This paper presents a raw-waveform neural network and uses it along with a denoising network for clustering in weakly supervised learning scenarios under extreme noise conditions. Specifically, we consider language independent Automatic Gender Recognition ...
The goal of this paper is to analyze the geometric properties of deep neural network image classifiers in the input space. We specifically study the topology of classification regions created by deep networks, as well as their associated decision boundary. ...
Remarkable hardware robustness of deep learning (DL) is revealed by error injection analyses performed using a custom hardware model implementing parallelized restricted Boltzmann machines (RBMs). RBMs in deep belief networks demonstrate robustness against ...
Deep neural networks have recently shown impressive classification performance on a diverse set of visual tasks. When deployed in real-world (noise-prone) environments, it is equally important that these classifiers satisfy robustness guarantees: small per ...
Institute of Electrical and Electronics Engineers2017
We study an elliptic equation with stochastic coefficient modeled as a lognormal random field. A perturbation approach is adopted, expanding the solution in Taylor series around the nominal value of the coefficient. The resulting recursive deterministic pr ...
A key aspect of constructing highly scalable Deep-learning microelectronic systems is to implement fault tolerance in the learning sequence. Error-injection analyses for memory is performed using a custom hardware model implementing parallelized restricted ...
