Neural functional localization using synaptic connectivity graphs

Patent metadata

Field	Value
Publication number	US-11636349-B2
Application number	US-202016829107-A
Country	US
Kind code	B2
Filing date	Mar 25, 2020
Priority date	Mar 25, 2020
Publication date	Apr 25, 2023
Grant date	Apr 25, 2023

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying one or more regions of a brain of a biological organism that are predicted to be functionally-specialized for performing a task. In one aspect, a method comprises: obtaining data defining a synaptic connectivity graph representing synaptic connectivity between neurons in the brain of the biological organism; identifying a plurality of sub-graphs of the synaptic connectivity graph; determining, for each sub-graph of the plurality of sub-graphs, a performance measure characterizing a performance of a neural network having a neural network architecture that is specified by the sub-graph in accomplishing the task; and determining, based on the performance measures, that one or more sub-graphs of the plurality of sub-graphs correspond to regions of the brain of the biological organism that are predicted to be functionally-specialized for performing the task.

First claim

What is claimed is:

1. A method performed by one or more data processing apparatus for identifying one or more regions of a brain of a biological organism that are predicted to be functionally-specialized for performing a task, the method comprising:
obtaining data defining a synaptic connectivity graph representing synaptic connectivity between neurons in the brain of the biological organism, wherein the synaptic connectivity graph is generated by processing a three-dimensional (3D) synaptic resolution image of the brain of the biological organism;
identifying a plurality of sub-graphs of the synaptic connectivity graph;
determining, for each sub-graph of the plurality of sub-graphs of the synaptic connectivity graph, a performance measure characterizing a performance of a neural network having a neural network architecture that is specified by the sub-graph of the synaptic connectivity graph in accomplishing the task, comprising, for each of the plurality of sub-graphs of the synaptic connectivity graph:
processing the sub-graph of the synaptic connectivity graph to generate a neural network having a neural network architecture that is specified by the sub-graph of the synaptic connectivity graph;
training the neural network having the neural network architecture that is specified by the sub-graph of the synaptic connectivity graph to accomplish the task; and
after the training, evaluating a performance measure of the neural network having the neural network architecture that is specified by the sub-graph of the synaptic connectivity graph in accomplishing the task; and

determining, based on the performance measures of neural networks having neural network architectures specified by the sub-graphs of the synaptic connectivity graph in accomplishing the task, that one or more sub-graphs of the plurality of sub-graphs of the synaptic connectivity graph correspond to regions of the brain of the biological organism that are predicted to be functionally-specialized for performing the task.

2. The method of claim 1 , wherein the synaptic connectivity graph comprises a plurality of nodes and edges, wherein each edge connects a pair of nodes, each node corresponds to a respective neuron in the brain of the biological organism, and each edge connecting a pair of nodes in the synaptic connectivity graph corresponds to a synaptic connection between a pair of neurons in the brain of the biological organism.

3. The method of claim 2 , wherein for each of the plurality of sub-graphs of the synaptic connectivity graph, processing the sub-graph of the synaptic connectivity graph to generate the neural network having the neural network architecture that is specified by the sub-graph of the synaptic connectivity graph comprises:
mapping each node in the sub-graph to a corresponding artificial neuron in the neural network architecture; and
for each edge in the sub-graph:
mapping the edge to a connection between a pair of artificial neurons in the neural network architecture that correspond to the pair of nodes in the sub-graph that are connected by the edge.

4. The method of claim 1 , wherein identifying the plurality of sub-graphs of the synaptic connectivity graph comprises, at each of a plurality of iterations:
identifying a current sub-graph of the synaptic connectivity graph in accordance with current values of one or more parameters; and
updating the current values of the parameters based at least in part on the performance measure characterizing the performance of the neural network having the neural network architecture that is specified by the current sub-graph in accomplishing the task.

5. The method of claim 1 , wherein evaluating the performance of the trained neural network having the neural network architecture that is specified by the sub-graph of the synaptic connectivity graph in accomplishing the task comprises:
determining an accuracy of the trained neural network having the neural network architecture in accomplishing the task.

6. The method of claim 1 , wherein evaluating the performance of the trained neural network having the neural network architecture that is specified by the sub-graph of the synaptic connectivity graph in accomplishing the task further comprises:
determining a measure of complexity of the neural network architecture that is specified by the sub-graph of the synaptic connectivity graph.

7. The method of claim 1 , further comprising:
providing data identifying the one or more sub-graphs of the plurality of sub-graphs corresponding to regions of the brain of the biological organism that are predicted to be functionally-specialized for performing the task.

8. The method of claim 1 , further comprising:
generating a visualization of the one or more sub-graphs of the plurality of sub-graphs corresponding to regions of the brain of the biological organism that are predicted to be functionally-specialized for performing the task.

9. The method of claim 1 , wherein the task is a visual data processing task.

10. The method of claim 1 , wherein the task is an audio data processing task.

11. The method of claim 1 , wherein obtaining data defining the synaptic connectivity graph representing synaptic connectivity between neurons in the brain of the biological organism comprises:
processing the 3D synaptic resolution image to segment: (i) a plurality of neurons in the 3D synaptic resolution image, and (ii) a plurality of synaptic connections between pairs of neurons in the 3D synaptic resolution image.

12. The method of claim 1 , wherein the 3D synaptic resolution image of the brain of the biological organism is generated using electron microscopy techniques.

13. The method of claim 1 , wherein determining, based on the performance measures of neural networks having architectures specified by sub-graphs of the synaptic connectivity graph in accomplishing the task, that one or more sub-graphs of the plurality of sub-graphs of the synaptic connectivity graph correspond to regions of the brain of the biological organism that are predicted to be functionally-specialized for performing the task comprises:
determining that a sub-graph of the synaptic connectivity graph associated with a highest performance measure corresponds to a region of the brain that is predicted to be functionally-specialized for performing the task.

14. A system comprising:
one or more computers; and
one or more storage devices communicatively coupled to the one or more computers, wherein the one or more storage devices store instructions that, when executed by the one or more computers, cause the one or more computers to perform operations for identifying one or more regions of a brain of a biological organism that are predicted to be functionally-specialized for performing a task, the operations comprising:
obtaining data defining a synaptic connectivity graph representing synaptic connectivity between neurons in the brain of the biological organism, wherein the synaptic connectivity graph is generated by processing a three-dimensional (3D) synaptic resolution image of the brain of the biological organism;
identifying a plurality of sub-graphs of the synaptic connectivity graph;
determining, for each sub-graph of the plurality of sub-graphs of the synaptic connectivity graph, a performance measure characterizing a performance of a neural network having a neural network architecture that is specified by the sub-graph of the synaptic connectivity graph in accomplishing the task, comprising, for each of the plurality of sub-graphs of the synaptic connectivity graph:
processing the sub-graph of the synaptic connectivity graph to gener

Assignees

• X Dev Llc

Inventors

• Laszlo Sarah Ann
• Sibigtroth Matthew
• Ni Bin

Classifications

• G06N3/082

  modifying the architecture, e.g. adding, deleting or silencing nodes or connections · CPC title

• G06N3/0985

  Hyperparameter optimisation; Meta-learning; Learning-to-learn · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0495

  Quantised networks; Sparse networks; Compressed networks · CPC title

• G06N3/10 Primary

  Interfaces, programming languages or software development kits, e.g. for simulating neural networks · CPC title