{"id":{"repo_id":"edithcowan","oai_identifier":"oai:ro.ecu.edu.au:theses-1790"},"canonical_url":"https://search.dev.ndltd.org/etd/edithcowan/oai:ro.ecu.edu.au:theses-1790","repository":{"repo_id":"edithcowan","name":"Edith Cowan University","base_url":"https://ro.ecu.edu.au/do/oai/"},"display":{"title":"A generalised feedforward neural network architecture and its applications to classification and regression","abstract":"Shunting inhibition is a powerful computational mechanism that plays an important role in sensory neural information processing systems. It has been extensively used to model some important visual and cognitive functions. It equips neurons with a gain control mechanism that allows them to operate as adaptive non-linear filters. Shunting Inhibitory Artificial Neural Networks (SIANNs) are biologically inspired networks where the basic synaptic computations are based on shunting inhibition. SIANNs were designed to solve difficult machine learning problems by exploiting the inherent non-linearity mediated by shunting inhibition. The aim was to develop powerful, trainable networks, with non-linear decision surfaces, for classification and non-linear regression tasks. This work enhances and extends the original SIANN architecture to a more general form called the Generalised Feedforward Neural Network (GFNN) architecture, which contains as subsets both SIANN and the conventional Multilayer Perceptron (MLP) architectures. The original SIANN structure has the number of shunting neurons in the hidden layers equal to the number of inputs, due to the neuron model that is used having a single direct excitatory input. This was found to be too restrictive, often resulting in inadequately small or inordinately large network structures.","abstract_html":"Shunting inhibition is a powerful computational mechanism that plays an important role in sensory neural information processing systems. It has been extensively used to model some important visual and cognitive functions. It equips neurons with a gain control mechanism that allows them to operate as adaptive non-linear filters. Shunting Inhibitory Artificial Neural Networks (SIANNs) are biologically inspired networks where the basic synaptic computations are based on shunting inhibition. SIANNs were designed to solve difficult machine learning problems by exploiting the inherent non-linearity mediated by shunting inhibition. The aim was to develop powerful, trainable networks, with non-linear decision surfaces, for classification and non-linear regression tasks. This work enhances and extends the original SIANN architecture to a more general form called the Generalised Feedforward Neural Network (GFNN) architecture, which contains as subsets both SIANN and the conventional Multilayer Perceptron (MLP) architectures. The original SIANN structure has the number of shunting neurons in the hidden layers equal to the number of inputs, due to the neuron model that is used having a single direct excitatory input. This was found to be too restrictive, often resulting in inadequately small or inordinately large network structures.","abstract_has_math":false,"creators":["Arulampalam, Ganesh"],"institution":"Edith Cowan University, Research Online, Perth, Western Australia","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2004,"date_issued":"2004-01-01T08:00:00Z","date_published":"2004-01-01T08:00:00Z","updated_at":"2026-07-27T19:22:03Z","subjects":["Neural networks","Computer science","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://ro.ecu.edu.au/theses/789","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Arulampalam, Ganesh"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2004-01-01T08:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["Edith Cowan University, Research Online, Perth, Western Australia"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Neural networks","Computer science","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://ro.ecu.edu.au/theses/789","https://ro.ecu.edu.au/context/theses/article/1790/viewcontent/A_generalised_feedforward_neural_network_architecture_and_its_app.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Shunting inhibition is a powerful computational mechanism that plays an important role in sensory neural information processing systems. It has been extensively used to model some important visual and cognitive functions. It equips neurons with a gain control mechanism that allows them to operate as adaptive non-linear filters. Shunting Inhibitory Artificial Neural Networks (SIANNs) are biologically inspired networks where the basic synaptic computations are based on shunting inhibition. SIANNs were designed to solve difficult machine learning problems by exploiting the inherent non-linearity mediated by shunting inhibition. The aim was to develop powerful, trainable networks, with non-linear decision surfaces, for classification and non-linear regression tasks. This work enhances and extends the original SIANN architecture to a more general form called the Generalised Feedforward Neural Network (GFNN) architecture, which contains as subsets both SIANN and the conventional Multilayer Perceptron (MLP) architectures. The original SIANN structure has the number of shunting neurons in the hidden layers equal to the number of inputs, due to the neuron model that is used having a single direct excitatory input. This was found to be too restrictive, often resulting in inadequately small or inordinately large network structures."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:source","label":"Dc Source","values":["Theses: Doctorates and Masters"]},{"key":"dc:title","label":"Title","values":["A generalised feedforward neural network architecture and its applications to classification and regression"]}]}],"canonical_facts":{"dc:creator":["Arulampalam, Ganesh"],"dc:date":["2004-01-01T08:00:00Z"],"dc:description":["Shunting inhibition is a powerful computational mechanism that plays an important role in sensory neural information processing systems. It has been extensively used to model some important visual and cognitive functions. It equips neurons with a gain control mechanism that allows them to operate as adaptive non-linear filters. Shunting Inhibitory Artificial Neural Networks (SIANNs) are biologically inspired networks where the basic synaptic computations are based on shunting inhibition. SIANNs were designed to solve difficult machine learning problems by exploiting the inherent non-linearity mediated by shunting inhibition. The aim was to develop powerful, trainable networks, with non-linear decision surfaces, for classification and non-linear regression tasks. This work enhances and extends the original SIANN architecture to a more general form called the Generalised Feedforward Neural Network (GFNN) architecture, which contains as subsets both SIANN and the conventional Multilayer Perceptron (MLP) architectures. The original SIANN structure has the number of shunting neurons in the hidden layers equal to the number of inputs, due to the neuron model that is used having a single direct excitatory input. This was found to be too restrictive, often resulting in inadequately small or inordinately large network structures."],"dc:format":["application/pdf"],"dc:identifier":["https://ro.ecu.edu.au/theses/789","https://ro.ecu.edu.au/context/theses/article/1790/viewcontent/A_generalised_feedforward_neural_network_architecture_and_its_app.pdf"],"dc:publisher":["Edith Cowan University, Research Online, Perth, Western Australia"],"dc:source":["Theses: Doctorates and Masters"],"dc:subject":["Neural networks","Computer science","Computer Sciences"],"dc:title":["A generalised feedforward neural network architecture and its applications to classification and regression"],"dc:type":["thesis"]},"updated_at":"2026-07-27T19:22:03Z"}