Modular connectionist structure for 100-word recognition

Hackbarth, Heidi; Mantel, Juval

doi:10.1109/ijcnn.1991.155444

Cited by 6 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, due to the limited sizes of the neural networks they rely on, these approaches to super-resolution are inappropriate for globalscale reconstruction and high magnification rates (the papers cited present results for a scaling factor of 2 only). Actually, we showed in [1] that traditional networks such as multilayer perceptrons and merge-and-glue modular networks [17,18] do not scale up when applied to image transformation (the training process systematically fails to converge as soon as the size of the images and number of patterns increase). On the contrary, our network appears to be highly scalable in that it can be trained reliably to transform images of subsequent size.…”

Section: Comparison With Other Super-resolution Methodsmentioning

confidence: 98%

A modular neural network for super-resolution of human faces

Carcenac

2007

Appl Intell

View full text Add to dashboard Cite

This paper presents the original and versatile architecture of a modular neural network and its application to super-resolution. Each module is a small multilayer perceptron, trained with the Levenberg-Marquardt method, and is used as a generic building block. By connecting the modules together to establish a composition of their individual mappings, we elaborate a lattice of modules that implements full connectivity between the pixels of the low-resolution input image and those of the higher-resolution output image. After the network is trained with patterns made up of low and high-resolution images of objects or scenes of the same kind, it will be able to enhance dramatically the resolution of a similar object's representation. The modular nature of the architecture allows the training phase to be readily parallelized on a network of PCs. Finally, it is shown that the network performs global-scale reconstruction of human faces from very low resolution input images.

show abstract

Section: Comparison With Other Super-resolution Methodsmentioning

confidence: 98%

A modular neural network for super-resolution of human faces

Carcenac

2007

Appl Intell

View full text Add to dashboard Cite

show abstract

“…In addition to this study, we have also applied to image transformation the so-called merge-and-glue modular neural network [31,32] and studied its convergence. Similarly to our architecture, this network consists of modules that are taught separately and then merged together.…”

Section: Comparison With Related Neural Architecturesmentioning

confidence: 99%

A modular neural network applied to image transformation and mental images

Carcenac

2007

Neural Comput Applic

View full text Add to dashboard Cite

This paper presents an original modular neural network architecture whose modules are multilayer perceptrons. The modules' inputs are external inputs or hidden layers of other modules, thereby allowing them to be connected in a general manner. Based on this flexible architecture, networks with high numbers of inputs and outputs can be elaborated and properly trained. A suitable application is image transformation, i.e. the transformation of many input pixels into as many output pixels. Some architectural variations are presented; first the localization over a fraction of the network of a specific transformation's training, and then the merging of two input images into a single output image. As a case study, we use the modular network to model mental images and their transformations (mental rotation, mental assemblage). It should eventually prove to be a valuable tool for image processing applications, such as super-resolution, or for the elaboration of complex cognitive systems.

show abstract

“…18 Therefore, it is important to develop new structures which have less memory and speed requirements, especially when dealing with large scale applications. 16,18,55,56 The main constraints on the hardware implementations of NN are the number of fan-in (-out) connections per node 18 ; speed of processing information 57 ; and the length of physical connections. 30 The following are some advantages of the MNN over the nonmodular NNs with respect to these constraints.…”

Section: Hardware Motivationsmentioning

confidence: 99%

“…(b) When the number of classes increases substantially, e.g., recognizing 100 words in Ref. 55, it is usually difficult for the MNNdesigner to figure out which classes should be grouped in separate sub-tasks. (c) Sometimes, even when the designer has a visual image of the classes, the utilized featurevector may fail in representing the visual inter-and intraclass variations, e.g., vowel recognition problem in Ref.…”

Section: Naturally-defined Modulesmentioning

confidence: 99%

See 1 more Smart Citation

Modular Neural Networks: A Survey

Auda

Kamel

1999

Int. J. Neur. Syst.

129

View full text Add to dashboard Cite

Modular Neural Networks (MNNs) is a rapidly growing field in artificial Neural Networks (NNs) research. This paper surveys the different motivations for creating MNNs: biological, psychological, hardware, and computational. Then, the general stages of MNN design are outlined and surveyed as well, viz., task decomposition techniques, learning schemes and multi-module decision-making strategies. Advantages and disadvantages of the surveyed methods are pointed out, and an assessment with respect to practical potential is provided. Finally, some general recommendations for future designs are presented.

show abstract

Modular connectionist structure for 100-word recognition

Cited by 6 publications

References 4 publications

A modular neural network for super-resolution of human faces

A modular neural network for super-resolution of human faces

A modular neural network applied to image transformation and mental images

Modular Neural Networks: A Survey

Contact Info

Product

Resources

About