Elements of Active Continuous Learning and Uncertainty Self-Awareness: a Narrow Implementation for Face and Facial Expression Recognition

TL;DR

This paper introduces a self-awareness mechanism in neural networks that monitors uncertainty in face recognition tasks, enabling active learning and human intervention to improve performance.

Contribution

It presents a novel self-awareness ANN that observes CNN activations to assess trustworthiness, facilitating active learning in narrow AI applications.

Findings

Effective uncertainty detection in face recognition CNNs

Improved performance through active learning triggers

Demonstrated self-awareness mechanism enhances reliability

Abstract

Reflection on one's thought process and making corrections to it if there exists dissatisfaction in its performance is, perhaps, one of the essential traits of intelligence. However, such high-level abstract concepts mandatory for Artificial General Intelligence can be modelled even at the low level of narrow Machine Learning algorithms. Here, we present the self-awareness mechanism emulation in the form of a supervising artificial neural network (ANN) observing patterns in activations of another underlying ANN in a search for indications of the high uncertainty of the underlying ANN and, therefore, the trustworthiness of its predictions. The underlying ANN is a convolutional neural network (CNN) ensemble employed for face recognition and facial expression tasks. The self-awareness ANN has a memory region where its past performance information is stored, and its learnable parameters are adjusted during the training to optimize the performance. The trustworthiness verdict triggers the active learning mode, giving elements of agency to the machine learning algorithm that asks for human help in high uncertainty and confusion conditions.