Constructivist Design for Interactive Machine Learning

@article{Sarkar2016ConstructivistDF,
  title={Constructivist Design for Interactive Machine Learning},
  author={Advait Sarkar},
  journal={Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems},
  year={2016}
}
  • Advait Sarkar
  • Published 7 May 2016
  • Computer Science
  • Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems
Interactive machine learning systems allow end-users, often non-experts, to build and apply statistical models for their own uses. Constructivism is the view that learning occurs when ideas and experiences interact. I argue that the objectives of interactive machine learning can be interpreted as constructivist. By so characterising them, I show how constructivist learning environments pose critical questions for the design of interactive machine learning systems. 
View on ACM
cl.cam.ac.uk
12 Citations
Highly Influential Citations
1
Background Citations
8
Methods Citations
1

12 Citations

Citation Type

Citation Type

Interactive Machine Learning Heuristics
TLDR
Ten heuristics have been developed by distilling design principles from interactive machine learning literature by adapting the heuristic evaluation method for end-user experiences in the context of interaction with and understanding by end-users.
Interactive machine teaching: a human-centered approach to building machine-learned models
TLDR
It is argued that IMT processes that enable people to leverage intrinsic human capabilities and have a variety of benefits, including making machine learning methods accessible to subject-matter experts and the creation of semantic and debuggable machine learning (ML) models.
Towards an integrative Theoretical Framework of Interactive Machine Learning Systems
TLDR
The main contribution of this paper is organising and structuring the body of knowledge in IML for the advancement of the field and suggesting three opportunities for future IML research.
The Impact of Visual Representations in a Machine Teaching Interaction
TLDR
This paper presents a machine-teaching demo that can be run with a data clustering component that visualizes results and error rate performance of the model, and aims to understand how a teacher can be influenced by how the model evolves and performs while training it.
Applying Radical Constructivism to Machine Learning: A Pilot Study in Assistive Robotics
TLDR
This article matches machine learning and interactive machine learning with radical constructivism (RC) to build a tentative radical constructivist framework for iML.
Human-In-The-Loop Machine Learning with Intelligent Multimodal Interfaces
TLDR
It is argued that intelligent multimodal interfaces add an important dimension for advancing the cause of human-in-the-loop machine learning (HITL-ML) and that implicit learning of system parameters and labelling of user cognitive states is an effective and often overlooked dimension of HITL- ML.
How to Support Users in Understanding Intelligent Systems? An Analysis and Conceptual Framework of User Questions Considering User Mindsets, Involvement and Knowledge Outcomes
TLDR
This work reviews the literature in HCI through the lens of implied user questions to synthesise a conceptual framework integrating user mindsets, user involvement, and knowledge outcomes to reveal, differentiate and classify current notions in prior work, which aims to resolve conceptual ambiguity in the field.
Design fictions for learning: A method for supporting students in reflecting on technology in Human-Computer Interaction courses
CODA: Constructivism Learning for Instance-Dependent Dropout Architecture Construction
TLDR
This work proposes Constructivism learning for instance-dependent Dropout Architecture (CODA), which is inspired from a philosophical theory, constructivism learning, and designed a better drop out technique, Uniform Process Mixture Models, using a Bayesian nonparametric method Uniform process.
Collaborative Learning Supported with Mediawiki Platform in Technical University Environment
TLDR
This paper proposes collaborative learning for students of a technical university as part of courses on “Computer criminality”, and prepares a base platform, MediaWiki, to support the collaborative approach.
...
1
2
...

References

SHOWING 1-10 OF 41 REFERENCES
Principles of Explanatory Debugging to Personalize Interactive Machine Learning
TLDR
An empirical evaluation shows that Explanatory Debugging increased participants' understanding of the learning system by 52% and allowed participants to correct its mistakes up to twice as efficiently as participants using a traditional learning system.
Interactive visual machine learning in spreadsheets
TLDR
Through a study investigating users' learning barriers while building models using BrainCel, it is found that this approach successfully complements the Teach and Try system to facilitate more complex modelling activities.
Interacting with an inferred world: the challenge of machine learning for humane computer interaction
  • A. Blackwell
  • Computer Science
    Aarhus Conference on Critical Alternatives
  • 2015
TLDR
The way in which this new generation of technology raises fresh challenges for the critical evaluation of interactive systems is explored and some proposed measures for the design of inference-based systems that are more open to humane design and use are proposed.
Interactive machine learning
TLDR
An interactive machine-learning (IML) model that allows users to train, classify/view and correct the classifications and the Crayons tool embodies the notions of interactive machine learning is proposed.
Teach and try: A simple interaction technique for exploratory data modelling by end users
TLDR
A spreadsheet-based interaction technique that can be used to build and apply sophisticated statistical models such as neural networks, decision trees, support vector machines and linear regression is described.
Confidence, command, complexity: metamodels for structured interaction with machine intelligence
TLDR
A speculative discussion of a potential solution: metamodels of machine cognition, where the notion of "correctness" for these programs is now unknown or ill-defined.
Learning Syntax as Notational Expertise when using DrawBridge
TLDR
This research investigates text syntax use as a specific notational competence, and evaluates the use of DrawBridge to scaffold text syntax acquisition.
Constructivist Learning Environments: Case Studies in Instructional Design
Inhoudsopgave : Foreword : minds in the 'hood / David N. Perkins -- Introduction : what is a constructivist learning environment? / Brent G. Wilson -- Seven goals for the design of constructivist…
Activity theory as a framework for designing constructivist learning environments
TLDR
This paper argues that activity theory provides an appropriate framework for analyzing needs, tasks, and outcomes for designing constructivist learning environments (CLEs) and describes a process for using activity theory as a framework for describing the components of an activity system that can be modeled in CLEs.
Why Minimal Guidance During Instruction Does Not Work: An Analysis of the Failure of Constructivist, Discovery, Problem-Based, Experiential, and Inquiry-Based Teaching
Evidence for the superiority of guided instruction is explained in the context of our knowledge of human cognitive architecture, expert–novice differences, and cognitive load. Although unguided or…
...
1
2
3
4
5
...