Online adaptation of neural network compression using weight masking
AssigneeEMC IP Holding Company LLC
InventorsTiago Salviano Calmon, Vinicius Michel Gottin, Paulo Abelha Ferreira
Life of this patent
Estimating the term…
Abstract
Dynamic adapting neural networks. A latency of a neural network, such as time to inference, is controlled by dynamically compressing/decompressing the neural network. The level of compression or the compression ratio is based on a relationship between the latency and the desired service level. The compression ratio and thus the level of compression can be adjusted until the latency complies with a required latency. A minimum level of accuracy is maintained such that catastrophic forgetting does not occur in the neural network.
Claims20
A method for dynamically adapting a neural network, the method comprising:
- determining a latency associated with the neural network;
- determining a current compression level applied to the neural network;
- determining a relation parameter that relates the latency with the current compression level;
- adjusting a compression ratio based on the relation parameter;
- and
- applying the compression ratio to the neural network.
A non-transitory storage medium having stored therein instructions that are executable by one or more hardware processors to perform operations comprising:
- determining a latency associated with the neural network;
- determining a current compression level applied to the neural network;
- determining a relation parameter that relates the latency with the current compression level;
- adjusting a compression ratio based on the relation parameter;
- and
- applying the compression ratio to the neural network.
Dependencies are inferred from the claim text.