Catastrophic forgetting (CF) occurs when a neural network loses the
info...
Image-to-image translation (I2I) aims at transferring the content
repres...
Spatial audio methods are gaining a growing interest due to the spread o...
The L3DAS22 Challenge is aimed at encouraging the development of machine...
Catastrophic forgetting (CF) happens whenever a neural network overwrite...
Recent research has found that neural networks are vulnerable to several...
In this paper, we investigate the degree of explainability of graph neur...
In this paper, we propose a novel ensembling technique for deep neural
n...
Graph representation learning has become a ubiquitous component in many
...
Nonlinear models are known to provide excellent performance in real-worl...
The L3DAS21 Challenge is aimed at encouraging and fostering collaborativ...
Deep probabilistic generative models have achieved incredible success in...
Catastrophic forgetting (CF) happens whenever a neural network overwrite...
Deep neural networks are generally designed as a stack of differentiable...
Bayesian Neural Networks (BNNs) are trained to optimize an entire
distri...
Graph convolutional networks (GCNs) are a family of neural network model...
Continual learning of deep neural networks is a key requirement for scal...
Multiple sclerosis is one of the most common chronic neurological diseas...
In recent years, hyper-complex deep networks (e.g., quaternion-based) ha...
Recently, data augmentation in the semi-supervised regime, where unlabel...
Missing data imputation (MDI) is a fundamental problem in many scientifi...
In this brief we investigate the generalization properties of a
recently...
Complex-valued neural networks (CVNNs) have been shown to be powerful
no...
Learning from data in the quaternion domain enables us to exploit intern...
Gated recurrent neural networks have achieved remarkable results in the
...
Graph neural networks (GNNs) are a class of neural networks that allow t...
Complex-valued neural networks (CVNNs) are a powerful modeling tool for
...
Neural networks are generally built by interleaving (adaptable) linear l...
In this paper, we consider the joint task of simultaneously optimizing (...
Neural networks require a careful design in order to perform properly on...