3,528 research outputs found
Universal approximation capability of cascade correlation for structures
No full textHammer B, Micheli A, Sperduti A. Universal approximation capability of cascade correlation for structures. Neural Computation. 2005;17(5):1109-1159
Adaptive Contextual Processing of Structured Data by Recursive Neural Networks: A Survey of Computational Properties
No full textHammer B, Micheli A, Sperduti A. Adaptive Contextual Processing of Structured Data by Recursive Neural Networks: A Survey of Computational Properties. In: Hammer B, Hitzler P, eds. Perspectives of Neural-Symbolic Integration. Studies in computational Intelligence, 77. Berlin: Springer; 2007: 67-94
A general framework for unsupervised processing of structured data
No full textHammer B, Micheli A, Sperduti A, Strickert M. A general framework for unsupervised processing of structured data. Neurocomputing. 2004;57:3-35
Recursive self-organizing network models
No full textHammer B, Micheli A, Sperduti A, Strickert M. Recursive self-organizing network models. Neural Networks. 2004;17(8-9):1061-1085
On linear Separability of Sequences and Structures
No full textLinear separability of sequences and structured data is studied. On the basis of a theoretical model, necessary and sufficient conditions for nonlinear separability are derived by a well known result for vectors. Examples of sufficient conditions for linear separability of both sequences and structured data are given
Embeddings and Representation Learning for Structured Data
No full textPaaßen B, Gallicchio C, Micheli A, Sperduti A. Embeddings and Representation Learning for Structured Data. In: Verleysen M, ed. Proceedings of the 27th European Symposium on Artificial Neural Networks (ESANN 2019). 2019: 85-94.Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form. Therefore, multiple approaches have emerged to construct vectorial representations of structured data, from kernel and distance approaches to recurrent, recursive, and convolutional neural networks. Recent years have seen heightened attention in this demanding field of research and several new approaches have emerged, such as metric learning on structured data, graph convolutional neural networks, and recurrent decoder networks for structured data. In this contribution, we provide an high-level overview of the state-of-the-art in representation learning and embeddings for structured data across a wide range of machine learning fields
On the Computational Power of Recurrent Neural Networks for Structures
No full textRecurrent neural networks can simulate any finite state automata as well as any multi-stack Turing machine. When constraining the network architecture, however, this computational power may no longer hold. For example, recurrent cascade-correlation cannot simulate any finite state automata. Thus, it is important to assess the computational power of a given network architecture, since this characterizes the class of functions which, in principle, can be computed by it. We discuss the computational power of neural networks for structures. Elman-style networks, cascade-correlation networks and neural trees for structures are introduced We show that Elman-style networks can simulate any frontier-to-root tree automation while neither cascade-correlation networks nor neural trees can. As a special case of the latter result, we obtain that neural trees for sequences cannot simulate any finite state machine
Labelling Recursive Auto-associative Memory
No full textIn this paper, we propose an extension to the recursive auto-associative memory (RAAM) by Pollack. This extension, the labelling RAAM (LRAAM), can encode labelled graphs with cycles by representing pointers explicitly. Some technical problems encountered in the RAAM, such as the termination problem in the learning and decoding processes, are solved more naturally in the LRAAM framework. The representations developed for the pointers seem to be robust to recurrent decoding along a cycle. Theoretical and experimental results show that the performances of the proposed learning scheme depend on the way the graphs are represented in the training set. Critical features for the representation are cycles and confluent pointers. Data encoded in a LRAAM can be accessed by a pointer as well as by content. Direct access by content can be achieved by transforming the encoder network of the LRAAM into a particular bidirectional associative memory (BAM). Statistics performed on different instances of LRAAM show a strict connection between the associated BAM and a standard BAM. Different access procedures can be defined depending on the access key. The access procedures are not wholly reliable; however, they seem to have a good success rate. The generalization test for the RAAM is no longer complete for the LRAAM. Some suggestions on how to solve this problem are given. Some results on modular LRAAM, stability and application to neural dynamics control are summarized
- …
