Artificial neural network with dynamic transfer learning capability and optogenetic implementation
AssigneeUVic Industry Partnerships Inc.
InventorsBrosnan Yuen, Xiaodai Dong, Tao Lu
Life of this patent
Estimating the term…
Loading patent…
AssigneeUVic Industry Partnerships Inc.
InventorsBrosnan Yuen, Xiaodai Dong, Tao Lu
Estimating the term…
Training large neural networks on big datasets requires significant computational resources and time. Transfer learning reduces training time by pre-training a base model on one dataset and transferring the knowledge to a new model for another dataset; while current choices of transfer learning algorithms are limited, biological neural networks (BNNs) are adept at rearranging themselves to tackle completely different problems using transfer learning. Taking advantage of BNNs, an artificial neural network (ANN) with dynamic transfer learning capability is transferable to any other network architecture and can accommodate many datasets. The ANN includes artificial neurons and artificial glial cells distributed within an N-dimensional space; connections are formed between pairs of artificial neurons that meet certain criteria. In an optogenetics implementation, machine learning models such as the disclosed ANN are implemented on real BNNs to decrease power consumption.
A computing system implementing an artificial neural network, the computing system comprising:
A computer-implemented method for implementing an artificial neural network, comprising:
One or more non-transitory computer-readable media comprising computer-executable instructions that, when executed by a computing system, cause the computing system to perform operations comprising:
A method for training live biological neurons to emulate the behavior of a machine learning model, comprising:
Dependencies are inferred from the claim text.