Back to results
US 2022/0067525 A1Published application
Techniques for pruning neural networks
AssigneeNVIDIA Corporation
InventorsDilip Sequeira, Pavlo Molchanov, Gregory Heinrich, Edvard Olav Valter Fagerholm
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques to reduce a size of neural networks. In at least one embodiment, a size of a neural network is reduced by at least removing one or more neurons of the neural network and adjusting one or more layers of the neural network to compensate for the removed one or more neurons.
Claims34
A processor, comprising:
- one or more circuits to reduce the size of a neural network by at least removing one or more neurons of the neural network and adjusting one or more layers of the neural network to compensate for the removed one or more neurons.
A machine-readable medium having stored thereon a set of instructions, which if performed by one or more processors, cause the one or more processors to at least:
- prune a neural network by at least removing one or more neurons of the neural network and adjusting one or more layers of the neural network to compensate for the pruned one or more neurons.
A method, comprising:
- reducing the size of a neural network by at least removing one or more neurons of the neural network and adjusting one or more layers of the neural network to compensate for the removed one or more neurons.
A system, comprising:
- one or more processors to reduce the size of a neural network by at least removing one or more neurons of the neural network and adjusting one or more layers of the neural network to compensate for the removed one or more neurons;
- and
- one or more memories to store a representation of the size reduced neural network.
A vehicle comprising:
- a computer vision system that includes one or more processors to identify one or more features of a vehicle operating environment based, at least in part, on using a first neural network generated, at least in part, by reducing the size of a second neural network by at least removing one or more neurons of the second neural network and adjusting one or more layers of the second neural network to compensate for the removed one or more neurons;
- and
- one or more of a propulsion system and a directional control system to control one or more movements of the vehicle based, at least in part, on the identified one or more features.
Dependencies are inferred from the claim text.