Search Results - "Cancelliere, Rossella"

Anomaly Detection Techniques in the Gaia Space Mission Data by Roberti, Marco, Druetto, Alessandro, Busonero, Deborah, Cancelliere, Rossella, Cavagnino, Davide, Gai, Mario

“…In this paper we deal with classification of anomalous data detected by the data reduction system of the Gaia space mission, in operation since 2013. Given the…”
Get full text

Correction to: Anomaly Detection Techniques in the Gaia Space Mission Data by Roberti, Marco, Druetto, Alessandro, Busonero, Deborah, Cancelliere, Rossella, Cavagnino, Davide, Gai, Mario

Get full text

The Rare Word Issue in Natural Language Generation: A Character-Based Solution by Bonetta, Giovanni, Roberti, Marco, Cancelliere, Rossella, Gallinari, Patrick

“…In this paper, we analyze the problem of generating fluent English utterances from tabular data, focusing on the development of a sequence-to-sequence neural…”
Get full text

Simultaneous derivation of galaxy physical properties with multimodal deep learning by Gai, Mario, Bove, Mario, Bonetta, Giovanni, Zago, Davide, Cancelliere, Rossella

“…ABSTRACT Upcoming telescopes and surveys will revolutionize our understanding of the Universe by providing unprecedented amounts of observations on…”
Get full text

Regularization-based pruning of irrelevant weights in deep neural architectures by Bonetta, Giovanni, Ribero, Matteo, Cancelliere, Rossella

“…Deep neural networks exploiting million parameters are currently the norm. This is a potential issue because of the great number of computations needed for…”
Get full text

Controlling hallucinations at word level in data-to-text generation by Rebuffel, Clement, Roberti, Marco, Soulier, Laure, Scoutheeten, Geoffrey, Cancelliere, Rossella, Gallinari, Patrick

“…Data-to-Text Generation (DTG) is a subfield of Natural Language Generation aiming at transcribing structured data in natural language descriptions. The field…”
Get full text

OCReP: An Optimally Conditioned Regularization for pseudoinversion based neural training by Cancelliere, Rossella, Gai, Mario, Gallinari, Patrick, Rubini, Luca

“…In this paper we consider the training of single hidden layer neural networks by pseudoinversion, which, in spite of its popularity, is sometimes affected by…”
Get full text

Real-time detection of driver distraction: random projections for pseudo-inversion-based neural training by Botta, Marco, Cancelliere, Rossella, Ghignone, Leo, Tango, Fabio, Gallinari, Patrick, Luison, Clara

“…There is an accumulating evidence that distracted driving is a leading cause of vehicle crashes and accidents. In order to support safe driving, numerous…”
Get full text

Local search and pseudoinversion: an hybrid approach to neural network training by Rubini, Luca, Cancelliere, Rossella, Gallinari, Patrick, Grosso, Andrea

“…We consider recent successful techniques proposed for neural network training that set randomly the weights from input to hidden layer, while weights from…”
Get full text

Regularization-based Pruning of Irrelevant Weights in Deep Neural Architectures by Bonetta, Giovanni, Ribero, Matteo, Cancelliere, Rossella

“…Deep neural networks exploiting millions of parameters are nowadays the norm in deep learning applications. This is a potential issue because of the great…”
Get full text

Job Shop Scheduling via Deep Reinforcement Learning: a Sequence to Sequence approach by Bonetta, Giovanni, Zago, Davide, Cancelliere, Rossella, Grosso, Andrea

“…Proceedings of the International Conference on Learning and Intelligent Optimization (LION17). Springer International Publishing (2023, June) Job scheduling is…”
Get full text

Neural networks for wind power generation forecasting: A case study by Cancelliere, R., Gosso, A., Grosso, A.

“…This paper uses data collected in a southern Italy wind farm to develop a neural network based prediction of the power produced by each turbine. First, some…”
Get full text

Dynamics and stability of generalized cellular nonlinear network model by Cancelliere, Rossella, Slavova, Angela

“…The aim of this paper is the definition of a new model of neural network, called generalized cellular nonlinear network, that covers architectures and dynamics…”
Get full text

Retrieval-Augmented Transformer-XL for Close-Domain Dialog Generation by Bonetta, Giovanni, Cancelliere, Rossella, Liu, Ding, Vozila, Paul

“…Transformer-based models have demonstrated excellent capabilities of capturing patterns and structures in natural language generation and achieved…”
Get full text

Copy mechanism and tailored training for character-based data-to-text generation by Roberti, Marco, Bonetta, Giovanni, Cancelliere, Rossella, Gallinari, Patrick

“…In the last few years, many different methods have been focusing on using deep recurrent neural networks for natural language generation. The most widely used…”
Get full text

A comparative analysis of neural network performances in astronomical imaging by Cancelliere, Rossella, Gai, Mario

“…Neural networks are widely used as recognisers and classifiers since the second half of the 80's; this is related to their capability of solving a nonlinear…”
Get full text

Controlling Hallucinations at Word Level in Data-to-Text Generation by Rebuffel, Clément, Roberti, Marco, Soulier, Laure, Scoutheeten, Geoffrey, Cancelliere, Rossella, Gallinari, Patrick

“…Data-to-Text Generation (DTG) is a subfield of Natural Language Generation aiming at transcribing structured data in natural language descriptions. The field…”
Get full text

Performance of an Algorithm for Estimation of Flux, Background and Location on One-Dimensional Signals by Gai, Mario, Busonero, Deborah, Cancelliere, Rossella

“…Optimal estimation of signal amplitude, background level, and photocentre location is crucial to the combined extraction of astrometric and photometric…”
Get full text

OCReP: An Optimally Conditioned Regularization for Pseudoinversion Based Neural Training by Cancelliere, Rossella, Gai, Mario, Gallinari, Patrick, Rubini, Luca

“…In this paper we consider the training of single hidden layer neural networks by pseudoinversion, which, in spite of its popularity, is sometimes affected by…”
Get full text

On the approximation error introduced using principal component analysis in neural networks by Cancelliere, Rossella, Gai, Mario

Get full text