Adaptable neural network
AssigneeKoninklijke Philips N.V.
InventorsBinyam Gebrekidan Gebre, Stojan Trajanovski
Life of this patent
Estimating the term…
Abstract
An adaptable neural network system (1) formed of two neural networks (4, 5). One of the neural networks (5) adjusts a structure of the other neural network (4) based on information about a specific task each time that new second input data (12) indicative of a desired task is received by the one neural network (5), so that the other neural network (4) is adapted to perform that specific task. Thus, an adaptable neural network system (1) capable of performing different tasks on input data (11) can be realized.
Claims15
An adaptable neural network system for processing first input data, the neural network system comprising:
- a first neural network formed of a plurality of sequential layers, wherein the first neural network is adapted to generate output data by processing first input data using the plurality of sequential layers;
- a second neural network adapted to generate at least one task-specific parameter for the plurality of sequential layers of the first neural network based on second input data indicative of a desired task to be performed on the first input data;
- and
- a neural network modifier adapted to modify the first neural network based on the at least one task-specific parameter generated by the second neural network, to thereby adapt the first neural network to the desired task each time that new second input data is received by the second neural network.
A method of processing first input data using an adaptable neural network system comprising a first neural network formed of a plurality of sequential layers, the method comprising:
- generating, using a second neural network, at least one task-specific parameter for the plurality of sequential layers of a first neural network based on second input data indicative of a desired task to be performed on the first input data;
- modifying the first neural network based on the at least one task-specific parameter, to thereby adapt to first neural network to the desired task each time that new second input data is received by the second neural network;
- and
- generating output data by processing the first input data using the modified first neural network.
Dependencies are inferred from the claim text.