Podcast: Play in new window | Download
Machine learning models can be built by plotting points in space and optimizing a function based off of those points.
For example, I can plot every person in the United States in a 3 dimensional space: age, geographic location, and yearly salary. Then I can draw a function that minimizes the distance between my function and each of those data points. Once I define that function, you can give me your age and a geographic location, and I can predict your salary.
Plotting these points in space is called embedding. By embedding a rich data set, and then experimenting with different functions, we can build a model that makes predictions based on those data sets. Yufeng Guo is a developer advocate at Google working on CloudML. In this show, we described two separate examples for preparing data, embedding the data points, and iterating on the function in order to train the model.
In a future episode, Yufeng will discuss CloudML and more advanced concepts of machine learning.
Transcript provided by We Edit Podcasts. Software Engineering Daily listeners can go to weeditpodcasts.com/sed to get 20% off the first two months of audio editing and transcription services. Thanks to We Edit Podcasts for partnering with SE Daily. Please click here to view this show’s transcript.
Pingback: Dew Drop - October 18, 2017 (#2584) - Morning Dew()
Machine learning has become synonymous with “Make a dumb but deep network, throw a LOT of data at it and pray it will learn”. Its similar to my learning golf: I throw a lot of money at it, hoping that i will get it one day. Humans don’t need to see 25,000 cats and dogs to start identifying which is a cat and which is a dog. Can networks learn with frugal data or minimal samples? Can we learn a new diagnosis of cancer with only a handful of x-Rays and not 30,000 x-Rays? Then only it can be called intelligence of any use, artificial or otherwise. The AI today is nothing but simple algorithms on steroids. Whats your opinion on this? – Renga
I think machine learning is just teaching computers to improve their systems as they receive more data.
We should simplify it as much as possible so that programmers are not intimidated by it.