Multiplicative Filter Network

A system comprising:

• at least one sensor to provide sensor data;
• one or more non-transitory computer readable storage devices that include at least (i) a machine learning system and (ii) computer readable data that is executable to perform a method involving the machine learning system;
• and
• one or more processors operably connected to the one or more non-transitory computer readable storage devices, the one or more processors being configured to execute the computer readable data to perform the method, wherein the method includes:
• obtaining input data based on the sensor data;
• applying a filter to the input data based on an initial set of parameters to generate an initial feature map, wherein the filter is configured to activate a filter function that involves a periodic function;
• performing a first linear transform on the initial feature map based on a subset of a first set of parameters to generate a first linear transform;
• applying the filter to the input data based on another subset of the first set of parameters to generate a first feature map;
• performing a multiplicative operation on the first linear transform and the first feature map to obtain a first product;
• performing a second linear transform on the first product based on a subset of a second set of parameters to generate a second linear transform;
• and
• providing output data that takes into account at least the second linear transform.

A computer product comprising at least one non-transitory computer readable storage device that includes computer-readable data, which when executed by one or more electronic processors, is operable to cause the one or more electronic processors to implement a method that comprises:

• obtaining input data;
• applying a filter to the input data based on an initial set of parameters to generate an initial feature map, wherein the filter is configured to activate a filter function that involves a periodic function;
• transforming the initial feature map based on a subset of a first set of parameters to generate a first linear transform;
• applying the filter to the input data based on another subset of the first set of parameters to generate a first feature map;
• performing a multiplicative operation on the first linear transform and the first feature map to generate a first product;
• transforming the first product based on a subset of a second set of parameters to generate a second linear transform;
• and
• generating output data that takes into account at least the second linear transform.