Search results for "REPRESENTATION"
showing 10 items of 1710 documents
An associative link from geometric to symbolic representations in artificial vision
1991
Recent approaches to modelling the reference of internal symbolic representations of intelligent systems suggest to consider a computational level of a subsymbolic kind. In this paper the integration between symbolic and subsymbolic processing is approached in the framework of the research work currently carried on by the authors in the field of artificial vision. An associative mapping mechanism is defined in order to relate the constructs of the symbolic representation to a geometric model of the observed scene.
A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons
2006
In this paper we propose a three-layered neural network for binary pattern recognition and memorization. Unlike the classic approach to pattern recognition, our net works organizing itself in an unsupervised way, to distinguish beetween different patterns or to recognize similar ones. If we present a binary input to the first layer, after some time steps we could read the output of the net in the third layer, as one and only one neuron activating with high firing rate; the middle layer will act as a generalization layer, i.e. similar pattern will have similar (or the same) representation in the middle layer. We used learning algorithms inspired from other works or from biological data to ac…
Hybrid architecture for shape reconstruction and object recognition
1998
The proposed architecture is aimed to recover 3-D- shape information from gray-level images of a scene; to build a geometric representation of the scene in terms of geometric primitives; and to reason about the scene. The novelty of the architecture is in fact the integration of different approaches: symbolic reasoning techniques typical of knowledge representation in artificial intelligence, algorithmic capabilities typical of artificial vision schemes, and analogue techniques typical of artificial neural networks. Experimental results obtained by means of an implemented version of the proposed architecture acting on real scene images are reported to illustrate the system capabilities.
A spiking network for body size learning inspired by the fruit fly
2013
The concept of peripersonal space is an interesting research topics for psychologists, neurobiologists and for robotic applications. A living being can learn the representation of its own body to take the correct behavioral decision when interacting with the world. To transfer these important learning mechanisms on bio-robots, simple and efficient solutions can be found in the insect world. In this paper a neural-based model for body-size learning is proposed taking into account the results obtained in experiments with fruit flies. Simulations and experimental results on a roving platform are reported and compared with the biological counterpart.
Estimation of Granger causality through Artificial Neural Networks: applications to physiological systems and chaotic electronic oscillators
2021
One of the most challenging problems in the study of complex dynamical systems is to find the statistical interdependencies among the system components. Granger causality (GC) represents one of the most employed approaches, based on modeling the system dynamics with a linear vector autoregressive (VAR) model and on evaluating the information flow between two processes in terms of prediction error variances. In its most advanced setting, GC analysis is performed through a state-space (SS) representation of the VAR model that allows to compute both conditional and unconditional forms of GC by solving only one regression problem. While this problem is typically solved through Ordinary Least Sq…
Internal Simulation of an Agent’s Intentions
2013
We present the Associative Self-Organizing Map (A-SOM) and propose that it could be used to predict an agent’s intentions by internally simulating the behaviour likely to follow initial movements. The A-SOM is a neural network that develops a representation of its input space without supervision, while simultaneously learning to associate its activity with an arbitrary number of additional (possibly delayed) inputs. We argue that the A-SOM would be suitable for the prediction of the likely continuation of the perceived behaviour of an agent by learning to associate activity patterns over time, and thus a way to read its intentions.
The Cercle de l’Ermitage by Alberto Sartoris. Axonometry as a Synthetic Representation of the Project
2022
Analisi della cromolitografia di Alberto Sartoris pubblicata nel 1936 dalla rivista The Architectural Review. Analysis of Alberto Sartoris' chromolithography published in 1936 in The Architectural Review.
Diffeomorphisms, Noether charges, and the canonical formalism in two-dimensional dilaton gravity
1995
We carry out a parallel study of the covariant phase space and the conservation laws of local symmetries in two-dimensional dilaton gravity. Our analysis is based on the fact that the Lagrangian can be brought to a form that vanishes on-shell giving rise to a well-defined covariant potential for the symplectic current. We explicitly compute the symplectic structure and its potential and show that the requirement to be finite and independent of the Cauchy surface restricts the asymptotic symmetries.
A noodle, hockey stick, and spaghetti plate: a perspective on high‐resolution paleoclimatology
2010
The high-resolution reconstruction of hemispheric-scale temperature variation over the past-millennium benchmarks recent warming against more naturally driven climate episodes, such as the Little Ice Age and the Medieval Warm Period, thereby allowing assessment of the relative efficacies of natural and anthropogenic forcing factors. Icons of past temperature variability, as featured in the Intergovernmental Panel on Climate Change (IPCC) reports over nearly two decades, have changed from a schematic sketch in 1990, to a seemingly well-solved story in 2001, to more explicit recognition of significant uncertainties in 2007. In this article, we detail the beginning of the movement to reconstru…
Metodi per la ricostruzione virtuale e la visualizzazione di opere d'architettura perdute
2022
Digital technologies for architecture representation have strongly modified uses and rules inherited from a millennial tradition. In the initial development period CAD tools worked as electronic drafting machines and digital drawings were almost similar to hand-made drawings; plans, fronts, sections and the like. In this period perspective and axonometric drawings were rarely executed because architects realized that these drawings had to be substituted by 3D digital models views, but modeling tools were not so familiar to professionals, both for software and hardware limitations. The evolution of architecture digital representation is still in progress, but it is possible to outline a prec…