Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

39 results about "Interneuron" patented technology

An interneuron (also called internuncial neuron, relay neuron, association neuron, connector neuron, intermediate neuron or local circuit neuron) is a broad class of neurons found in the human body. Interneurons create neural circuits, enabling communication between sensory or motor neurons and the central nervous system (CNS). They have been found to function in reflexes, neuronal oscillations, and neurogenesis in the adult mammalian brain.

Automated Construction of Neural Network Architecture with Bayesian Graph Exploration

PendingUS20220004875A1Efficient searchPromote nuisance-robust feature extractionMathematical modelsNeural architecturesData setInterneuron
A system for automated construction of an artificial neural network architecture is provided. The system includes a set of interfaces and data links configured to receive and send signals, wherein the signals include datasets of training data, validation data and testing data, wherein the signals include a set of random number factors in multi-dimensional signals X, wherein part of the random number factors are associated with task labels Y to identify, and nuisance variations S. The system further includes a set of memory banks to store a set of reconfigurable deep neural network (DNN) blocks, hyperparameters, trainable variables, intermediate neuron signals, and temporary computation values including forward-pass signals and backward-pass gradients. The system further includes at least one processor, in connection with the interface and the memory banks, configured to submit the signals and the datasets into the reconfigurable DNN blocks, wherein the at least one processor is configured to execute a Bayesian graph exploration using the Bayes-Ball algorithm to reconfigure the DNN blocks such that redundant links are pruned to be compact by modifying the hyperparameters in the memory banks. The system realizes nuisance-robust variational Bayesian inference to be transferable to new datasets in semi-supervised settings.
Owner:MITSUBISHI ELECTRIC RES LAB INC

Illumination regulating and controlling composition for specifically regulating and controlling internuncial neuron activity of hypothalamus and application of illumination regulating and controlling composition

The invention provides an illumination regulating and controlling composition for specifically regulating and controlling internuncial neuron activity of hypothalamus and an application of the illumination regulating and controlling composition. The internuncial neuron activity of the hypothalamus is specifically regulated and controlled by an optogenetic regulation and control technology to affect an anxiety behavior. The illumination regulating and controlling composition for specifically regulating and controlling the internuncial neuron activity of the hypothalamus comprises a virus vector and an illumination device, wherein the virus vector is used for infecting photoesthetic genes carried by internuncial neurons or precursor cells of the internuncial neurons; the carrier comprises a promoter, the photoesthetic genes and a green fluorescence marker gene; the promoter is a VGAT promoter; and the illumination device is used for carrying out illumination regulation and control on the infected internuncial neuron cells or precursor cells of the internuncial neuron cells to change the activity. According to the technique provided by the invention, the internuncial neurons of the hypothalamus can be accurately and specifically regulated and controlled; and anxiety-like behaviors can be effectively affected.
Owner:SHENZHEN INST OF ADVANCED TECH

Prediction method and device based on multi-modal extreme learning machine, equipment and medium

PendingCN114386523ASolve the technical problem of unstable precisionCharacter and pattern recognitionNeural architecturesLearning machineInterneuron
The invention discloses a prediction method and device based on a multi-mode extreme learning machine, equipment and a medium, and the method comprises the steps: obtaining training data and neuron weight parameters under probability distribution, and constructing a tag vector corresponding to the training data; constructing a plurality of intermediate neurons under each probability distribution according to the weight parameters of the neurons; according to the plurality of interneurons, constructing composite features of the training data under each probability distribution; second-order sample features corresponding to the composite features are calculated, and a kernel matrix corresponding to the second-order sample features is constructed; and obtaining a to-be-predicted sample, and predicting the to-be-predicted sample according to an extreme learning machine model jointly constructed by the kernel matrix and the label vector to obtain a prediction result. The method can be applied to solving data-driven modeling problems, such as image classification, sequence prediction, geophysics, credit evaluation and the like. The technical problem of unstable precision caused by random mapping of an extreme learning machine model in the prior art is solved.
Owner:INST OF ADVANCED TECH UNIV OF SCI & TECH OF CHINA

A Probabilistic Calculation-Based Artificial Neural Network Hardware Realization Device

ActiveCN105913118BSave hardware logic resourcesLow costPhysical realisationNerve networkInterneuron
The invention relates to an artificial neural network hardware implementation device based on probability calculation. The artificial neural network hardware implementation device based on probability calculation comprises input, intermediate and output modules. The input module is formed by I input neurons, and the input neurons receive first data and output a first random data sequence; the intermediate module is formed by J intermediate neurons, and the intermediate neurons receive the first random data / parameter sequence and output a second random sequence; and the output module is formed by K output neurons, and the output neurons receive the second random data / parameter sequence and output the second data, wherein I, J and K are integers greater than or equal to 1. The output end of the input neurons is connected with the input end of the intermediate neurons, the output end of the intermediate neurons is connected with the input end of the output neurons, and a complete or partial connection mode is adopted. The first and second random data sequences and the first and second random parameter sequences are expressed by the probability values of 0 or 1 appearing in the data sequences within a period of time. According to the neural network device, hardware logic and wiring resources can be greatly reduced, and circuit cost and power consumption can be reduced so that implementation of a super-large-scale neural network through small and medium-sized circuits is enabled to be possible.
Owner:SHANGHAI 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
Try Eureka
PatSnap group products