# US 2021/0232930 A1 · Temporal Coding in Leaky Spiking Neural Networks

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0232930 A1
- Document ID: US20210232930A1
- Status: Published application
- Kind: A1
- Application number: 16/972,427
- Filed: 2019-10-11
- Published: 2021-07-29
- Earliest claimed: 2018-10-11
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Jyrki Alakuijala; Iulia-Maria Comsa; Krzysztof Potempa
- Web page: https://patentgrep.com/patent/US20210232930A1

## CPC

- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/048: Activation functions
- G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 3/063: using electronic means
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Spiking neural networks that perform temporal encoding for phase-coherent neural computing are provided. In particular, according to an aspect of the present disclosure, a spiking neural network can include one or more spiking neurons that have an activation layer that uses a double exponential function to model a leaky input that an incoming neuron spike provides to a membrane potential of the spiking neuron. The use of the double exponential function in the neuron's temporal transfer function creates a better defined maximum in time. This allows very clearly defined state transitions between “now” and the “future step” to happen without loss of phase coherence.

## Claims

### Claim 1

A computer system comprising:
one or more processors; and
one or more non-transitory computer readable media that collectively store:
a machine-learned spiking neural network that comprises one or more spiking neurons that have an activation layer that uses a double exponential function to model a leaky input that an incoming neuron spike provides to a membrane potential of the spiking neuron; and
instructions that, when executed by the one or more processors, cause the computer system to perform operations, the operations comprising:
obtaining a network input;
implementing the machine-learned spiking neural network to process the network input; and
receiving a network output generated by the machine-learned spiking neural network as a result of processing the network input.

### Claim 2 (depends on 1)

The computer system of claim 1, wherein the machine-learned spiking neural network encodes information in respective spike times associated with the one or more spiking neurons.

### Claim 3 (depends on 1)

The computer system of claim 1, wherein the double exponential function models the leaky input as a double exponential pulse.

### Claim 4 (depends on 1)

The computer system of claim 1, wherein the double exponential function has the form e−t(t−1+c), where c is a hyperparameter.

### Claim 5 (depends on 1)

The computer system of claim 1, wherein the double exponential function has the form te−t.

### Claim 6 (depends on 5)

The computer system of claim 5, wherein the membrane potential of each of the one or more spiking neurons, if it has not spiked, has the form Σi wi(t−ti)eti−t, where i refers to one or more presynaptic neurons connected to the spiking neuron via one or more artificial synapses with weights wi and spiking at time points ti.

### Claim 7 (depends on 6)

The computer system of claim 6, wherein implementing the machine-learned spiking neural network comprises determining, for each of the one or more spiking neurons, a spike time that corresponds to an earliest time at which the membrane potential of the spiking neuron is equal to a firing threshold.

### Claim 8 (depends on 7)

The computer system of claim 7, wherein determining, for each of the one or more spiking neurons, the spike time comprises applying a Lambert W function to determine the spike time.

### Claim 9 (depends on 8)

The computer system of claim 8, wherein the operations further comprise:
prior to obtaining the network input, training the machine-learned spiking neural network on training data via a gradient descent technique, wherein training the machine-learned spiking neural network via the gradient descent comprises:
determining, for each of the one or more spiking neurons, one or both of:
a derivative of a spike time of such spiking neuron with respect to the time points ti; and
a derivative of the spike time of such spiking neuron with respect to one or more of the weights wi, wherein the spike time corresponds to an earliest time at which the membrane potential of such spiking neuron is equal to a firing threshold; and
modifying, for each of the one or more spiking neurons, at least one of the weights wi based at least in part on one or both of the derivative of the spike time of such spiking neuron with respect to the time points ti and the derivative of the spike time of such spiking neuron with respect to one or more of the weights wi.

### Claim 10 (depends on 1)

The computer system of claim 1, wherein the machine-learned spiking neural network comprises a plurality of layers, at least two of the plurality of layers comprising at least one of the one or more spiking neurons, and wherein the machine-learned spiking neural network has been trained on training data using a backpropagation technique.

### Claim 11 (depends on 1)

The computer system of claim 1, wherein the operations further comprise:
training the machine-learned spiking neural network on training data via a gradient descent technique to simultaneously learn both parameters of the machine-learned spiking neural network and a topology of the machine-learned spiking neural network.

### Claim 12

A computer-implemented method to train a spiking neural network that encodes information in respective spike times associated with a plurality of spiking neurons included in the spiking neural network, the method comprising:
obtaining, by one or more computing devices, data descriptive of the spiking neural network that comprises the plurality of spiking neurons, wherein each of the plurality of spiking neurons is respectively connected to one or more pre-synaptic neurons via one or more artificial synapses that have one or more weights associated therewith, wherein each of the plurality of spiking neurons has an activation layer that controls a respective spike time of such spiking neuron based on a membrane potential of such spiking neuron, and wherein the activation layer for each of the plurality of spiking neurons comprises a double exponential that models incoming spikes received from the one or more pre-synaptic neurons as leaky inputs to the membrane potential; and
training, by the one or more computing devices, the spiking neural network based on a set of training data, wherein training, by the one or more computing devices, the spiking neural network comprises:
determining, by the one or more computing devices, a gradient of a loss function that evaluates a performance of the spiking neural network on the set of training data; and
modifying, by the one or more computing devices for at least one of the plurality of spiking neurons, at least one of the one or more weights based at least in part on the gradient of the loss function.

### Claim 13 (depends on 12)

The computer-implemented method of claim 12, wherein:
each of the plurality of spiking neurons receives the incoming spikes from the one or more presynaptic neurons at respective inbound spike times; and
determining, by the one or more computing devices, the gradient of the loss function comprises determining, by the one or more computing devices, for at least one of the plurality of spiking neurons, a derivative of the spike time of such spiking neuron with respect to the inbound spike times.

### Claim 14 (depends on 12)

The computer-implemented method of claim 12, wherein determining, by the one or more computing devices, the gradient of the loss function comprises determining, by the one or more computing devices, for at least one of the plurality of spiking neurons, a derivative of the spike time of such spiking neuron with respect to one or more of the weights associated with such spiking neuron.

### Claim 15 (depends on 12)

The computer-implemented method of claim 12 wherein training, by the one or more computing devices, the spiking neural network further comprises modifying, by the one or more computing devices for at least one of the plurality of spiking neurons, at least one synaptic delay parameter based at least in part on the gradient of the loss function.

### Claim 16 (depends on 12)

The computer-implemented method of claim 12, wherein:
the plurality of spiking neurons are arranged in a plurality of layers; and
training, by the one or more computing devices, the spiking neural network comprises backpropagating, by the one or more computing devices, the loss function through the plurality of layers.

### Claim 17 (depends on 12)

The computer-implemented method of claim 12, wherein, for each of the plurality of spiking neurons, the membrane potential, if such spiking neuron has not yet spiked, has the form Σi wi(t−ti)eti−t, where i refers to the one or more presynaptic neurons connected to such spiking neuron via one or more artificial synapses, wi refers to the one or more weights associated with the one or more artificial synapses, and ti refers to respective inbound spike times at which such spiking neuron receives the incoming spikes from the one or more presynaptic neurons.

### Claim 18

An electronic device that comprises:
a machine-learned spiking neural network that comprises one or more spiking neurons;
wherein each of the one or more spiking neurons has an activation layer that uses a double exponential function to model a leaky input that an incoming neuron spike provides to a membrane potential of the spiking neuron;
and wherein the machine-learned spiking neural network is configured to receive a network input and to process the network input to generate a network output.

### Claim 19 (depends on 18)

The electronic device of claim 18, wherein the machine-learned spiking neural network comprises computer-readable instructions stored on a non-transitory computer-readable medium.

### Claim 20 (depends on 18)

The electronic device of claim 18, wherein the machine-learned spiking neural network comprises one or more electronic circuits that comprise electronic components arranged to execute the machine-learned spiking neural network using electrical current.

### Claim 21 (depends on 20)

The electronic device of claim 20, wherein, for each of the one or more spiking neurons, the corresponding electronic components that model the double exponential function comprise two capacitors, two resistors, and one or more transistors.

### Claim 22

(canceled)
