Often machine learning engines are designed to require little human input. However, while machines are fast, scalable, and reliable, selectively leveraging human input can be an excellent resource to provide continuous feedback and improvement. This is especially important given the inevitable changes in input data and the long tail of edge cases, which are traditionally difficult for machine learning engines.
This talk discusses how we built a product categorization engine at Slice that involves different types of human workers - engineers, analysts, outsourced and crowdsourced workers - to allow for continuous improvement with limited resources.
Video Recording:
https://youtu.be/tOsxjnZu9tM?list=PLNVIqXmk6x8yxm3uM_Mw062imX76q_t2s
Unfortunately, this video has noises and intruptions.