CEC435 Lecture 3 - Supervised, Unsupervised & Reinforcement Learning PDF

SUPERVISED VS UNSUPERVISED VS REINFORCED LEARNING 3  What is Supervised Learning  Also called inductive learning  Given: training data + desired output (label)  Supervised learning is analogous to training a child to walk. You will hold the child’s hand, show him how to t...

SUPERVISED VS UNSUPERVISED VS REINFORCED LEARNING 3  What is Supervised Learning  Also called inductive learning  Given: training data + desired output (label)  Supervised learning is analogous to training a child to walk. You will hold the child’s hand, show him how to take his foot forward, walk yourself for a demonstration and so on , until the child learns to walk on his own  Supervised learning algorithms are trained using labelled examples.  For example, a text segment might have a category label like;  Spam vs. legal email  Positive vs. negative movie review  Supervised learning is used in applications were historical data predict likely 4 future events  Types of Supervised Learning 1. Regression A regression problem is when the output is a real or continues value, such as “salary” or “weight”. Many models can be used, the simplest is the linear regression. It tries to fit data with the best hyper-plane which goes through the points 5  Types of Supervised Learning cont. Types of Regression Models 6  Types of Supervised Learning cont. Examples of Regression Models  Predicting the age of a person  Predicting nationality  Forecasting stock prices  Handwriting recognition  Acoustic signal processing If for example there is a housing data set and we want to predict the price of the house, we can predict the if we are given the code, the following might be the output 7  Types of Supervised Learning 2. Classification Classification is a form of “pattern recognition”. Classification algorithms applied to the training data find the same pattern (similar number sequence, words or sentiments, and the like) in future data sets. 8 9  What is Unsupervised Learning In unsupervised learning, an AI system is presented with unlabeled, uncategorized data and the systems’ algorithm act on the data without prior training. The output is dependent upon the coded algorithm. Subjecting a system to unsupervised learning is one way of testing AI. 10  Types of Unsupervised Learning 1. Clustering A clustering problem is when you want to discover the inherent groupings in the data, such as grouping customers by purchasing behavior 2. Association A association rule problem is when you want to discover the rules that describe large portions of your data, such as people that buy X also tend to buy Y 11  What is Reinforced Learning Reinforcement Learning(RL) is a type of machine learning technique that enables an agent to learn in an interactive environment by trial and error using feedback from its own actions and experiences. 14 Considering training a pet dog to bring a ball to us, we throw the ball at a distance and ask the dog to bring it to us. Every time the dog does this right, we reward the dog. Slowly, the dog learns that doing the job rightly gives him a reward and then the dog starts doing the job right way every time in future.