Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A reconfigurable deep belief network implementation system

A deep belief network and implementation system technology, applied in the field of deep belief network implementation system, can solve the problems of inability to balance performance and flexibility, few efficient and flexible deep belief network implementation systems, etc., to achieve good practical application value and low computational complexity high-speed, low-hardware-overhead effect

Active Publication Date: 2019-05-03
NANJING UNIV
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the existing deep belief network algorithms focus on the application level, and few efficient and flexible deep belief network implementation systems and architectures have been proposed, which cannot balance performance and flexibility, and cannot well meet the needs of practical applications.

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
  • A reconfigurable deep belief network implementation system
  • A reconfigurable deep belief network implementation system
  • A reconfigurable deep belief network implementation system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The solution of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0041]The reconfigurable deep belief network implementation system of the present invention is composed of a control unit, a restricted Boltzmann machine, a parameter update unit, and a data temporary storage unit, such as figure 1 shown.

[0042] Control unit, read including the number of network layers L, the number of nodes in each layer N i , the type of algorithm to be executed (training / reasoning), the configuration information including the number of currently visited layers t and the training status of the current layer, the operation flow of the deep belief network algorithm is controlled through the finite state machine, and the multiplexing restricted Boltzmann machine , gating the parameter updating unit to realize two algorithms of training and reasoning.

[0043] The restricted Boltzmann machine is used to calculate the activation prob...

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

The invention discloses a reconfigurable deep belief network implementation system. The system comprises a control unit used for controlling the operation process of a deep belief network algorithm; the data temporary storage unit is used for storing and calculating required input layer information, weights, offsets and output layer results; the restricted Boltzmann machine is used for calculatingthe activation probability of each layer of nodes in the deep belief network so as to determine the activation state; and the parameter updating unit is used for updating the weight and bias of eachlayer of nodes in the deep belief network, and is only activated in the training algorithm. The implementation system has the beneficial effects that two algorithms of training and reasoning can be supported by multiplexing the restricted Boltzmann machine and controlling the state jump of the algorithm, the hardware resource cost of the algorithm is reduced, the performance of the algorithm is ensured, and the implementation system is suitable for various artificial intelligence scenes.

Description

technical field [0001] The invention relates to the field of artificial intelligence algorithms, in particular to a reconfigurable deep belief network realization system. Background technique [0002] With the advancement of machine learning and the advent of deep learning, several tools and graphical representations are gradually used to correlate large amounts of data. Deep Belief Networks (Deep Belief Networks, DBN) was proposed by Hinton et al. in 2006. It is essentially a graph representation network with generative capabilities, that is, it generates all possible values ​​​​of the current example. As a fusion of probability and statistics with machine learning and neural networks, DBN consists of multiple layers with values, where there are relationships between layers but not between values. The main goal of the deep belief network is to help the system classify data into different categories, and it is widely used in application scenarios such as pattern recognition...

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): G06N3/063G06N3/08
CPCG06N3/063G06N3/088G06N3/047G06N3/048G06N3/044Y02D10/00
Inventor 李丽宋文清傅玉祥何国强李伟
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products