Professional Documents
Culture Documents
CSC551 Lecture1 Introduction
CSC551 Lecture1 Introduction
Lecture 1
Instructor
Lin-Ching Chang
1
Something you want to know….
Grading
Homework, Quiz & Class participation
Exam
1 midterm and 1 final examinations
Term project
Project presentation (10%)
Final report & code (20%)
Weight (%)
Homework & Quiz 20%
Project 30%
Midterm 20%
Final Exam 30%
2
Textbooks (option)
Easy to read but limited information.
3
Textbooks (option)
Pattern Recognition and Machine Introduction to Statistical Pattern
Learning (Information Science Recognition (Computer Science &
and Statistics) by Christopher M. Scientific Computing) 2nd Edition
Bishop by Keinosuke Fukunaga
4
Textbooks (option)
Pattern Classification (2nd ed) Pattern Recognition, Fourth
by R. O. Duda, P. E. Hart and Edition by Sergios Theodoridis
D. G. Stork, John Wiley & and Konstantinos Koutroumbas,
Sons, 2000 Academic Press, 2008
5
Machine Learning
Learning/training: build a classification or regression rule
from a set of samples
6
What is pattern recognition?
The task: we assign labels to unknown objects.
Assign unknown objects – patterns – into the correct
class. This is known as classification.
The question: P belongs to which class?
7
What is pattern recognition?
Definitions from the literature
“The assignment of a physical object or event to one of several pre-
specified categories” –Duda and Hart
“A problem of estimating density functions in a high-dimensional
space and dividing the space into the regions of categories or
classes” – Fukunaga
“Given some examples of complex signals and the correct
decisions for them, make decisions automatically for a stream of
future examples” –Ripley
“The science that concerns the description or classification
(recognition) of measurements” –Schalkoff
“The process of giving names ω to observations x”, –Schürmann
Pattern Recognition is concerned with answering the question
“What is this?” –Morse
8
What is pattern?
9
Examples of pattern recognition tasks
10
Machine Perception
12
Application: Fraud and Risk
Detection
Over the years, banking companies learned to
divide and conquer data via customer profiling,
past expenditures and other essential variables
to analyze the probabilities of risk and default.
13
Application: Image Recognition
You upload your image with friends on Facebook and
you start getting suggestions to tag your friends. This
automatic tag suggestion feature uses face recognition
algorithm.
14
Application: Character recognition
15
16
Application: Finger prints recognition
17
Application:
Image Segmentation/
Brain Segmentation
18
Application: Brain Tissue Segmentation
19
Sony IPT-DS1 Party-Shot
What’s the definition
of a smile?
21
Data Scientist – again, best job in
America for 2017
22
Software Developer - best job in
America for 2018
23
24
Components of a pattern recognition system
25
The pattern recognition design cycle
Data collection
Probably the most time-intensive component of a PR
project
How many examples are enough?
26
Data sets can be used for pattern
recognition project
UC Irvine: more than 200 sets available for downloading
http://archive.ics.uci.edu/ml/datasets.html
27
The pattern recognition design cycle
Data collection
Probably the most time-intensive component of a PR project
How many examples are enough?
Feature choice
Critical to the success of the PR problem
“Garbage in, garbage out”
Requires basic prior knowledge
Model choice
Statistical, neural and structural approaches
Parameter settings
Training
Given a feature set and a “blank” model, adapt the model to explain
the data
Supervised, unsupervised and reinforcement learning
Evaluation
How well does the trained model do?
Overfitting vs. generalization
28
Consider the following scenario
A fish processing plan wants to automate the process of sorting
incoming fish according to species (salmon or sea bass)
The automation system consists of
a conveyor belt for incoming products
two conveyor belts for sorted products
a pick-and-place robotic arm
a vision system with an overhead CCD camera
a computer to analyze images and control the robot arm
29
From [Duda, Hart and Stork, 2001]
An Example from the Book
Sea bass
Species
Salmon
Lightness Width
Next class
Background review
linear algebra
probability and statistics
39
Term project
40
The Catholic University of America
Fall 2018
Instructor
Lin-Ching Chang
41
Step 1
Download the Python 3.X version of the Anaconda distribution for
your operating system.
https://www.anaconda.com/download/
42
Step 1
If you already have Python installed. You can install other 3rd party
library by using tools such as pip or conda
You can still install Anaconda if you have Python installed already.
Anaconda is installed in its own directory, so both installations
shouldn't interfere at all.
The only problem you could encounter is if you add Anaconda to
your PATH environment variable, which will make it the default
Python in your system.
There's an option in the installer which let's you decide if you
want to accept that change or not.
43
Python Libraries you may need
Scikit-Learn
Machine Learning in Python.
Numpy
Numpy will help you to manage multi-dimensional arrays very
efficiently.
Scipy
Numerical routines such as integration, interpolation,
optimization, etc.
Many routines in Scikit-Learn library highly relies on it.
Pandas
Pandas is the “SQL of Python
45
Step 3
Installing Packages (if you still need some more)
46
You are good to go
47