Overview
- Authors:
-
-
Vasantha Kalyani David
-
Avinashilingam Deemed University , India
-
Sundaramoorthy Rajasekaran
-
PSG College of Technology, India
- Recent research in Pattern recognition using neural and functional networks
Access this book
Other ways to access
Table of contents (11 chapters)
-
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 1-7
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 9-13
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 15-26
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 27-49
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 51-71
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 73-91
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 93-113
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 115-122
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 123-134
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 135-136
-
- Vasantha Kalyani David, Sundaramoorthy Rajasekaran
Pages 137-137
-
About this book
Biologically inspiredcomputing isdi?erentfromconventionalcomputing.Ithas adi?erentfeel; often the terminology does notsound like it’stalkingabout machines.The activities ofthiscomputingsoundmorehumanthanmechanistic as peoplespeak ofmachines that behave, react, self-organize,learn, generalize, remember andeven to forget.Much ofthistechnology tries to mimic nature’s approach in orderto mimicsome of nature’s capabilities.They havearigorous, mathematical basisand neuralnetworks forexamplehaveastatistically valid set on which the network istrained. Twooutlinesaresuggestedasthepossibletracksforpatternrecognition.They are neuralnetworks andfunctionalnetworks.NeuralNetworks (many interc- nected elements operating in parallel) carryout tasks that are not only beyond the scope ofconventionalprocessing but also cannotbeunderstood in the same terms.Imagingapplicationsfor neuralnetworksseemtobea natural?t.Neural networks loveto do pattern recognition. A new approachto pattern recognition usingmicroARTMAP together with wavelet transforms in the context ofhand written characters,gestures andsignatures havebeen dealt.The KohonenN- work,Back Propagation Networks andCompetitive Hop?eld NeuralNetwork havebeen considered for various applications. Functionalnetworks,beingageneralizedformofNeuralNetworkswherefu- tionsarelearnedratherthanweightsiscomparedwithMultipleRegressionAn- ysisforsome applicationsandtheresults are seen to be coincident. New kinds of intelligence can be added to machines, and we will havethe possibilityof learningmore about learning.Thus our imaginationsand options are beingstretched.These new machines will be fault-tolerant,intelligentand self-programmingthustryingtomakethemachinessmarter.Soastomakethose who use the techniques even smarter. Chapter1isabrief introduction toNeural and Functionalnetworks in the context of Patternrecognitionusing these disciplinesChapter2 givesa review ofthearchitectures relevantto the investigation andthedevelopment ofthese technologies in the past few decades. Retracted VIII Preface Chapter3begins with the lookattherecognition ofhandwritten alphabets usingthealgorithm for ordered list ofboundary pixelsas well as the Ko- nenSelf-Organizing Map (SOM).Chapter 4 describes the architecture ofthe MicroARTMAP and its capability.