Corpus ID: 55428044

Machine learning as a design material: a curated collection of exemplars for visual interaction

  title={Machine learning as a design material: a curated collection of exemplars for visual interaction},
  author={Danwei Tran Luciani and Martin Lindvall and Jonas L{\"o}wgren},
Although machine learning is not a new phenomenon, it has truly entered the spotlight in recent years. With growing expectations, we see a shift in focus from performance tuning to awareness of meaningful interaction and purpose. Interaction design and UX research is currently in a position to provide important and necessary knowledge contributions to the development of machine learning systems. Machine learning can be viewed as a design material that is arguably more unpredictable, emergent… Expand
Eliciting New Perspectives in RtD Studies through Annotated Portfolios: A Case Study of Robotic Artefacts
It is suggested that annotated portfolios – when performed by external experts – allow design researchers to obtain a form of creative and generative peer critique in research-through-design (RtD) studies through annotatedfolios. Expand
Designing fine-grained interactions for automation in air traffic control
This work designs a concept and develops an interactive lo-fi prototype of an assisted sketching system to enable air traffic controllers to interact with automation in a fine-grained manner and to externalize mental images. Expand
Designing for sketching to support concept exploration
Sketching is a way of exploring early concepts through the act of externalization in a suitable material with the aid of a suitable tool. One could use paper and sketch with a pencil or go digital ...
Designerly Ways of Knowing in HRI: Broadening the Scope of Design-oriented HRI Through the Concept of Intermediate-level Knowledge
A critical analysis of current HRI design literature identifies a lack of work dedicated to understanding the conceptual implications of robotic artifacts, which are implicit carriers of crucial HRI knowledge that can challenge established assumptions about how a robot should look, act, and be like. Expand


UX Design Innovation: Challenges for Working with Machine Learning as a Design Material
A survey of current UX practitioners with regards to how new ML services are envisioned and developed in UX practice and a review of related literature presents a series of challenges for UX and interaction design research and education. Expand
Interaction criticism: An introduction to the practice
A synthesis of practices of criticism derived from analytic philosophy of aesthetics and critical theory is offered, including the introduction of five core claims from this literature and the outline of four perspectives that constitute a big-picture view of interaction criticism. Expand
What should we expect from research through design?
It is suggested that the design research community should be wary of impulses towards convergence and standardisation, and instead take pride in its aptitude for exploring and speculating, particularising and diversifying, and - especially - its ability to manifest the results in the form of new, conceptually rich artefacts. Expand
Annotated portfolios and other forms of intermediate-level knowledge
The notion of annotated portfolios as a way to communicate design research is proposed to provide an alternative to accounts that suggest for design to become productive as research, it should engage in some sort of theory formation. Expand
The Role of Design Artifacts in Design Theory Construction
It is identified that extensible, systemic approaches to research through design are the most promising ones for developing design theory, and illustrated with examples. Expand
An analysis and critique of Research through Design: towards a formalization of a research approach
A critique of current RtD practices within the HCI research and interaction design communities is performed, showing possible directions for further developments and refinements of the approach. Expand
Digital design materials are temporal as much as they are spatial, which means that specific concepts are needed for understanding the use experiences of digital artifacts and the aesthetics ofExpand
Intelligence on tap
Interaction designers need to consider AI as a new design material, with its own unique opportunities and limitations, in the future. Expand
A Neural Representation of Sketch Drawings
We present sketch-rnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects. The model is trained on thousands of crude human-drawn images representing hundredsExpand
The Importance of UX for Machine Teaching