Interactive machine learning

By Jerry Alan Fails, D. Olsen. 2003

501 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

In Signal Processing

Citations in the corpus

Rewriting a Deep Generative Model (2020, background): “Interactive machine learning systems aim to improve training through human interaction in labeling [15,22,68], or by allowing a user to to aid in the model optimization process via interactive feature selection [19,27,64,50] or model and hyperparameter selection [39,61,37].”
Interscript: A dataset for interactive learning of scripts through error feedback (2021, background): “There are various modes of interaction (through labels (Raghavan 2006; Fails and Olsen 2003), utterance (Radlinski et al. 2019), imitation (Brantley, Sharaf, and Daum’e 2020), and language (Elgohary, Awadallah et al. 2020)).”
Investigating statistical machine learning as a tool for software development (2008, methodology): “For example, Fails and Olsen developed Crayons, a tool for creating camera-based systems using pixel-level classiﬁers [4, 5].”
Artificial Intelligence and Management: The Automation–Augmentation Paradox (2020, background): “The experts ’ revision of the learned knowledge is therefore an important part of the augmented learning process (Fails & Olsen, 2003).”
Principles of Explanatory Debugging to Personalize Interactive Machine Learning (2015, background): “…build better mental models, and if so, whether these mental models helped users more efﬁciently personalize their learning system’s behavior. in a paper describing how an iterative train-feedback-correct cycle allowed users to quickly correct the mistakes made by an image segmentation system [11].”
Creative Writing with a Machine in the Loop: Case Studies on Slogans and Stories (2018, background): “1In contrast, human-in-the-loop machine learning actively includes humans in the process of training machine learning models by asking humans to provide feedback such as labeling diffcult examples or suggesting new features [4, 6, 9, 20].”
Interactive Machine Learning via a GPU-accelerated Toolkit (2017, background): “In the context of supervised learning, Fail and Olsen [15] describes partially-supervised learning with a user supplying some (sparse) labelled data to help an ML algorithm label the rest.”
Visual Interaction with Deep Learning Models through Collaborative Semantic Inference (2019, background): “While some guidelines have been developed for interaction design for machine learning [2,25,75,86], they focus on designing machine learning methods where the model performs complementary tasks to the user, or where the user interacts with black-box models.”
Interpretation and trust: designing model-driven visualizations for text analysis (2012, unknown): “[1, 20].”
Teachable Machine: Approachable Web-Based Tool for Exploring Machine Learning Classification (2020, methodology): “For example, Crayon is an IML system for image classiﬁcation [13].”
ModelTracker: Redesigning Performance Analysis Tools for Machine Learning (2015, background): “A similar strategy is direct evaluation , where users provide new data to the model to examine its predictions in real time (e.g., [9,10,21]).”
Interacting meaningfully with machine learning systems: Three experiments (2009, methodology): “The overall premise we explore is that, if the machine learning system could explain its reasoning more fully to the user, perhaps the user would, in return, specify why the prediction was wrong and provide other, rich forms of feedback that could improve the accuracy of machine learning.”
Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “feedback in object recognition [107], or even to alter correctly identified instances where the interpretation is not in”