On Interactive Machine Learning and the Potential of Cognitive Feedback

Abstract

In order to increase productivity, capability, and data exploitation, numerous defense applications are experiencing an integration of state-of-theart machine learning and AI into their architectures. Especially for defense applications, having a human analyst in the loop is of high interest due to quality control, accountability, and complex subject matter expertise not readily automated or replicated by AI. However, many applications are suffering from a very slow transition. This may be in large part due to lack of trust, usability, and productivity, especially when adapting to unforeseen classes and changes in mission context. Interactive machine learning is a newly emerging field in which machine learning implementations are trained, optimized, evaluated, and exploited through an intuitive humancomputer interface. In this paper, we introduce interactive machine learning and explain its advantages and limitations within the context of defense applications. Furthermore, we address several of the shortcomings of interactive machine learning by discussing how cognitive feed-back may inform features, data, and results in the state of the art. We define the three techniques by which cognitive feedback may be employed: self reporting, implicit cognitive feedback, and modeled cognitive feedback. The advantages and disadvantages of each technique are discussed.DISTRIBUTION STATEMENT A. Approved for public release: distribution unlimited.

RootPainter3D: Interactive‐machine‐learning enables rapid and accurate contouring for radiotherapy

“…54 The benefits of corrective-annotation to routine clinical contouring are clear as correcting inaccurate contours is already essential to optimize treatment planning. 3,4 In addition to being usable by non-experts 55 and providing performance improvements in comparison to fully-automated systems, 56 IML can provide trust and quality control benefits 57 which are of particular interest in a radiotherapy context.…”

Implementing the Dynamic Feedback-Driven Learning Optimization Framework: A Machine Learning Approach to Personalize Educational Pathways

“…ML algorithms provide personalized content and adaptive learning experiences that enable the algorithms to cater to individual learning styles and preferences; these increase student motivation and engagement. ML-driven platforms are interactive and often include game-like elements and instant feedback mechanisms in their learning approach [34]. Such engagement is not superficial but grounded in an individual learner's cognitive alignment of educational content and generates authentic, meaningful pleasure experienced during learning.…”

Leveraging explanations in interactive machine learning: An overview

“…As suggested by Ware et al (2001), this stands in contrast to standard procedures, in which building a model is a fully automated process and domain experts have little control beyond data preparation. Research in IML explores ways to learn and manipulate models through an intuitive human-computer interface (Michael et al, 2020) and encompasses a variety of learning and interaction strategies. Perhaps the most well-known IML framework is active learning (Settles, 2012;Herde et al, 2021), which tackles learning high-performance predictors in settings in which supervision is expensive.…”

“…However stakeholders only participate as passive observers and have no control over the system or its behavior. On the other hand, IML focuses primarily on communication between machines and humans, and it is specifically concerned with eliciting and incorporating human feedback into the training process via intelligent user interfaces (Ware et al, 2001;Fails and Olsen, 2003;Amershi et al, 2014;He et al, 2016;Wang, 2019;Michael et al, 2020). Despite covering a broad range of techniques for in-the-loop interaction between humans and machines, most research in IML does not explicitly consider explanations of ML models.…”