EE 4389W
Homework 5 (10 pts)
Due date: Dec 6, 2011
F 2011
Topic: SVM classification
This homework illustrates the use of SVM classification, and SVM model selection.
You can use any SVM s/w package (i.e., STPR - see course web site).
Problem 1: low-dimens
Introduction to
Predictive Learning
LECTURE SET 7
Support Vector Machines
Electrical and Computer Engineering
1
OUTLINE
Objectives
explain motivation for SVM
describe basic SVM for classification & regression
compare SVM vs. statistical & NN methods
Motiv
Introduction to Predictive
Learning
LECTURE SET 5
Statistical Methods
Electrical and Computer Engineering
1
OUTLINE
Objectives
- introduce statistical terminology/methodology/motivation
- taxonomy of methods
- describe several representative statistical m
Introduction to
Predictive Learning
LECTURE SET 2
Basic Learning Approaches and
Complexity Control
Electrical and Computer Engineering
1
OUTLINE
2.0 Objectives
2.1 Data Encoding + Preprocessing
2.2 Terminology and Common Learning Tasks
2.3 Basic Learning
Introduction to
Predictive Learning
LECTURE SET 4
Statistical Learning Theory
Electrical and Computer Engineering
1
OUTLINE of Set 4
Objectives and Overview
Inductive Learning Problem Setting
Keep-It-Direct Principle
Analysis of ERM
VC-dimension
Generaliz
Introduction to
Predictive Learning
LECTURE SET 1
INTRODUCTION and OVERVIEW
Electrical and Computer Engineering
1
OUTLINE of Set 1
1.1 Overview: what is this course about:
- subject matter
- philosophical connections
- prerequisites and HW1
- expected out
Introduction to
Predictive Learning
LECTURE SET 3
Philosophical Perspectives
Electrical and Computer Engineering
1
OUTLINE
3.1 Overview of Philosophy
3.2 Epistemology
3.3 Acquisition of Knowledge and Inference
3.4 Empirical Risk Minimization
3.5 Occams Ra
EE 4389W Reading 5 Notes
All learning methods presented so far in this book follow a standard inductive learning setting,
where the goal is to estimate a predictive model from finite training data . The estimated function
(or model) is then used for predi
EE 4389W Reading 4 Notes
This chapter describes a family of learning algorithms known as Support Vector Machines
(SVM). SVM methodology was developed in Statistical Learning Theory, and later was adopted
by researchers in machine learning, statistics and
EE 4389W Reading 3 Notes
This chapter describes data-analytic methods developed in the field of artificial neural networks
(ANNs). Neural network methods have been inspired by biological learning, and they use very
specialized terminology. However, most n
EE 4389W Reading 2 Notes
The remaining chapters of this book describe various learning algorithms for estimating
predictive models from data. This chapter describes statistical methods for classification and
regression tasks, introduced in Chapter 2. Neur
EE 4389W Reading 1 Notes
This chapter explores close relationship between predictive learning and relevant philosophical
ideas. This connection is not obvious, because predictive learning is described in precise
mathematical terms and well-defined algorit
1
EE 4389W
FALL 2011
Homework 1 (5 pts total)
Due Sep 15, 2011
BACKGROUND ON PROBABILITY AND PROGRAMMING
Problem 1 (1 point)
Consider a fair coin toss, so that the probability of the Head or Tails outcome is the same, i.e.
0.5. If 4 coins are tossed at th
EE 4389W
Homework 2 (10 pts)
Due date: Oct 4, 2011
Fall 2011
Topic: Model selection and complexity control
This homework illustrates the use of resampling methods for model selection (complexity
control), and for comparing prediction accuracy of a learnin
1
EE 4389
Homework 3 (10 pts)
Due date: Nov. 3, 2011
F 2011
Trading international mutual funds
Background: this HW applies predictive data-analytic methods to frequent trading of international
mutual funds. This practice called timing of mutual funds atte
EE 4389W
Homework 4 (10 pts)
Due date: Nov 15, 2011
Topic: Nonlinear classification and regression methods
Fall 2011
Problem 1: Classification
(a) Estimate predictive model for presidential elections using Year 2000 election results
as training data. Esti
Introduction to
Predictive Learning
LECTURE SET 6
Neural Network Learning
Electrical and Computer Engineering
1
OUTLINE
Objectives
- introduce biologically inspired NN learning methods for
clustering, regression and classification
- explain similarities a