In this paper, we propose a method of improving Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming. Conventional CNNs convolve learnable shared weights, or filters, across the input data. The filters use a linear matching of weights to inputs using an inner product between the filter and a window of the input. However, it is ...

Modeling user preference from his historical sequences is one of the core problems sequential recommendation. Existing methods in this field are widely distributed conventional to deep learning methods. However, most them only model users' interests within their own and ignore dynamic collaborative signals among different sequences, making it insufficient explore preferences. We take inspiratio...

The pre-training of the graph neural network model is to learn general characteristics large-scale graphs or similar type usually through a self-supervised method, which allows work even when node labels are missing. However, existing methods do not take temporal information edge generation and evolution process into consideration. To address this issue, paper proposes method based on dynamic n...

Modern deep neural networks are powerful and widely applicable models that extract task-relevant information through multi-level abstraction. Their cross-domain success, however, is often achieved at the expense of computational cost, high memory bandwidth, long inference latency, which prevents their deployment in resource-constrained time-sensitive scenarios, such as edge-side self-driving ca...

We have investigated two specific network types in the class of dynamic neural networks: LSTM and spiking neural networks. Dynamic neural networks in general are computationally powerful and very promising for tasks in which temporal information has to be processed. We’d like to remark that this is the case for virtually any task or application interacting with the real world. We have tested th...

We have investigated two specific network types in the class of dynamic neural networks: LSTM and spiking neural networks. Dynamic neural networks in general are computationally powerful and very promising for tasks in which temporal information has to be processed. We’d like to remark that this is the case for virtually any task or application interacting with the real world. We have tested th...

Non-linear dynamical systems are difficult to control due to the model uncertainties and external disturbances that may occur in these systems. This paper addresses the problem of identification using dynamic neural networks (DNNs) based on genetic algorithm (GA) for nonlinear dynamic systems. Four different dynamic neural networks are used for identification of the same nonlinear dynamic syste...