COGS109: Modeling and Data Analysis (Fall 2014)

Lecture: M/W/F 5:00- 5:50 pm CENTR 105

Section A01: M 11:00-11:50 am CSB115 
Section A02: W 2:00-2:50 pm CSB115
Section A03: F 10:00-10:50 am CSB115


Students may attend extra sections as needed (space permitting)

All content-related 109 questions should be asked through the discussion links at the piazza site.

Course website: http://thiscourse.com/ucsd/cogs109/fa14/

Instructors

He Crane Huang (Instructor)

Office Hours: Monday 3-4 pm in Atkinson Hall Room 6101

Jake Olson (TA)

Office Hours: Thursday 1-2 pm in CSB 115

Chun Chieh Fan (TA)

Office Hours: Monday 10-11 am in CSB 228

Daniel Maryanovsky (TA/Tutor)

/ phone: 858-922-4461

Office Hours: Thursday 3-7 pm or by appointment in SSRB 246

The lab wing has restricted access, so students will need to call the above number to be let in.

Alex Wooten (IA)

Office Hours: Friday 4-4:50 pm in CSB 115

Course Description

This course is designed to be an introduction to basic computational methods for data analysis in Cognitive Science. 

Course-level Learning Goals:

  • Understand the concept of introduced models (Linear regression, Neural network, Bayesian inference, PCA and K-means clustering) and its application.
  • Develop appropriate models based on given data type and problems of interests.
  • Use Matlab to visualize data, create models and solve computational problems. 

Websites:

TED: Grades, short assignments 
Thiscourse: Lecture notes, long assignments 
Piazza: Discussion, questions

Clickers are available in the bookstore. Register your clicker using TED.
All content-related 109 questions should be asked through the discussion links at the piazza site.

Course Details and Policies

Grading Scheme:

  • Short Assignments       One for each topic                    20%  (about once a week)
  • Long Assignments        Every 2-3 weeks                        20%  (longer version of short assignments)
  • Mid-term                    11/05 (Wed, 5-6 pm)                 25%  (similar to long assignments and short assignments)
  • Final                          12/18 (Thu, 7-10 pm)                 25%  (similar to long assignments and short assignments)
  • Clicker Questions        Every lecture                             10%  (only for participation)
  • Bonus                         Active participation on Piazza    up to 5%

Course Schedule

Week Date Topic Resources Assignments
0 Fri Oct 03 Introduction Matlab Tutorial (video)  
1 Mon Oct 06 Linear Regression I  Linear Regression
(video)

Short Assignment 1
Wed Oct 08 Linear Regression II Demo_LargeData_1st

 
Fri Oct 10
Guest Talk (Walter Talbott)
Linear Regression III


Why Least Squares? (Optional but Fun)

Long Assignment 1

2 Mon Oct 13 Q & A Linear Regression Demo_3pts2order

 
Wed Oct 15 Perceptron Learning I Perceptron Learning (Video)
Perceptron Learning (Advanced/Optional)

Short Assignment 2
Fri Oct 17 Perceptron Learning II In Class Exercise  
3 Mon Oct 20 Perceptron Learning III    
Wed Oct 22
Guest Talk (Vicente Malave)
Q & A Perceptron Learning
   
Fri Oct 24
Guest Lecture (Prof de Sa)
   
4 Mon Oct 27 Neural Network I Demo_Gradient Descent

Short Assignment 3
Wed Oct 29 Neural Network II Neural Networks and Machine Learning

 
Fri Oct 31 Neural Network III Demo_neural net  
5 Mon Nov 03 Midterm Review   Additional Exercise (Neural Network)


Wed Nov 05 Midterm    
Fri Nov 07 Bayes Rule I Probability Review SA4-Q1 (in class)
6 Mon Nov 10 Bayes Rule II Bayes' Rule (required) Short Assignment 4
(TED)
Wed Nov 12 Bayes Rule III (Bayesian Inference) Demo_Bayesian   
Fri Nov 14 Bayes Rule IV (Bayesian Inference) Yu & Huang 2014
Extra Exercise 
7 Mon Nov 17 Q & A Bayes Rule   LA2 (vectorarrow)

Wed Nov 19 PCA I PCA Tutorial (video)

SA5 (eigsort)

Fri Nov 21 PCA II PCA Tutorial (required I-V; optional VI-VII)

 
8 Mon Nov 24
Guest Talk (Chun Chieh Fan)
Covariance Matrix, Eigenvector and Eigenvalue

 
Wed Nov 26 PCA IV Demo_Face_Recognition (FaceData) SA5 due

Fri Nov 28 (Thanksgiving Holiday)    
9 Mon Dec 01 Q & A PCA    
Wed Dec 03 Guest Talk (Jeremy Karnowski)    
Fri Dec 05 K-means Clustering I   LA2 Due
10 Mon Dec 08 K-means Clustering II   SA6 
K-means template
Wed Dec 10 Review I and Q & A   Matlab Take-home Final
Fri Dec 12 Review II and Q & A   SA6 due
11 Thu Dec 18 Final 7:00 pm-9:59 pm