US 2019/0318224 A1 · EFFICIENT AND SCALABLE SYSTEMS FOR CALCULATING NEURAL NETWORK CONNECTIVITY IN AN EVENT-DRIVEN WAY

Abstract

Systems and methods achieving scalable and efficient connectivity in neural algorithms by re-calculating network connectivity in an event-driven way are disclosed. The disclosed solution eliminates the storing of a massive amount of data relating to connectivity used in traditional methods. In one embodiment, a deterministic LFSR is used to quickly, efficiently, and cheaply re-calculate these connections on the fly. An alternative embodiment caches some or all of the LFSR seed values in memory to avoid sequencing the LFSR through all states needed to compute targets for a particular active neuron. Additionally, connections may be calculated in a way that generates neural networks with connections that are uniformly or normally (Gaussian) distributed.

Claims20

Dependent claims

A scalable system for recalculating, in an event-driven manner, property parameters including connectivity parameters of a neural network, the system comprises:

an input component that receives a time varying input signal;
a storage component for storing the property parameters of the neural network;
a state machine capable of recalculating property parameters of the neural network, wherein the property parameters include connectivity among neurons of the neural network;
and
an output component that generates output signals reflective of the calculated property parameters of the neural network and the input signal.

2 more elements

A computer-implemented method for recalculating network property parameters of a neural network including connectivity parameters in an event-driven manner, the method comprises:

initializing property parameters of the neural network;
receiving, at an evaluating neuron of the neural network, a neural input corresponding to a time varying input signal to the neural network;
recalculating by a state machine of the neural network at least some of the property parameters of the evaluating neuron, wherein the property parameters are random but determined after initialization;
determining whether the evaluating neuron is to generate a neural output to its target neurons in the neural network;
and
if the evaluating neuron is determined to generate a neural output to its target neurons in the neural network, propagating the output of the evaluating neuron to its target neurons.

3 more elements

Dependencies are inferred from the claim text.

Facts

Application

16/453,876Filed 26 Jun 2019

Priority

1 Oct 2014

Published

17 Oct 2019

Term ends

Not estimatedThe source records don’t support an estimate.

Classification4 codes

G06N 3/04
Neural networks: architecture, e.g. interconnection topology
G06N 3/0495
Architecture, e.g. interconnection topology: quantised networks; Sparse networks; Compressed networks
G06N 3/08
Neural networks: learning methods
G06N
AI and machine learning

Family

Application62/058,565Us provisional application · filed 1 Oct 2014

Application14/873,138Continuation · filed 1 Oct 2015

Application16/453,876Continuation

US 10,339,439 B2Related patent

US 2016/0098629 A1Published application

US 2019/0318224 A1This patent

From the US filing history. Foreign family members aren’t listed.

Efficient and scalable systems for calculating neural network connectivity in an event-driven way

Life of this patent

Efficient and scalable systems for calculating neural network connectivity in an event-driven way

Life of this patent

Abstract

Claims20