1,721,142 research outputs found
The Loading Problem for Recursive Neural Networks
No full textThe present work deals with one of the major and not yet completely understood topics of supervised connectionist models. Namely, it investigates the relationships between the difficulty of a given learning task and the chosen neural network architecture. These relationships have been investigated and nicely established for some interesting problems in the case of neural networks used for processing vectors and sequences, but only a few studies have dealt with loading problems involving graphical inputs. In this paper, we present sufficient conditions which guarantee the absence of local minima of the error function in the case of learning directed acyclic graphs with recursive neural networks. We introduce topological indices which can be directly calculated from the given training set and that allows us to design the neural architecture with local minima free error function. In particular, we conceive a reduction algorithm that involves both the information attached to the nodes and the topology, which enlarges significantly the class of the problems with unimodal error function previously proposed in the literature. (c) 2005 Elsevier Ltd. All rights reserved
A general framework for self-organizing structure processing neural networks
No full textHammer B, Micheli a., Sperduti A. A general framework for self-organizing structure processing neural networks. Pisa: Universita di Pisa, Dipartimento die Informatica; 2003
A general framework for unsupervised processing of structured data
No full textHammer B, Micheli A, Sperduti A. A general framework for unsupervised processing of structured data. In: Verleysen M, ed. ESANN 2002, 10th European Symposium on Artificial Neural Network. Proceedings. De-side publication; 2002: 389-394
Approximation and generalization issues of recurrent networks dealing with structured data
No full textHammer B. Approximation and generalization issues of recurrent networks dealing with structured data. In: Frasconi P, Sperduti A, Gori M, eds. ECAI workshop: Foundations of connectionist-symbolic integration: representation, paradigms, and algorithms. 2000
Polynomial-based graph convolutional neural networks for graph classification
Full text linkGraph convolutional neural networks exploit convolution operators, based on some neighborhood aggregating scheme, to compute representations of graphs. The most common convolution operators only exploit local topological information. To consider wider topological receptive fields, the mainstream approach is to non-linearly stack multiple graph convolutional (GC) layers. In this way, however, interactions among GC parameters at different levels pose a bias on the flow of topological information. In this paper, we propose a different strategy, considering a single graph convolution layer that independently exploits neighbouring nodes at different topological distances, generating decoupled representations for each of them. These representations are then processed by subsequent readout layers. We implement this strategy introducing the polynomial graph convolution (PGC) layer, that we prove being more expressive than the most common convolution operators and their linear stacking. Our contribution is not limited to the definition of a convolution operator with a larger receptive field, but we prove both theoretically and experimentally that the common way multiple non-linear graph convolutions are stacked limits the neural network expressiveness. Specifically, we show that a graph neural network architecture with a single PGC layer achieves state of the art performance on many commonly adopted graph classification benchmarks
A framework for the definition of complex structured feature spaces
No full textIn this paper, we propose a general framework that, starting from the feature space of an existing base graph kernel, allows to define more expressive kernels which can learn more complex concepts, meanwhile generalizing different proposals in literature. Experimental results on eight real-world graph datasets from different domains show that the proposed framework instances are able to get a statistically significant performance improvement over both the considered base kernels and framework instances previously defined in literature, obtaining state-of-the-art results on all the considered datasets
Simple Multi-resolution Gated GNN
No full textMost Graph Neural Networks (GNNs) proposed in literature tend to add complexity (and non-linearity) to the model. In this paper, we follow the opposite direction by proposing a simple linear multi-resolution architecture that implements a multi-head gating mechanism. We assessed the performances of the proposed architecture on node classification tasks. To perform a fair comparison and present significant results, we re-implemented the competing methods from the literature and ran the experimental evaluation considering two different experimental settings with different model selection procedures. The proposed convolution, dubbed Simple Multi-resolution Gated GNN, exhibits state-of-the-art predictive performance on the considered benchmark datasets in terms of accuracy. In addition, it is way more efficient to compute than GAT, a well-known multihead GNN proposed in literature
Caring for their teeth. Dental health in nonadults from two Roman Imperial age communities from Italy
No full textA Hybrid System for Systematic Generalization in Simple Arithmetic Problems
Full text linkSolving symbolic reasoning problems that require compositionality and systematicity is considered one of the key ingredients of human intelligence. However, symbolic reasoning is still a great challenge for deep learning models, which often cannot generalize the reasoning pattern to out-of-distribution test cases. In this work, we propose a hybrid system capable of solving arithmetic problems that require compositional and systematic reasoning over sequences of symbols. The model acquires such a skill by learning appropriate substitution rules, which are applied iteratively to the input string until the expression is completely resolved. We show that the proposed system can accurately solve nested arithmetical expressions even when trained only on a subset including the simplest cases, significantly outperforming both a sequence-to-sequence model trained end-to-end and a state-of-the-art large language model
- …
