The reinforcement learning research area contains a wide range of methods for solving the problems of intelligent agent control. Despite the progress that has been made, the task of creating a highly autonomous agent ...
详细信息
Abstract: We develop/propose the method reducing the dimension of a data matrix, based on its direct and inverse projection, and the calculation of projectors that minimize the cross-entropy functional, remove. We int...
详细信息
Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output ...
详细信息
The solution tree of the 2D stationary Kuramoto-Sivashinsky equations in the periodic domain is analized using the analytical and numerical methods. The evolution of stationary solutions is considered by constructing ...
详细信息
Continuous subgraph matching (CSM) is a critical task for analyzing dynamic graphs and has a wide range of applications, such as merchant fraud detection, cyber-attack hunting, and rumor detection. Although many effic...
详细信息
The classical A.N. Kolmogorov's flow problem for the stationary 2D Navier-Stokes equations on a stretched torus for velocity vector function is considered. The problem is analysed by the construction of the soluti...
详细信息
The system of governing equations for the dynamics of the compressible viscous ideal gas is considered in the 3D bounded domain with the inflow and outflow boundary conditions. The cylinder is located in the domain. S...
详细信息
The extension of the classical A.N. Kolmogorov’s flow problem for the stationary 3D Navier-Stokes equations on a stretched torus for velocity vector function is considered. A spectral Fourier method with the Leray pr...
详细信息
With the growth of non-motorized vehicles, low-carbon and environmentally friendly travel has gradually become the mainstream of people all over the world. The wide distribution and small proportion of non-motorized v...
详细信息
The biology of the brain can inspire the development of a wide range of intelligent information processing algorithms. Spatiotem-poral processing allows the brain to aggregate and represent information on multiple tim...
详细信息
The biology of the brain can inspire the development of a wide range of intelligent information processing algorithms. Spatiotem-poral processing allows the brain to aggregate and represent information on multiple time and space scales. This paper examines temporal pooling, a biologically inspired spatiotemporal processing algorithm, in the task of creating stable sequential representations of objects while preserving their relative similarity. We compare two temporal pooling algorithm implementations: an existing Hierarchical Temporal Memory framework implementation called Union Temporal Pooler and our proposed Sandwich Temporal Pooler. We evaluate the temporal poolers on synthetic sequences using various aggregating metrics. It is shown that both implementations preserve high similarity; however, Union Temporal Pooler has better ability to preserve low and moderate similarity, while the proposed Sandwich Temporal Pooler features better output representation stability and computational efficiency.
暂无评论