Multilayer feedforward networks are universal approximators
Neural Networks
Recursive distributed representations
Artificial Intelligence - On connectionist symbol processing
On the Problem of Local Minima in Backpropagation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A probabilistic resource allocating network for novelty detection
Neural Computation
A Layer-by-Layer Least Squares based Recurrent Networks Training Algorithm: Stalling and Escape
Neural Processing Letters
Unsupervised Segmentation of Color-Texture Regions in Images and Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning with Recurrent Neural Networks
Learning with Recurrent Neural Networks
Application of Cascade Correlation Networks for Structures toChemistry
Applied Intelligence
Machine Learning
Logo Recognition by Recursive Neural Networks
GREC '97 Selected Papers from the Second International Workshop on Graphics Recognition, Algorithms and Systems
Gradient Based Learning Methods
Adaptive Processing of Sequences and Data Structures, International Summer School on Neural Networks, "E.R. Caianiello"-Tutorial Lectures
Towards Incremental Parsing of Natural Language Using Recursive Neural Networks
Applied Intelligence
Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
Genetic Evolution Processing of Classification
IEEE Transactions on Knowledge and Data Engineering
Neural Computation
IEEE Transactions on Image Processing
Input-output HMMs for sequence processing
IEEE Transactions on Neural Networks
Face recognition/detection by probabilistic decision-based neural network
IEEE Transactions on Neural Networks
Supervised neural networks for the classification of structures
IEEE Transactions on Neural Networks
A general framework for adaptive processing of data structures
IEEE Transactions on Neural Networks
ViSOM - a novel method for multivariate data projection and structure visualization
IEEE Transactions on Neural Networks
A self-organizing map for adaptive processing of structured data
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
Entropy-based generation of supervised neural networks for classification of structured patterns
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
PRSOM: a new visualization method by hybridizing multidimensional scaling and self-organizing map
IEEE Transactions on Neural Networks
Learning long-term dependencies with gradient descent is difficult
IEEE Transactions on Neural Networks
Maximum likelihood training of probabilistic neural networks
IEEE Transactions on Neural Networks
Training feedforward networks with the Marquardt algorithm
IEEE Transactions on Neural Networks
Decision-based neural networks with signal/image classification applications
IEEE Transactions on Neural Networks
A local experts organization model with application to face emotion recognition
Expert Systems with Applications: An International Journal
Classification of Arrhythmia Using Hybrid Networks
Journal of Medical Systems
Hi-index | 12.05 |
One of the most popular frameworks for the adaptive processing of data structures to date, was proposed by Frasconi et al. [Frasconi, P., Gori, M., & Sperduti, A. (1998). A general framework for adaptive processing of data structures. IEEE Transactions on Neural Networks, 9(September), 768-785], who used a Backpropagation Through Structures (BPTS) algorithm [Goller, C., & Kuchler, A. (1996). Learning task-dependent distributed representations by back-propagation through structures. In Proceedings of IEEE international conference on neural networks (pp. 347-352); Tsoi, A. C. (1998). Adaptive processing of data structure: An expository overview and comments. Technical report in Faculty Informatics. Wollongong, Australia: University of Wollongong] to carry out supervised learning. This supervised model has been successfully applied to a number of learning tasks that involve complex symbolic structural patterns, such as image semantic structures, internet behavior, and chemical compounds. In this paper, we extend this model, using probabilistic estimates to acquire discriminative information from the learning patterns. Using this probabilistic estimation, smooth discriminant boundaries can be obtained through a process of clustering onto the observed input attributes. This approach enhances the ability of class discrimination techniques to recognize structural patterns. The proposed model is represented by a set of Gaussian Mixture Models (GMMs) at the hidden layer and a set of ''weighted sum input to sigmoid function'' models at the output layer. The proposed model's learning framework is divided into two phases: (a) locally unsupervised learning for estimating the parameters of the GMMs and (b) globally supervised learning for fine-tuning the GMMs' parameters and optimizing weights at the output layer. The unsupervised learning phase is formulated as a maximum likelihood problem that is solved by the expectation-maximization (EM) algorithm. The supervised learning phase is formulated as a cost minimization problem, using the least squares optimization or Levenberg-Marquardt method. The capabilities of the proposed model are evaluated in several simulation platforms. From the results of the simulations, not only does the proposed model outperform the original recursive model in terms of learning performance, but it is also significantly better at classifying and recognizing structural patterns.