4 results about "Stochastic matrix" patented technology

The invention discloses an unmanned aerial vehicle cluster patrol path decision-making method under resource constraint, and relates to the technical field of unmanned aerial vehicle path planning, and the method comprises the steps: carrying out the discretization of an actual to-be-patrolled physical position, and constructing an undirected topological graph; generating steady-state distribution of each patrol node according to topological constraints and importance degrees of the nodes; generating a plurality of transfer matrixes with the same steady-state distribution and different transfer characteristics according to a multi-stage entropy driving random matrix optimization algorithm; initializing the position of a navigator according to the transfer matrix and determining a selected path; according to the reference path of the navigator, the self-adaptive active positioning decision is realized under the positioning constraint to ensure the path tracking effect; according to path selection and tracking of the navigator, the follower and the navigator form a humanoid marshalling cluster through a reward function; and according to the multi-state transfer matrix and the humanoid marshalling, automatically switching to the next transfer matrix when a transfer frequency threshold value is reached, and realizing unmanned aerial vehicle cluster intelligent patrol path decision under resource constraint.

The invention belongs to the technical field of information communication, particularly relates to a directed network environment variance reduction distributed self-adaptive gradient tracking algorithm and system, and aims to solve the following problems in the prior art: 1) an existing distributed self-adaptive random optimization algorithm uses double random matrixes as communication matrixes and cannot be applied to directed network topology; and 2) the existing distributed stochastic optimization algorithm is limited by the property of stochastic gradient in any strong connectivity network, and the optimization precision is influenced by steady-state errors. An efficient variance reduction distributed adaptive gradient tracking algorithm-VRDAGT algorithm is provided, the algorithm combines a gradient tracking technology, an adaptive step length technology and a variance reduction technology, and eliminates steady-state errors introduced by stochastic gradients under a push-pull framework; by using the row random matrix and the column random matrix, the VRDAGT algorithm gets rid of dependence on double random matrixes, so that the applicable network topology range of the algorithm is widened. Compared with an existing algorithm, the VRDAGT algorithm has higher optimization precision and a wider application range.

This invention discloses a residual routing constraint method and system for enhancing the training stability of neural networks, comprising the following steps: S1, based on the residual routing constraint in the neural network... l Input feature tensor of the layer x l S1. Generate the original values ​​of the pre-scaling matrix, the post-scaling matrix, and the residual routing matrix; S2. Apply non-negativity constraints to and to obtain the pre-scaling matrix. H pre and post-scaling matrix H post By constraining optimization to satisfy the double stochastic matrix condition, the residual routing matrix is ​​obtained. H res S3, Utilize H pre right x l Premixing is performed to obtain preprocessed characteristics. u l ;Will u l Enter to the number l Layer core calculation function F layer Calculations are performed to obtain the layer output features. y l ;Will H post Acting on y l The scaled output will be obtained. H res Acting on x l After obtaining the stable residual, the scaled output is summed with the stable residual to obtain the first... l Layer output features x l +1. This invention significantly improves the numerical stability of deep neural network training.

Disclosed are a stochastic matrix-vector multiply-accumulate operation system and an operation method thereof. The operation system includes an input bit-stream generator, a weight bit-stream generator and a memory array. The input bit-stream generator generates a pulse sequence representing a corresponding input stochastic bit-stream according to respective preset input values of a preset input vector, the weight bit-stream generator generates a pulse sequence representing a corresponding weight stochastic bit-stream according to respective preset weight values of a preset weight matrix, and the pulse sequence representing the input stochastic bit-stream and the pulse sequence representing the weight stochastic bit-stream are applied to a word line and a bit line of the memory array respectively. In addition, a result multiply-accumulating between the input stochastic bit-stream and the weight stochastic bit-stream of each memory device of the memory array is stored as a conductance value of the corresponding memory device.