Channel-Independent and Sensor-Independent Stimulus Representations

TL;DR

This paper introduces a method for extracting stimulus representations that are independent of the specific sensors and channels used by a machine, enabling consistent perception across different devices through differential geometric analysis of stimulus trajectories.

Contribution

The paper presents a novel geometric framework that derives channel- and sensor-independent stimulus representations from uncalibrated sensory data, facilitating cross-device consistency.

Findings

Stimulus trajectories define a geometric structure that can be used for invariant representation.

The method is demonstrated with analytic examples and numerical simulations.

Channel- and sensor-independent representations can improve pattern recognition across different devices.

Abstract

This paper shows how a machine, which observes stimuli through an uncharacterized, uncalibrated channel and sensor, can glean machine-independent information (i.e., channel- and sensor-independent information) about the stimuli. First, we demonstrate that a machine defines a specific coordinate system on the stimulus state space, with the nature of that coordinate system depending on the device's channel and sensor. Thus, machines with different channels and sensors "see" the same stimulus trajectory through state space, but in different machine-specific coordinate systems. For a large variety of physical stimuli, statistical properties of that trajectory endow the stimulus configuration space with differential geometric structure (a metric and parallel transfer procedure), which can then be used to represent relative stimulus configurations in a coordinate-system-independent manner (and, therefore, in a channel- and sensor-independent manner). The resulting description is an "inner" property of the stimulus time series in the sense that it does not depend on extrinsic factors like the observer's choice of a coordinate system in which the stimulus is viewed (i.e., the observer's choice of channel and sensor). This methodology is illustrated with analytic examples and with a numerically simulated experiment. In an intelligent sensory device, this kind of representation "engine" could function as a "front-end" that passes channel/sensor-independent stimulus representations to a pattern recognition module. After a pattern recognizer has been trained in one of these devices, it could be used without change in other devices having different channels and sensors.