{"id":{"repo_id":"london-metro","oai_identifier":"oai:repository.londonmet.ac.uk:7520"},"canonical_url":"https://search.dev.ndltd.org/etd/london-metro/oai:repository.londonmet.ac.uk:7520","repository":{"repo_id":"london-metro","name":"London Metropolitan University","base_url":"https://repository.londonmet.ac.uk/cgi/oai2"},"display":{"title":"Adaptive function modal learning neural networks","abstract":"Modal learning method is a neural network learning term that refers to a single neural network which combines with more than one mode of learning. It aims to achieve more powerful learning results than a neural network combines with only one single mode of learning. This thesis introduces a novel modal learning Adaptive Function Neural Network (ADFUNN) with the aim to overcome the linear inseparability limitation in a single weight layer supervised network. Adaptation in the function mode of learning within individual neurons is carried out in parallel with the traditional weights adaptation mode of learning between neurons; thus producing a more powerful, flexible form of learning. ADFUNN employs modifiable linear piecewise neuron activation functions and meanwhile adapts the weights using a modified delta learning rule. Experimental results show the single layer ADFUNN is highly effective at assimilating and generalising on many linearly inseparable problems, such as the Iris dataset, and a natural language phrase recognition task. A multi-layer approach, a Multi-layer ADFUNN (MADFUNN) is introduced to solve highly complex datasets. It aims to find a suitably restricted subset of neuron activation functions which has a good representational capacity and enables efficient learning for complex models with large datasets. Experiments on analytical function recognition and letter image recognition are solved by MADFUNN with high levels of recognition. In order to further explore modal learning, ADFUNN is combined with an unsupervised modal learning neural network called Snap-Drift (Palmer-Brown and Lee) to create a Snap-drift ADFUNN (SADFUNN). It is used to solve an optical and pen-based handwritten digit recognition task from the DCI machine learning repository and exhibits more powerful generalisation ability than the MLPs. An additional benefit of ADFUNN, as well as a MADFUNN and SADFUNN, is that the learned functions can support intelligent data analysis. These learned activation function curves reveal many useful information about the data.","abstract_html":"Modal learning method is a neural network learning term that refers to a single neural network which combines with more than one mode of learning. It aims to achieve more powerful learning results than a neural network combines with only one single mode of learning. This thesis introduces a novel modal learning Adaptive Function Neural Network (ADFUNN) with the aim to overcome the linear inseparability limitation in a single weight layer supervised network. Adaptation in the function mode of learning within individual neurons is carried out in parallel with the traditional weights adaptation mode of learning between neurons; thus producing a more powerful, flexible form of learning. ADFUNN employs modifiable linear piecewise neuron activation functions and meanwhile adapts the weights using a modified delta learning rule. Experimental results show the single layer ADFUNN is highly effective at assimilating and generalising on many linearly inseparable problems, such as the Iris dataset, and a natural language phrase recognition task. A multi-layer approach, a Multi-layer ADFUNN (MADFUNN) is introduced to solve highly complex datasets. It aims to find a suitably restricted subset of neuron activation functions which has a good representational capacity and enables efficient learning for complex models with large datasets. Experiments on analytical function recognition and letter image recognition are solved by MADFUNN with high levels of recognition. In order to further explore modal learning, ADFUNN is combined with an unsupervised modal learning neural network called Snap-Drift (Palmer-Brown and Lee) to create a Snap-drift ADFUNN (SADFUNN). It is used to solve an optical and pen-based handwritten digit recognition task from the DCI machine learning repository and exhibits more powerful generalisation ability than the MLPs. An additional benefit of ADFUNN, as well as a MADFUNN and SADFUNN, is that the learned functions can support intelligent data analysis. These learned activation function curves reveal many useful information about the data.","abstract_has_math":false,"creators":["Kang, Miao"],"institution":"London Metropolitan University","degree_name":"phd","degree_level":"doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011","date_published":"2011","updated_at":"2026-07-24T02:54:41Z","subjects":["000 Computer science, information & general works"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.grantnumber","label":"Dc Identifier Grantnumber","values":["N/A"],"render_values":[{"text":"N/A","href":null,"code":true}]}]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.sponsor","label":"Sponsor","values":["London Metropolitan University"]},{"key":"dc:creator","label":"Author","values":["Kang, Miao"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2011"]},{"key":"dc:date.issued","label":"Date","values":["2011"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["School of Computing and Digital Media (SCDM)","Faculty of Computing"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["London Metropolitan University"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://repository.londonmet.ac.uk/7520/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["phd"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["000 Computer science, information & general works"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.grantnumber","label":"Dc Identifier Grantnumber","values":["N/A"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://repository.londonmet.ac.uk/7520/1/536730.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Modal learning method is a neural network learning term that refers to a single neural network which combines with more than one mode of learning. It aims to achieve more powerful learning results than a neural network combines with only one single mode of learning. This thesis introduces a novel modal learning Adaptive Function Neural Network (ADFUNN) with the aim to overcome the linear inseparability limitation in a single weight layer supervised network. Adaptation in the function mode of learning within individual neurons is carried out in parallel with the traditional weights adaptation mode of learning between neurons; thus producing a more powerful, flexible form of learning. ADFUNN employs modifiable linear piecewise neuron activation functions and meanwhile adapts the weights using a modified delta learning rule. Experimental results show the single layer ADFUNN is highly effective at assimilating and generalising on many linearly inseparable problems, such as the Iris dataset, and a natural language phrase recognition task. A multi-layer approach, a Multi-layer ADFUNN (MADFUNN) is introduced to solve highly complex datasets. It aims to find a suitably restricted subset of neuron activation functions which has a good representational capacity and enables efficient learning for complex models with large datasets. Experiments on analytical function recognition and letter image recognition are solved by MADFUNN with high levels of recognition. In order to further explore modal learning, ADFUNN is combined with an unsupervised modal learning neural network called Snap-Drift (Palmer-Brown and Lee) to create a Snap-drift ADFUNN (SADFUNN). It is used to solve an optical and pen-based handwritten digit recognition task from the DCI machine learning repository and exhibits more powerful generalisation ability than the MLPs. An additional benefit of ADFUNN, as well as a MADFUNN and SADFUNN, is that the learned functions can support intelligent data analysis. These learned activation function curves reveal many useful information about the data."]},{"key":"dc:format","label":"Dc Format","values":["text"]},{"key":"dc:title","label":"Title","values":["Adaptive function modal learning neural networks"]}]}],"canonical_facts":{"dc:contributor.sponsor":["London Metropolitan University"],"dc:creator":["Kang, Miao"],"dc:date":["2011"],"dc:date.issued":["2011"],"dc:description.abstract":["Modal learning method is a neural network learning term that refers to a single neural network which combines with more than one mode of learning. It aims to achieve more powerful learning results than a neural network combines with only one single mode of learning. This thesis introduces a novel modal learning Adaptive Function Neural Network (ADFUNN) with the aim to overcome the linear inseparability limitation in a single weight layer supervised network. Adaptation in the function mode of learning within individual neurons is carried out in parallel with the traditional weights adaptation mode of learning between neurons; thus producing a more powerful, flexible form of learning. ADFUNN employs modifiable linear piecewise neuron activation functions and meanwhile adapts the weights using a modified delta learning rule. Experimental results show the single layer ADFUNN is highly effective at assimilating and generalising on many linearly inseparable problems, such as the Iris dataset, and a natural language phrase recognition task. A multi-layer approach, a Multi-layer ADFUNN (MADFUNN) is introduced to solve highly complex datasets. It aims to find a suitably restricted subset of neuron activation functions which has a good representational capacity and enables efficient learning for complex models with large datasets. Experiments on analytical function recognition and letter image recognition are solved by MADFUNN with high levels of recognition. In order to further explore modal learning, ADFUNN is combined with an unsupervised modal learning neural network called Snap-Drift (Palmer-Brown and Lee) to create a Snap-drift ADFUNN (SADFUNN). It is used to solve an optical and pen-based handwritten digit recognition task from the DCI machine learning repository and exhibits more powerful generalisation ability than the MLPs. An additional benefit of ADFUNN, as well as a MADFUNN and SADFUNN, is that the learned functions can support intelligent data analysis. These learned activation function curves reveal many useful information about the data."],"dc:format":["text"],"dc:identifier.grantnumber":["N/A"],"dc:identifier.uri":["https://repository.londonmet.ac.uk/7520/1/536730.pdf"],"dc:publisher.department":["School of Computing and Digital Media (SCDM)","Faculty of Computing"],"dc:publisher.institution":["London Metropolitan University"],"dc:relation.isreferencedby":["https://repository.londonmet.ac.uk/7520/"],"dc:subject":["000 Computer science, information & general works"],"dc:title":["Adaptive function modal learning neural networks"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["doctoral"],"dc:type.qualificationname":["phd"]},"updated_at":"2026-07-24T02:54:41Z"}