31 results about "Neuron membrane" patented technology

Described is a neuromorphic system implemented in hardware that implements neuron membrane potential update based on the leaky integrate and fire (LIF) model. The system further models synapse weights update based on the spike time-dependent plasticity (STDP) model. The system includes an artificial neural network in which the update scheme of neuron membrane potential and synapse weight are effectively defined and implemented.

The invention relates to a method and a system for converting neuron membrane potential into a pulse sequence, belonging to the field of neural network control. The pulse sequence and the second membrane potential data determine the hard threshold, and according to the hard threshold, the membrane potential data of the biological neuron model is converted into the second pulse sequence; the first pulse sequence is converted into the first pulse moment set represented by the time, and the The second pulse sequence is converted into a second pulse time set represented by time; the maximum error tolerance of the elements in the first pulse time set and the elements in the second pulse time set is determined according to the first pulse time set and the second pulse time set; Based on the first set of pulse times and the second set of pulse times, a pulse sequence of the biological neuron model with maximum error tolerance is determined. The invention improves the accuracy of converting the membrane potential of the biological neuron model into a pulse sequence.

The invention provides a reconfigurable self-learning pulse neural network processor, which includes a processing unit array composed of a plurality of processing units and channels in four directions of east, south, west and north; the processing unit includes an external routing module, a sorting module, pulse queue module, controller module, search module, memory module, client module, server module, internal routing module, multiple exclusive computing resources and multiple borrowable computing resources; the processor adopts pulse generation time and source neural The pulse packet transmission signal composed of element ID; the mode of computing resource execution calculation is divided into reasoning mode and learning mode, and the reconfigurable circuit is used to update the target neuron membrane potential, synaptic weight related variables or synaptic weight; computing resource Including adaptive clock-driven and event-driven computing mechanism modules, according to the update time interval, adaptively change the calculation method of the calculation unit to perform update calculations.

A method and system are provided for updating a neuron membrane potential in a spike time dependent plasticity model in a Neuromorphic system. The method includes approximating a shape of an analog spike signal from an axon input using a hardware-based digital axon timer. The method further includes generating a first intermediately updated neuron membrane potential value from a current axon timer value, a current synapse weight value and a current neuron membrane potential value using a first look-up table and an accumulator. The method also includes generating a second intermediately updated neuron membrane potential value with a leak decay effect using a second look-up table and the first intermediately updated neuron membrane potential value. The method additionally includes generating a final updated neuron membrane potential value based on a comparison of the second intermediately updated neuron membrane potential value with a neuron fire threshold level using a comparator.

The inventors surprisingly found that neural stimulation caused the synthesis and degradation of proteins into peptides which were then secreted into the cell media within minutes of stimulation by a novel neural-specific and membrane bound proteasome (neuronal membrane proteasome or NMP) that is transmembrane in nature. These secreted, activity-induced, proteasomal peptides (SNAPPs) range in size from about 500 Daltons to about 3000 Daltons. Surprisingly none of the peptides appear to be those previously known to have any neuronal function. Moreover, these SNAPPs have stimulatory activity and are heretofore a new class of signaling molecules. Moreover, the NMP appears to play a highly significant role in aspects of neuronal signaling known to be critical for neuronal function. The inventors have gone on to develop all tools to study this novel mechanisms including protocols and practice for generation and purification of SNAPPs as well as a new and specific inhibitor of the NMP allowing for selective control of this process in the nervous system. The present invention provides methods of making and using these SNAPPs for both laboratory and clinical purposes, the screening for molecules which modulate NMP function in vivo and in vitro, and methods for diagnosis of NMP related diseases.

The invention discloses an image classification method based on a multi-layer spiking convolutional neural network, relates to the field of image processing, converts images in a training set into pulse sequences; sets the parameters of spiking neurons, and uses the spiking neurons to construct a convolutional neural network ; Using the pulse sequence as input, train the convolutional neural network layer by layer, obtain the classification result after obtaining the visual features of the pulse sequence, the training method is an unsupervised learning algorithm based on hebbian rules; the image to be identified Convert it into a pulse sequence, input the trained convolutional neural network, and get the classification result of the image to be recognized; this method solves the technical problem of redundant calculation of spiking neuron membrane voltage due to the increase of neuron scale, and solves the The activation function is not derivable, and it is impossible to use backpropagation to calculate the residual, which leads to technical problems that the learning does not converge.