Introduction: The neural substrates of temporal processing are not still fully known. The majority of interval timing studies have dealt with this subject in the context of “Explicit timing” (computing the time intervals explicitly). The hypothesis “Implicit timing” (implicitly using temporal processing to improve function) has also proposed. This lesion study addressed explicit and implicit ti...

In recent years, the use of hybrid soft computing methods has shown that in various applications the synergism of several techniques is superior to a single technique. For example, the use of a neural fuzzy system and an evolutionary fuzzy system hybridises the approximate reasoning mechanism of fuzzy systems with the learning capabilities of neural networks and evolutionary algorithms. Evoluti...

For the pursuit of ubiquitous computing, distributed computing systems containing cloud, edge devices, and Internet-of-Things devices are highly demanded. However, existing frameworks do not tailor for fast development Deep Neural Network (DNN), which is key technique behind many intelligent applications nowadays. Based on prior exploration deep neural networks (DDNN), we propose Heterogeneous ...

Conventional electronic Artificial Neural Networks (ANNs) accelerators focus on architecture design and numerical computation optimization to improve the training efficiency. However, these approaches have recently encountered bottlenecks in terms of energy efficiency computing performance, which leads an increase interest photonic accelerator. Photonic architectures with low consumption, high ...