Latent Cognizance: What Machine Really Learns
This work addresses the problem of enabling machines to identify out-of-scope questions, which is incremental as it builds on prior LC research by directly investigating its probabilistic interpretation.
The paper tackles the challenge of scalable open-set recognition in machine learning by investigating Latent Cognizance (LC), a new probabilistic interpretation based on Bayesian theorem and internal model analysis, showing its viability in sign language recognition and supporting its rationale to reveal hidden mechanisms.
Despite overwhelming achievements in recognition accuracy, extending an open-set capability -- ability to identify when the question is out of scope -- remains greatly challenging in a scalable machine learning inference. A recent research has discovered Latent Cognizance (LC) -- an insight on a recognition mechanism based on a new probabilistic interpretation, Bayesian theorem, and an analysis of an internal structure of a commonly-used recognition inference structure. The new interpretation emphasizes a latent assumption of an overlooked probabilistic condition on a learned inference model. Viability of LC has been shown on a task of sign language recognition, but its potential and implication can reach far beyond a specific domain and can move object recognition toward a scalable open-set recognition. However, LC new probabilistic interpretation has not been directly investigated. This article investigates the new interpretation under a traceable context. Our findings support the rationale on which LC is based and reveal a hidden mechanism underlying the learning classification inference. The ramification of these findings could lead to a simple yet effective solution to an open-set recognition.