US Patent Application 18295692. COMPUTER IMPLEMENTED METHOD AND APPARATUS FOR UNSUPERVISED REPRESENTATION LEARNING simplified abstract
COMPUTER IMPLEMENTED METHOD AND APPARATUS FOR UNSUPERVISED REPRESENTATION LEARNING
Organization Name
Inventor(s)
Artem Moskalev of Amsterdam (NL)
Arnold Smeulders of Amsterdam (NL)
Volker Fischer of Renningen (DE)
COMPUTER IMPLEMENTED METHOD AND APPARATUS FOR UNSUPERVISED REPRESENTATION LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18295692 titled 'COMPUTER IMPLEMENTED METHOD AND APPARATUS FOR UNSUPERVISED REPRESENTATION LEARNING
Simplified Explanation
The patent application describes an apparatus and method for unsupervised representation learning.
- The method involves using an input data set that includes samples from two different domains.
- A reference assignment is provided between pairs of samples from the two domains.
- An encoder is used to map the input data samples to embeddings, which are representations of the samples.
- A similarity kernel is used to determine the similarity between the embeddings.
- The encoder is used to determine embeddings for samples from both domains.
- The similarity kernel is used to determine similarities between pairs of embeddings from the two domains.
- The encoder's parameters are adjusted based on a loss function to improve the quality of the embeddings.
Original Abstract Submitted
An apparatus and a computer implemented method for unsupervised representation learning. The method includes: providing an input data set comprising samples of a first domain and samples of a second domain; providing a reference assignment between pairs of one sample from the first domain and one sample from the second domain; providing an encoder that is configured to map a sample of the input data set depending on at least one parameter of the encoder to an embedding; providing a similarity kernel for determining a similarity between embeddings; determining with the encoder embeddings of samples from the first domain and embeddings of samples from the second domain; determining with the similarity kernel similarities for pairs of one embedding of a sample from the first domain and one embedding of a sample from the second domain; determining at least one parameter of the encoder depending on a loss.