We outline emerging opportunities and challenges to enhance the utility ...
Quantization and pruning are core techniques used to reduce the inferenc...
We propose a novel modification of the standard upper confidence bound (...
A novel energy-efficient edge computing paradigm is proposed for real-ti...
The use of Deep Learning hardware algorithms for embedded applications i...
When trained as generative models, Deep Learning algorithms have shown
e...
Stochastic-sampling-based Generative Neural Networks, such as Restricted...
The power budget for embedded hardware implementations of Deep Learning
...
The electroencephalogram (EEG) provides a non-invasive, minimally
restri...
In recent years deep learning algorithms have shown extremely high
perfo...
Probabilistic generative neural networks are useful for many application...
Restricted Boltzmann Machines and Deep Belief Networks have been success...