Question? Leave a message!




Learning from Observations

learning from observations in artificial intelligence and learning from dependent observations
Dr.BenjaminClark Profile Pic
Dr.BenjaminClark,United States,Teacher
Published Date:21-07-2017
Website URL
Comment
Learning from Observations Chapter 18 Sections 1-3 CS 3243 - Learning 1 Outline   Learning   Hypothesis Spaces   Learning Algorithms   K Nearest Neighbors   Decision Trees   Naïve Bayes   Not really described in the text well   Training and Testing CS 3243 - Learning 2 What is Learning   Memorizing something   Learning facts through observation and exploration   Generalizing a concept from experience “Learning denotes changes in the system that are adaptive in the sense that they enable the system to do the task or tasks drawn from the same population more efficiently and more effectively the next time” – Herb Simon CS 3243 - Learning 3 Why is it necessary? Three reasons:   Unknown environment – need to deploy an agent in an unfamiliar territory   Save labor – we may not have the resources to encode knowledge   Can’t explicitly encode knowledge – may lack the ability to articulate necessary knowledge. CS 3243 - Learning 4 Learning agents CS 3243 - Learning 5 Learning element   Design of a learning element is affected by   Which components of the performance element are to be learned   What feedback is available to learn these components   What representation is used for the components   Type of feedback:   Supervised learning: correct answers for each example   Unsupervised learning: correct answers not given   Reinforcement learning: occasional rewards CS 3243 - Learning 6 Induction   Making predictions about the future based on the past. If asked why we believe the sun will rise tomorrow, we shall naturally answer, “Because it has always risen every day.” We have a firm belief that it will rise in the future, because it has risen in the past. – Bertrand Russell   Is induction sound? Why believe that the future will look similar to the past? CS 3243 - Learning 7 Inductive learning   Simplest form: learn a function from examples f is the target function An example is a pair (x, f(x)) Problem: find a hypothesis h such that h ≈ f given a training set of examples This is a highly simplified model of real learning:   Ignores prior knowledge   Assumes examples are given CS 3243 - Learning 8 Inductive learning method   Memorization   Noise   Unreliable function   Unreliable sensors CS 3243 - Learning 9 Inductive learning method   Construct/adjust h to agree with f on training set   (h is consistent if it agrees with f on all examples)   E.g., curve fitting: CS 3243 - Learning 10 Inductive learning method   Construct/adjust h to agree with f on training set   (h is consistent if it agrees with f on all examples)   E.g., curve fitting: CS 3243 - Learning 11 Inductive learning method   Construct/adjust h to agree with f on training set   (h is consistent if it agrees with f on all examples)   E.g., curve fitting: CS 3243 - Learning 12 Inductive learning method   Construct/adjust h to agree with f on training set   (h is consistent if it agrees with f on all examples)   E.g., curve fitting: CS 3243 - Learning 13 Inductive learning method   Construct/adjust h to agree with f on training set   (h is consistent if it agrees with f on all examples)   E.g., curve fitting: CS 3243 - Learning 14 Inductive learning method   Construct/adjust h to agree with f on training set   (h is consistent if it agrees with f on all examples)   E.g., curve fitting:   Ockham’s razor: prefer the simplest hypothesis consistent with data CS 3243 - Learning 15 An application: Ad blocking CS 3243 - Learning 16 height Learning Ad blocking   Width and height of image   Binary Classification: Ad or ¬Ad? – – – – – – – – – – – + + – – – + + + – – width CS 3243 - Learning 17 height Nearest Neighbor   A type of instance based learning   Remember all of the past instances   Use the nearest old data point as answer – – – – – – – – – – ? – + + – – – + + + – – width   Generalize to kNN, that is take the average class of the closest k neighbors. CS 3243 - Learning 18 Application: Eating out Problem: Decide on a restaurant, based on the following attributes: 1.  Alternate: is there an alternative restaurant nearby? 2.  Bar: is there a comfortable bar area to wait in? 3.  Fri/Sat: is today Friday or Saturday? 4.  Hungry: are we hungry? 5.  Patrons: number of people in the restaurant (None, Some, Full) 6.  Price: price range (, , ) 7.  Raining: is it raining outside? 8.  Reservation: have we made a reservation? 9.  Type: kind of restaurant (French, Italian, Thai, Burger) 10.  WaitEstimate: estimated waiting time (0-10, 10-30, 30-60, 60) CS 3243 - Learning 19 Attribute representation   Examples described by attribute or feature values (Boolean, discrete, continuous)   E.g., situations where I will/won't wait for a table:   Classification of examples is positive (T) or negative (F) CS 3243 - Learning 20