This paper focuses on the problem of finite-time boundedness and finite-time passivity of discrete-time T-S fuzzy neural networks with time-varying delays. A suitable Lyapunov--Krasovskii functional(LKF) is established to derive sufficient condition for finite-time passivity of discrete-time T-S fuzzy neural networks. The dynamical system is transformed into a T-S fuzzy model with uncertain par...

The boundary contraction training for acoustic models based on deep neural networks in a discrete system (discrete DNNs) is presented in this paper. Representing the parameters of DNNs with small bits (such as 4 bits) can reduce not only memory usage but also computational complexity by utilizing a CPU cache and look-up tables efficiently. However, simply quantizing parameters of the normal con...

Although deep neural networks (DNNs) are being a revolutionary power to open up the AI era, the notoriously huge hardware overhead has challenged their applications. Recently, several binary and ternary networks, in which the costly multiplyaccumulate operations can be replaced by accumulations or even binary logic operations, make the on-chip training of DNNs quite promising. Therefore there i...

This paper formulates the model and then studies its dynamics of a system of linearly and diffusively coupled identical delayed neural networks (DNNs), which is generalization of delayed Hopfied neural networks (DHNNs) and delayed cellular neural networks (DCNNs). In particularly, a simple yet generic sufficient condition for global synchronization of such coupled DNNs is derived based on the L...

The performance of deep neural networks (DNNs) crucially relies on good hyperparameter settings. Since the computational expense of training DNNs renders traditional blackbox optimization infeasible, recent advances in Bayesian optimization model the performance of iterative methods as a function of time to adaptively allocate more resources to promising hyperparameter settings. Here, we propos...

Recently, neural networks with deep architecture have been widely applied to acoustic scene classification. Both Convolutional Neural Networks (CNNs) and Long Short-Term Memory Networks (LSTMs) have shown improvements over fully connected Deep Neural Networks (DNNs). Motivated by the fact that CNNs, LSTMs and DNNs are complimentary in their modeling capability, we apply the CLDNNs (Convolutiona...

Deep neural networks (DNNs) have achieved remarkable success on complex data processing tasks. In contrast to biological neural systems, capable of learning continuously, DNNs have a limited ability to incorporate new information in a trained network. Therefore, methods for continuous learning are potentially highly impactful in enabling the application of DNNs to dynamic data sets. Inspired by...

As deep neural networks (DNNs) are applied to increasingly challenging problems, they will need to be able to represent their own uncertainty. Modeling uncertainty is one of the key features of Bayesian methods. Scalable Bayesian DNNs that use dropout-based variational distributions have recently been proposed. Here we evaluate the ability of Bayesian DNNs trained with Bernoulli or Gaussian dis...

Deep Neural Networks (DNN) have achieved human level performance in many image analytics tasks but DNNs are mostly deployed to GPU platforms that consume a considerable amount of power. Brain-inspired spiking neuromorphic chips consume low power and can be highly parallelized. However, for deploying DNNs to energy efficient neuromorphic chips the incompatibility between continuous neurons and s...