Excited about synthetic data? Maybe you’ve read my article about how design fits into the machine learning process, and the power of synthetic data. When you don’t have access to a clean public dataset, generating synthetic data can be a powerful way to bootstrap your models. And synthetic data has its advantages. You spend much less time on data cleaning and can reduce bias during data generation by including a balanced number of examples. And Sketch randomly distributes images and text values to avoid bias.
Want to create some synthetic data of your own? This tutorial shows you how to create synthetic data to train a classifier that can answer that age-old question, “what is good design?” by predicting whether a design is good or bad. You can then extend these techniques to any UI component — for example, training a model to classify component types, or classify components by state. …
Today, machine learning (ML) is a component of practically all new software products. For designers there is sometimes a question, “what is the role of design in machine learning?” How can designers engage in the process of creating a machine learning powered product? We’ve been working on Salesforce’s new Einstein Designer tool, which automatically generates design variations to improve UX. While this project was specifically focused on ML for design, what we learned is more broadly applicable. During the Einstein Designer project our team of hybrid designers/developers/data scientists discovered new ways of incorporating design techniques into ML projects.
When you’re working with machine learning, the traditional functions of design — crafting a product vision and communicating with stakeholders — apply, but ML also brings new factors to the table. This article explores how design techniques can be applied in ML development At base, it’s all about data — getting it (a lot of it!), cleaning it, understanding it, and ultimately building software on top of it. The process goes something like…
In the popular imagination, there’s still a wide gulf between machine-generated content and human creativity. But that gulf is narrowing as architects, product designers, filmmakers, and a wide range of other creative professionals use generative design to create and iterate on design possibilities.
UX design is no exception. Over the last year, Salesforce’s Einstein Designer team has been working to create models and algorithms that generate design variations, which human designers can adapt or riff on, speeding the design process and helping designers stretch their creative muscles. …
About
