Unlock instant, AI-driven research and patent intelligence for your innovation.

Distance based deep learning

A distance vector and vector technology, applied in the field of associative memory devices, can solve problems such as heavy calculations, and achieve the effect of reducing size

Pending Publication Date: 2019-09-03
GSI TECH
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It requires a lot of matrix-vector multiplication and SoftMax operations, which are computationally heavy

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Distance based deep learning
  • Distance based deep learning
  • Distance based deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be understood by those skilled in the art that the present invention may be practiced without these specific details. In other instances, well-known methods, procedures, and components have not been described in detail so as not to obscure the present invention.

[0052] Applicants have realized that parts of artificial networks such as RNNs (including LSTMs (Long Short Term Memory) and GRUs (Gated Recurrent Units)) can be efficiently implemented with associative memory devices. A system such as that described in U.S. Patent Publication US2017 / 0277659, entitled "INMEMORY MATRIX MULTIPLICATION AND ITS USAGE IN NEURAL NETWORKS" (which is assigned to the common assignee of the present invention and is incorporated herein by reference), can compute The matrix multiplication part of provides linear or event co...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method for a neural network includes concurrently calculating a distance vector between an output feature vector describing an unclassified item and each of a plurality of qualified feature vectors,each describing one classified item out of a collection of classified items. The method includes concurrently computing a similarity score for each distance vector and creating a similarity score vector of the plurality of computed similarity scores. A system for a neural network includes an associative memory array, an input arranger, a hidden layer computer and an output handler. The input arranger manipulates information describing an unclassified item stored in the memory array. The hidden layer computer computes a hidden layer vector. The output handler computes an output feature vectorand concurrently calculates a distance vector between an output feature vector and each of a plurality of qualified feature vectors, and concurrently computes a similarity score for each distance vector.

Description

technical field [0001] The present invention relates generally to associative memory devices, and more particularly to deep learning in associative memory devices. Background technique [0002] Neural networks are computing systems that learn to perform tasks by considering examples, usually without task-specific programming. A typical neural network is an interconnected group of nodes organized in layers; each layer can perform a different transformation on its input. Neural networks can be represented mathematically as vectors, representing the activations of nodes in a layer, and matrices, representing the weights of the interconnections between nodes in adjacent layers. Network functions are a series of mathematical operations performed on and between vectors and matrices, and non-linear operations performed on values ​​stored in vectors and matrices. [0003] Throughout this application, matrices are denoted by bold capital letters, eg, A, vectors in lowercase bold, e...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04
CPCG06N3/044G06N3/045G06N3/08G06N20/00G06N3/048G06N3/09G06N3/047G06N7/01
Inventor E·埃雷兹
Owner GSI TECH