1. Lectures
  2. Important Dates


The slides and resources for each lecture will be updated after the class. The schedule below is tentative and both the order and the content may change as the semester goes along.

Date Lecture
7-Jan Introduction
9-Jan Review: Supervised Learning
14-Jan Multiclass Classification: Local models
16-Jan Multiclass Classification: Global models
21-Jan First Look at Structures
23-Jan Sequence Models: HMM
28-Jan Sequence Models: Local models
30-Jan Local models (continued)
4-Feb Sequence Models: CRFs
6-Feb No class
11-Feb No class
13-Feb Sequence Models: Structured Perceptron
18-Feb General Formulations: Graphical Models
20-Feb General Formulations: Markov Logic Networks
25-Feb General Formulations: Constrained Conditioned Models
27-Feb Training strategies: Structural SVM
3-Mar Training strategies: Structural SVM, SGD
5-Mar Inference: Graph algorithms
10-Mar Spring Break. No class
12-Mar Spring Break. No class
17-Mar Inference: ILP Inference
19-Mar Inference: Approximate Inference
24-Mar Inference: Learning to Search
26-Mar Learning with constraints
31-Mar Learning latent variables
2-Apr Deep learning: Neural network review
7-Apr Deep learning: Recurrent Networks, LSTM
9-Apr Deep learning and structures
14-Apr Buffer lecture
16-Apr Buffer lecture
21-Apr Practical concerns
  Looking back
28-Apr Project presentations during final exam (8:00 AM - 10:00 AM)

Important dates

Date Deadline
28-Jan Project team information due
18-Feb Review 1 due
20-Feb Project proposals due
5-Mar Assignment due
19-Mar Project intermediate status report due
26-Mar Review 2 due
14-Apr Review 3 due
28-Apr Project presentations in class
28-Apr Project final report due