Learning from Data. Learning from Data Learning sensors actuators environment agent ? As an agent interacts with the world, it should learn about its.

Slides:



Advertisements
Similar presentations
Introduction to Machine Learning BITS C464/BITS F464
Advertisements

Learning from Observations Chapter 18 Section 1 – 3.
More probability CS151 David Kauchak Fall 2010 Some material borrowed from: Sara Owsley Sood and others.
Decision making in episodic environments
Machine Learning Group University College Dublin Decision Trees What is a Decision Tree? How to build a good one…
Learning from Observations Chapter 18 Section 1 – 4.
Introduction to Machine Learning course fall 2007 Lecturer: Amnon Shashua Teaching Assistant: Yevgeny Seldin School of Computer Science and Engineering.
Supervised Learning & Classification, part I Reading: DH&S, Ch 1.
Learning: Introduction and Overview
Redaction: redaction: PANAKOS ANDREAS. An Interactive Tool for Color Segmentation. An Interactive Tool for Color Segmentation. What is color segmentation?
Supervised Learning & Classification, part I Reading: W&F ch 1.1, 1.2, , 3.2, 3.3, 4.3, 6.1*
K-means Based Unsupervised Feature Learning for Image Recognition Ling Zheng.
Machine learning Image source:
Introduction to machine learning
Introduction to Data Mining Engineering Group in ACL.
CS Machine Learning. What is Machine Learning? Adapt to / learn from data  To optimize a performance function Can be used to:  Extract knowledge.
Machine learning Image source:
Machine Learning CPS4801. Research Day Keynote Speaker o Tuesday 9:30-11:00 STEM Lecture Hall (2 nd floor) o Meet-and-Greet 11:30 STEM 512 Faculty Presentation.
1 What is learning? “Learning denotes changes in a system that... enable a system to do the same task more efficiently the next time.” –Herbert Simon “Learning.
Mehdi Ghayoumi Kent State University Computer Science Department Summer 2015 Exposition on Cyber Infrastructure and Big Data.
INTRODUCTION TO MACHINE LEARNING. $1,000,000 Machine Learning  Learn models from data  Three main types of learning :  Supervised learning  Unsupervised.
Inductive learning Simplest form: learn a function from examples
Machine Learning An Introduction. What is Learning?  Herbert Simon: “Learning is any process by which a system improves performance from experience.”
LEARNING DECISION TREES Yılmaz KILIÇASLAN. Definition - I Decision tree induction is one of the simplest, and yet most successful forms of learning algorithm.
Learning from Observations Chapter 18 Through
CHAPTER 18 SECTION 1 – 3 Learning from Observations.
Pattern Recognition April 19, 2007 Suggested Reading: Horn Chapter 14.
Visual Information Systems Recognition and Classification.
L6. Learning Systems in Java. Necessity of Learning No Prior Knowledge about all of the situations. Being able to adapt to changes in the environment.
Intelligent Database Systems Lab Presenter : Chang,Chun-Chih Authors : Youngjoong Ko, Jungyun Seo 2009, IPM Text classification from unlabeled documents.
Machine learning Image source:
Machine Learning Chapter 18, 21 Some material adopted from notes by Chuck Dyer.
Chapter 18 Section 1 – 3 Learning from Observations.
Learning From Observations Inductive Learning Decision Trees Ensembles.
Introduction to Classification & Clustering Villanova University Machine Learning Lab Module 4.
Decision Tree Learning CMPT 463. Reminders Homework 7 is due on Tuesday, May 10 Projects are due on Tuesday, May 10 o Moodle submission: readme.doc and.
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Artificial Intelligence
Learning from Observations
Learning from Observations
Machine learning Image source:
Introduction to Classification & Clustering
Introduce to machine learning
Machine Learning overview Chapter 18, 21
Machine Learning overview Chapter 18, 21
Ananya Das Christman CS311 Fall 2016
Presented By S.Yamuna AP/CSE
Introduction to Data Science Lecture 7 Machine Learning Overview
Learning from Data.
Introductory Seminar on Research: Fall 2017
Supervised Learning Seminar Social Media Mining University UC3M
Machine Learning Ali Ghodsi Department of Statistics
AV Autonomous Vehicles.
What is Pattern Recognition?
Machine Learning Week 1.
Decision making in episodic environments
Supervised vs. unsupervised Learning
Classification and Prediction
Learning from Observations
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Basics of ML Rohan Suri.
Using Manifold Structure for Partially Labeled Classification
Learning from Observations
Machine Learning: Decision Tree Learning
Machine Learning overview Chapter 18, 21
Decision Trees - Intermediate
Pattern Recognition and Training
Pattern Recognition and Training
Presentation transcript:

Learning from Data

Learning sensors actuators environment agent ? As an agent interacts with the world, it should learn about its environment

APPLE APPLE BANANA BANANA APPLE Supervised learning: given labeled data…

Supervised Learning APPLE or BANANA? …learn to classify (label) new example

Unsupervised Learning Unsupervised learning: Given unlabeled data…

Unsupervised Learning …put examples into groups (Clustering)…

Unsupervised Learning ? Given new example, put it into a group.

Focus on Supervised Learning first… Given previous data, how can we “learn” to classify new data?

APPLE APPLE BANANA BANANA APPLE or BANANA? APPLE

Training Training Set

Training Training Set Extract features/ labels

Training Training Set Extract features/ labels Train

Learned model/ Classifier Training Learned model/ Classifier Training Set Extract features/ labels Train

Learned model/ Classifier Training Learned model/ Classifier Training Set Extract features/ labels Train Classifying Instance/Example

Learned model/ Classifier Training Learned model/ Classifier Training Set Extract features/ labels Train Classifying Instance/Example Extract features

Training Classifying Learned model/ Classifier Training Set Extract features/ labels Train Classifying Learned model/ Classifier Instance/Example Extract features

Training Classifying Learned model/ Classifier Training Set Extract features/ labels Train Classifying Learned model/ Classifier Label Instance/Example Extract features

Inductive Learning Generalize (learn) from a training set to make predictions on future test sets.

Inductive Learning Generalize (learn) from a training set to make predictions on future test sets. Supervised Learning: Training data is a set of (x, y) pairs x: input example/instance y: output/label Learn an unknown function f such that f(x)=y

Inductive Learning Generalize (learn) from a training set to make predictions on future test sets. Supervised Learning: Training data is a set of (x, y) pairs x: input example/instance y: output/label Learn an unknown function f(x)=y x represented by D-dimensional feature vector x = < x1 , x2 , x3 ,…, xD > Each dimension is a feature or attribute

Some examples image classification text classification does the image contain a person? apple? banana? text classification is this a good/bad review? is this article about sports or politics? is this e-mail spam? character recognition is this set of scribbles an ‘a’, ‘b’, ‘c’, … credit card transactions fraud or not? Many problems!!!

Another example Database of 20,000 images of handwritten digits, each labeled by a human This is perhaps the most well-studied data set in ML… handwritten digits, part of zipcodes scanned off envelopes by the post office. Use these to train a classifier which will label digit-images

Another example Database of 20,000 images of handwritten digits, each labeled by a human This is perhaps the most well-studied data set in ML… handwritten digits, part of zipcodes scanned off envelopes by the post office. Each image is of size 28x28 pixels. Labels are 0-9. Features?

Another example Database of 20,000 images of handwritten digits, each labeled by a human This is perhaps the most well-studied data set in ML… handwritten digits, part of zipcodes scanned off envelopes by the post office. Features are RGB values for each pixel 28x28 features, values ranging from 0 to 255

Wait for a Table? An intelligent agent that tells us if we should wait for a table at a restaurant How to apply supervised learning here?

Wait for a Table? An intelligent agent that tells us if we should wait for a table at a restaurant How to apply supervised learning here? What features should we consider?

Wait for a table? Alternate restaurant nearby? Comfy bar to wait at? Is it Friday? How hungry are we? How full is it? How expensive is it? What’s the weather like? Do we have reservations? Type of food? Estimated wait time? Features/Attributes

Wait for a Table?

Wait for a Table? How to organize/visualize this data? (Note that each attribute has a finite set of possibilities)

Alternate Restaurant. T or F Bar. T or F How full Alternate Restaurant? T or F Bar? T or F How full? Some, Full, pr None Prince? $, $$, $$$, or $$$$ Estimated Wait Time: 0-10, 10-30, 30-60, >60

All examples with Patrons=None were No Patrons = Some were Yes Examples with Patrons = Full depended on other features

Decision Trees

How to classify new example? All examples with Patrons=None were No Patrons = Some were Yes Examples with Patrons = Full depended on other features

How to classify new example? All examples with Patrons=None were No Patrons = Some were Yes Examples with Patrons = Full depended on other features

Classifying a New Example