The specific topics discussed in CSE 250B will include, not necessarily in this order,
January 7, 2014 
Maximum
likelihood (ML) 

January 9 
Conditional ML, logistic regression model 
Project 1 due on
January 23 
January 14 
Stochastic gradient descent/ascent (SGD) 
Quiz 1 with answer 
January 16 
Regularization 

January 21 
General loglinear model,
feature functions 
Quiz 2 with answer 
January 23 
Conditional random fields (CRFs) 
Project 2 due on
February 13 
January 28 
Viterbi algorithm for prediction with a CRF 
Quiz 3 with answer 
January 30 
Partial derivatives for CRFs, forward and
backward vectors 

February 4 
Stochastic gradient and Collins perceptron
for CRF training 
Quiz 4 with answer 
February 6 
Gibbs sampling, contrastive divergence 

February 11 
Text mining,
bag of words representation, multinomial model 
Quiz 5 with answer 
February 13 
The latent Dirichlet allocation (LDA)
generative model 
Project 3 due on
February 27 
February 18 
Overview of Gibbs sampling for LDA 
Quiz 6 with answer 
February 20 
Derivation of collapsed Gibbs sampling
formula 

February 25 
Introduction to recursive neural networks 
Quiz 7 with answer 
February 27 
Due date for Project 2 
Project 4A or Project 4B, due on Monday March
17 at 10am 
March 4 
Intro to backpropagation 
Quiz 8 with answer 
March 6 
Backpropagation in general 

March 11 
Review of backpropagation for scalar nodes 
Quiz 9 with answer 
March 13 
Review of backpropagation for vectorvalued
nodes 

March 18 (Tuesday) 
Final
exam from
3pm to 6pm 
You should not drop CSE 250B just because you are unhappy with the score that you receive on a project or quiz. Instead, you should make an appointment to discuss with a TA or the instructor how you can do better on following projects and quizzes.
Most recently
updated on March 13, 2014 by Charles Elkan, elkan@cs.ucsd.edu.