear regression to obtain a scaling law for Huxley's bird-egg data.
- Discrete Logistic Equation code
- Numerical solution of the exponential-decay differential equation
- Conway's Game of Life and a recent smooth version

Brooksley Born's story on Frontline about the regulation of deriviative markets, and why some people hold it against Larry Summers.

Curtousy of Doug, a blog post about the success of python in scientific computing.

We were discussing Chapter 8 in class on Bayesianists vs. Frequentists. Prof. Ipeirotis has a nice post giving a better explanation about the difference between the frequentist and Baysian perspectives. Prof. Wasserman, from Carnegie Mellon, has a blog post, courtessy of Corrine, that argues Nate has been mis-informed about the difference between Baysians and Frequentists, and that he's actually a frequentist. Of course, this started an argument, which get's down into the weeds and doesn't really settle anything unless you want to dig in deeply. To balance the picture, here's a different blog post from a recent convert to the frequentist philosophy.

Doug point's out that there is a lecture of interest to our climate modelling section this coming Friday, April 4, 2014 2:30 PM, 113 Information Sciences and Technology Building, The Cybertorium

"Big data" is a dominate idea in technological development right now, closely related to our readings of Nate Silver's book. But there is also a lot of pushback right now. Poster-child of model-free big-data inference Google flu trends seemed to work pretty good at first. Now there's another effort-involving critical analysis of this by Olson, Konty, Paladini, Viboud, and Simonsen as well as cheap commentaries by Butler, Lazer, Kennedy, King, and Vespignani, and Tim Harford helping the limitations of data without models.

Stephen Wolfram's enumeration of 1-dimensional spatial rewrite rules.

Nate Silver's in a fight with Paul Krugman over quantitative journalism. Michael Mann also has some tough comments on Nate's book.