Sunday, November 10, 2019

AI in the web browser with TensorFlow.js

very informative podcast interview!

Practical AI #61: AI in the browser with Victor Dibia, research engineer at Cloudera’s Fast Forward Labs |> News and podcasts for developers |> Changelog
Benefits of ML in web browser"

"The first would be privacy. Perhaps this is the most compelling and interesting benefit, that I really care about. If you could take a model and you could deploy that in the browser, you could create an environment where the user data actually doesn't get down to any back-end server. I could give some examples of that somewhere down the line, as we continue the conversation.

The second interesting benefit why machine learning might be interesting in the browser has to do with the ease of distribution. A few years ago I had a couple of friends who really wanted to get into machine learning, but they did give up because they spent a couple of days just trying to install TensorFlow. So while over the last two years the user experience has become a lot better, there are still a lot of challenges, especially if you want to get a machine learning model or an application that uses machine learning deployed on an end user system. However, if you go ahead and do that in the browser, this is a much more straightforward and much easier developer and end user experience.

Then finally, the last interesting feature has to do with interactivity and latency. Off the bat, the browsers, the web is designed to be interactive, and it's really valuable for crafting rich interactive experiences. So if there are situations where you have a model and you want to easily tailor that around user data, make changes and personalize that for a user, then the browser is a really excellent environment to interactively do all of that."

No comments: