Learning Systems Learning Systems Chapter 5 Chapter 5 Dr Ahmed Rafea Rafea Dr Ahmed
Overview Overview � One central element of intelligent behavior One central element of intelligent behavior � is the ability to adapt or learn from is the ability to adapt or learn from experience. experience. � Adding learning or adaptive behavior to an Adding learning or adaptive behavior to an � intelligent agent elevates it to a higher intelligent agent elevates it to a higher level of ability. level of ability.
Forms of learning Forms of learning � Rote Learning: Rote Learning: based on memorization of � based on memorization of examples examples � Parameter or weight adjustment: Parameter or weight adjustment: how to � how to weight the contribution of important decision weight the contribution of important decision factors to the answer. This technique is the basis factors to the answer. This technique is the basis of Neural Network of Neural Network � Induction: Induction: extraction of important � extraction of important characteristics of the problem to build a model characteristics of the problem to build a model that can be used to predict new situations. that can be used to predict new situations. � Clustering: Clustering: A way to organize similar patterns � A way to organize similar patterns into groups into groups
Data Mining Data Mining � All these learning techniques, including induction All these learning techniques, including induction � and clustering, are used in data mining. and clustering, are used in data mining. � Data mining is a process of extracting valuable , Data mining is a process of extracting valuable , � non non- -obvious information from large collection of obvious information from large collection of data. data. � The main contribution of data mining is to find The main contribution of data mining is to find � patterns which were not known to exist (finding patterns which were not known to exist (finding new information or knowledge) new information or knowledge) � Therefore, learning as applied to data mining, Therefore, learning as applied to data mining, � can be thought of as a way for intelligent agents can be thought of as a way for intelligent agents to automatically discover knowledge rather than to automatically discover knowledge rather than having it predefined. having it predefined.
Learning Paradigms Learning Paradigms � Supervised Learning: It relies on a teacher that Supervised Learning: It relies on a teacher that � provides the input data as well as the desired provides the input data as well as the desired solution (also known as programming by solution (also known as programming by example) example) � Unsupervised Learning: It depends on input data Unsupervised Learning: It depends on input data � only and makes no demand on knowing the only and makes no demand on knowing the solution solution � Reinforcement learning : A kind of Supervised Reinforcement learning : A kind of Supervised � Learning used when explicit input/ output pairs Learning used when explicit input/ output pairs of training data are not available of training data are not available
Online & Offline Learning Online & Offline Learning � Online Learning: Online Learning: It means that the agent � It means that the agent is sent out to perform its tasks and that it is sent out to perform its tasks and that it can adapt after each transaction is can adapt after each transaction is processed. processed. � Offline learning: Offline learning: It involves saving data � It involves saving data while the agent is working and using the while the agent is working and using the data later to train the agent. data later to train the agent.
Neural Networks Neural Networks � Neural Networks are parallel computing models Neural Networks are parallel computing models � that adapt when presented with training data. that adapt when presented with training data. � They operate in Supervised, Unsupervised and They operate in Supervised, Unsupervised and � Reinforcement learning modes. Reinforcement learning modes. � A neural network is comprised of a set of simple A neural network is comprised of a set of simple � processing units and a set of adaptive , real- - processing units and a set of adaptive , real valued connection weights. valued connection weights. � Learning in neural networks is accomplished Learning in neural networks is accomplished � through the adjustment of the connection through the adjustment of the connection weights. weights.
Back Propagation Back Propagation � Back propagation is the most popular neural Back propagation is the most popular neural � network architecture for supervised learning . network architecture for supervised learning . � It features a feed It features a feed- -forward connection topology , forward connection topology , � meaning that data flows through the network in a meaning that data flows through the network in a single direction , and uses a technique called the single direction , and uses a technique called the backward propagation of errors to adjust backward propagation of errors to adjust connection weights . connection weights . � The primary applications of back The primary applications of back- -propagation propagation � networks are for prediction and classification. networks are for prediction and classification.
Back Propagation Back Propagation This diagram illustrates the three major This diagram illustrates the three major steps of the training process: steps of the training process: � Input data is presented to the input layer of Input data is presented to the input layer of � units and flows in the network till reaching units and flows in the network till reaching output units. output units. � The difference between the desired and The difference between the desired and � the actual output is computed, producing the actual output is computed, producing the network error. the network error. � This error is then passed backwards This error is then passed backwards � through the network to adjust the through the network to adjust the connection weights. connection weights.
Kohonen Maps Kohonen Maps � Kohonen map networks are unsupervised , Kohonen map networks are unsupervised , � single single- -layer neural networks comprised of an layer neural networks comprised of an input layer and an output layer. input layer and an output layer. � Each time an input vector is presented to the Each time an input vector is presented to the � network, its distance to each unit in the output network, its distance to each unit in the output layer is computed using Euclidean distance. layer is computed using Euclidean distance. � Kohonen map networks self Kohonen map networks self- -organize and learn organize and learn � to map similar inputs into output units that are in to map similar inputs into output units that are in close proximity to each other. close proximity to each other. � They have become one of the most popular and They have become one of the most popular and � practical neural network models. practical neural network models.
Decision Trees- -1 1 Decision Trees � Decision trees can be defined as structures that Decision trees can be defined as structures that � consist of consist of � Leaf nodes, representing a class, and Leaf nodes, representing a class, and � Decision nodes, where a test is to be carried out on a Decision nodes, where a test is to be carried out on a single attribute value, with one branch for each possible single attribute value, with one branch for each possible outcome of the test. outcome of the test. � Decision trees perform induction on example data Decision trees perform induction on example data � sets, generating classifiers and prediction models sets, generating classifiers and prediction models � A decision tree examines the data set and uses A decision tree examines the data set and uses � information theory to determine which attribute information theory to determine which attribute contains the most information on which to base a contains the most information on which to base a decision. decision.
A Training Set: “ “Play/Don Play/Don’ ’t Play t Play” ” A Training Set: No. No. Outlook Outlook Temperature Temperature Humidity Humidity Windy Windy Class Class 1 sunny hot high false N 1 sunny hot high false N 2 sunny hot high true N 2 sunny hot high true N 3 overcast hot high false P 3 overcast hot high false P 4 4 rain rain mild mild high high false false P P 5 5 rain rain cool cool normal normal false false P P 6 rain cool normal true N 6 rain cool normal true N 7 overcast cool normal true P 7 overcast cool normal true P 8 sunny mild high false N 8 sunny mild high false N 9 9 sunny sunny cool cool normal normal false false P P 10 rain mild normal false P 10 rain mild normal false P 11 sunny mild normal true P 11 sunny mild normal true P 12 overcast mild high true P 12 overcast mild high true P 13 overcast hot normal false P 13 overcast hot normal false P 14 14 rain rain mild mild high high true true N N
Recommend
More recommend
