18468203. MULTI-RESOLUTION FIELD REPRESENTATIONS IN NEURAL NETWORKS (QUALCOMM Incorporated)
MULTI-RESOLUTION FIELD REPRESENTATIONS IN NEURAL NETWORKS
Organization Name
Inventor(s)
Kartikeya Bhardwaj of San Diego CA US
Paul Nicholas Whatmough of Cambridge MA US
Christopher Lott of San Diego CA US
Viswanath Ganapathy of Dublin CA US
Chirag Sureshbhai Patel of San Diego CA US
Joseph Binamira Soriaga of San Diego CA US
MULTI-RESOLUTION FIELD REPRESENTATIONS IN NEURAL NETWORKS
This abstract first appeared for US patent application 18468203 titled 'MULTI-RESOLUTION FIELD REPRESENTATIONS IN NEURAL NETWORKS
Original Abstract Submitted
Certain aspects provide techniques and apparatuses for efficiently processing inputs in a neural network using multiple receptive field sizes. An example method includes partitioning a first input into a first set of channels and a second set of channels. At a first layer of a neural network, the first set of channels and the second set of channels are convolved into a first output having a smaller dimensionality a dimensionality of the first input. The first set of channels and the first output are concatenated into a second input. The second input is convolved into a second output via a second layer of the neural network, wherein the second output merges a first receptive field generated by the first layer with a larger second receptive field generated by the second layer. One or more actions are taken based on at least one of the first output and the second output.
- QUALCOMM Incorporated
- Kartikeya Bhardwaj of San Diego CA US
- Piero Zappi of La Jolla CA US
- Paul Nicholas Whatmough of Cambridge MA US
- Christopher Lott of San Diego CA US
- Viswanath Ganapathy of Dublin CA US
- Chirag Sureshbhai Patel of San Diego CA US
- Joseph Binamira Soriaga of San Diego CA US
- G06N3/0464
- CPC G06N3/0464