# AI-in-the-Loop -- The impact of HMI in AI-based Application

arXiv: https://arxiv.org/abs/2303.11508 · HTML: https://mlsanity.com/paper/2303.11508/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 10 of 10)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Symbolic Discovery of Optimization Algorithms](https://mlsanity.com/paper/2302.06675/) (2023)
- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [Adversarial Attacks on Deep Neural Networks for Time Series Classification](https://mlsanity.com/paper/1903.07054/) (2019)
- [The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification](https://mlsanity.com/paper/1907.01803/) (2019)
- [Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training by Receptive Field Analysis](https://mlsanity.com/paper/2106.12307/) (2021)

## Built on by (most cited first, 4 of 4)

- [AI-Supported Assessment of Load Safety](https://mlsanity.com/paper/2306.03795/) (2023)
- [AI for non-programmers: Applied AI in the lectures for students without programming skills](https://mlsanity.com/paper/2403.05547/) (2024)
- [Compliance of AI Systems](https://mlsanity.com/paper/2503.05571/) (2025)
- [Architectural Transformations and Emerging Verification Demands in AI-Enabled Cyber-Physical Systems](https://mlsanity.com/paper/2510.00519/) (2025)

## Abstract (arXiv)

Artificial intelligence (AI) and human-machine interaction (HMI) are two keywords that usually do not fit embedded applications. Within the steps needed before applying AI to solve a specific task, HMI is usually missing during the AI architecture design and the training of an AI model. The human-in-the-loop concept is prevalent in all other steps of developing AI, from data analysis via data selection and cleaning to performance evaluation. During AI architecture design, HMI can immediately highlight unproductive layers of the architecture so that lightweight network architecture for embedded applications can be created easily. We show that by using this HMI, users can instantly distinguish which AI architecture should be trained and evaluated first since a high accuracy on the task could be expected. This approach reduces the resources needed for AI development by avoiding training and evaluating AI architectures with unproductive layers and leads to lightweight AI architectures. These resulting lightweight AI architectures will enable HMI while running the AI on an edge device. By enabling HMI during an AI uses inference, we will introduce the AI-in-the-loop concept that combines AI's and humans' strengths. In our AI-in-the-loop approach, the AI remains the working horse and primarily solves the task. If the AI is unsure whether its inference solves the task correctly, it asks the user to use an appropriate HMI. Consequently, AI will become available in many applications soon since HMI will make AI more reliable and explainable.