Taking inspiration from the brain, spiking neural networks (SNNs) have been proposed to understand and diminish gap between machine learning neuromorphic computing. Supervised is most commonly used algorithm in traditional ANNs. However, directly training SNNs with backpropagation-based supervised methods challenging due discontinuous non-differentiable nature of neuron. To overcome these probl...

Variational quantum algorithms are proposed to solve relevant computational problems on near term devices. Popular versions variational eigensolvers and ap- proximate optimization that ground state from chemistry binary problems, respectively. They based the idea of using a classical computer train parameterized circuit. We show corresponding NP-hard. Moreover, hardness is robust in sense that,...

neural network is one of the most widely used algorithms in the field of machine learning, on the other hand, neural network training is a complicated and important process. supervised learning needs to be organized to reach the goal as soon as possible. a supervised learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new examples.  hen...

A new training strategy with progressive random gate activation for variational quantum algorithms greatly mitigates barren plateaus and avoids the local minima while being resource efficient noise resilient.