# US 12,008,461 B2 · Method for determining neuron events based on cluster activations and apparatus performing same method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,008,461 B2 - Document ID: US12008461B2 - Status: Granted - Kind: B2 - Application number: 17/171,551 - Filed: 2021-02-09 - Published: 2021-06-03 - Granted: 2024-06-11 - Earliest claimed: 2016-07-13 - Assignees: Samsung Electronics Co., Ltd.; Universitaet Zuerich - Applicants: Samsung Electronics Co., Ltd.; Universitaet Zuerich - Inventors: Jun Haeng Lee; Daniel Neil; Shih-Chii Liu; Tobi Delbruck - Web page: https://patentgrep.com/patent/US12008461B2 ## CPC - G06N 3/063: using electronic means - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs - G06N 3/0495: Quantised networks; Sparse networks; Compressed networks - G06F 3/002: {Specific input/output arrangements not covered by G06F3/01 - G06F3/16 (other optical apparatus G02B27/00)} - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A method for operating an artificial neuron and an apparatus for performing the method are provided. The artificial neuron may calculate a change amount of an activation based on an input signal received via an input synapse, determine whether an event occurs in response to the calculated change amount of the activation, and transmit, to an output synapse, an output signal that corresponds to the event in response to an occurrence of the event. ## Claims ### Claim 1 A method which is performable by using a neural network, the method comprising: determining a current activation of an artificial neuron based on a previous activation of the artificial neuron and an input signal received via an input synapse of the artificial neuron; determining whether an event occurs in response to a first cluster that includes the previous activation and a second cluster that includes the determined current activation; and transmitting, to an output synapse, an output signal that corresponds to the event in response to an occurrence of the event, wherein the output signal includes at least one change bit that indicates at least one from among a change direction of at least one from among the first cluster and the second cluster and a change amount of the at least one from among the first cluster and the second cluster. ### Claim 2 (depends on 1) The method of claim 1, wherein the event occurs in response to the first cluster differing from the second cluster. ### Claim 3 (depends on 1) The method of claim 1, wherein the change direction is indicated by a sign bit. ### Claim 4 (depends on 1) The method of claim 1, wherein the at least one change bit may include more than two bits. ### Claim 5 (depends on 1) The method of claim 1, wherein the first cluster and the second cluster have different ranges. ### Claim 6 (depends on 1) The method of claim 1, wherein the neural network includes at least one from among an artificial neural network, a fully connected network, a deep convolutional network, a recurrent neural network, and a spiking neural network. ### Claim 7 (depends on 1) The method of claim 1, wherein the artificial neuron includes a decoder configured to decode the input signal, an encoder configured to generate the output signal, and a transmitter configured to transmit the output signal. ### Claim 8 An apparatus, comprising: a processor configured to execute instructions; and a memory storing the instructions, wherein execution of the instructions configures the processor to: determine a current activation of an artificial neuron based on a previous activation of the artificial neuron and an input signal received via an input synapse of the artificial neuron; determine whether an event occurs in response to a first cluster that includes the previous activation and a second cluster that includes the determined current activation; and transmit, to an output synapse, an output signal that corresponds to the event in response to an occurrence of the event, wherein the output signal includes at least one change bit that indicates at least one from among a change direction of at least one from among the first cluster and the second cluster and a change amount of the at least one from among the first cluster and the second cluster. ### Claim 9 (depends on 8) The apparatus of claim 8, wherein the event occurs in response to the first cluster differing from the second cluster. ### Claim 10 (depends on 8) The apparatus of claim 8, wherein the change direction is indicated by a sign bit. ### Claim 11 (depends on 8) The apparatus of claim 8, wherein the at least one change bit may include more than two bits. ### Claim 12 (depends on 8) The apparatus of claim 8, wherein the first cluster and the second cluster have different ranges. ### Claim 13 (depends on 8) The apparatus of claim 8, wherein the neural network includes at least one from among an artificial neural network, a fully connected network, a deep convolutional network, a recurrent neural network, and a spiking neural network. ### Claim 14 (depends on 8) The apparatus of claim 8, wherein the artificial neuron includes a decoder configured to decode the input signal, an encoder configured to generate the output signal, and a transmitter configured to transmit the output signal. ### Claim 15 An electronic device comprising: a plurality of processing components that respectively correspond to artificial neurons, wherein each of the processing components includes a respective processor and a respective memory configured to store respective computer-readable instructions, and wherein for each respective processor, when the corresponding instructions are executed by the respective processor, the respective processor is configured to: determine a current activation of an artificial neuron based on a previous activation of the artificial neuron and an input signal received via an input synapse of the artificial neuron; determine whether an event occurs in response to a first cluster that includes the previous activation and a second cluster that includes the determined current activation; and transmit, to an output synapse, an output signal that corresponds to the event in response to an occurrence of the event, wherein the output signal includes at least one change bit that indicates at least one from among a change direction of at least one from among the first cluster and the second cluster and a change amount of the at least one from among the first cluster and the second cluster. ### Claim 16 (depends on 15) The electronic device of claim 15, wherein the event occurs in response to the first cluster differing from the second cluster. ### Claim 17 (depends on 15) The electronic device of claim 15, wherein the change direction is indicated by a sign bit and the at least one change bit may include more than two bits. ### Claim 18 (depends on 15) The electronic device of claim 15, wherein the first cluster and the second cluster have different ranges. ### Claim 19 (depends on 15) The electronic device of claim 15, wherein the artificial neuron includes a decoder configured to decode the input signal, an encoder configured to generate the output signal, and a transmitter configured to transmit the output signal.