MIRROR LOSS NEURAL NETWORKS
First Claim
1. A method of training a neural network having a plurality of network parameters, wherein the neural network is configured to receive an input observation characterizing a state of an environment and to process the input observation to generate a numeric embedding of the state of the environment, the method comprising:
- obtaining a first observation captured by a first modality;
obtaining a second observation that is co-occurring with the first observation and that is captured by a second, different modality;
obtaining a third observation captured by the first modality that is not co-occurring with the first observation;
determining a gradient of a triplet loss that uses the first observation as an anchor example, the second observation as a positive example, and the third observation as a negative example; and
updating current values of the network parameters using the gradient of the triplet loss.
1 Assignment
0 Petitions
Accused Products
Abstract
This description relates to a neural network that has multiple network parameters and is configured to receive an input observation characterizing a state of an environment and to process the input observation to generate a numeric embedding of the state of the environment. The neural network can be used to control a robotic agent. The network can be trained using a method comprising: obtaining a first observation captured by a first modality; obtaining a second observation that is co-occurring with the first observation and that is captured by a second, different modality; obtaining a third observation captured by the first modality that is not co-occurring with the first observation; determining a gradient of a triplet loss that uses the first observation, the second observation, and the third observation; and updating current values of the network parameters using the gradient of the triplet loss.
6 Citations
24 Claims
-
1. A method of training a neural network having a plurality of network parameters, wherein the neural network is configured to receive an input observation characterizing a state of an environment and to process the input observation to generate a numeric embedding of the state of the environment, the method comprising:
-
obtaining a first observation captured by a first modality; obtaining a second observation that is co-occurring with the first observation and that is captured by a second, different modality; obtaining a third observation captured by the first modality that is not co-occurring with the first observation; determining a gradient of a triplet loss that uses the first observation as an anchor example, the second observation as a positive example, and the third observation as a negative example; and updating current values of the network parameters using the gradient of the triplet loss. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers, cause the one or more computers to perform operations for training a neural network having a plurality of network parameters, wherein the neural network is configured to receive an input observation characterizing a state of an environment and to process the input observation to generate a numeric embedding of the state of the environment, the operations comprising:
-
obtaining a first observation captured by a first modality; obtaining a second observation that is co-occurring with the first observation and that is captured by a second, different modality; obtaining a third observation captured by the first modality that is not co-occurring with the first observation; determining a gradient of a triplet loss that uses the first observation as an anchor example, the second observation as a positive example, and the third observation as a negative example; and updating current values of the network parameters using the gradient of the triplet loss.
-
-
13. One or more non-transitory computer storage media storing instructions that when executed by one or more computers, cause the one or more computers to perform operations for training a neural network having a plurality of network parameters, wherein the neural network is configured to receive an input observation characterizing a state of an environment and to process the input observation to generate a numeric embedding of the state of the environment, the operations comprising:
-
obtaining a first observation captured by a first modality; obtaining a second observation that is co-occurring with the first observation and that is captured by a second, different modality; obtaining a third observation captured by the first modality that is not co-occurring with the first observation; determining a gradient of a triplet loss that uses the first observation as an anchor example, the second observation as a positive example, and the third observation as a negative example; and updating current values of the network parameters using the gradient of the triplet loss. - View Dependent Claims (18, 19, 20, 21, 22, 23, 24)
-
-
14-17. -17. (canceled)
Specification