News for hackers. Stuff that matters.

A comment on Most companies developing AI capabilities have yet to gain significant benefits. Parent comment

Re:Most companies developing AI capabilities have yet to gai... by cultus on Tuesday October 20, 2020 @12:34PM (#24839392)
Most ML algorithms boil down to linear regression with some loss function. Even deep learning networks are essentially just linear regressions stacked on top of each other, with lower layers being trained on features predicted by higher layers.

I think if neural networks or SVMs are AI, then linear regression is as well. Neural Turing machines and other recent developments I think are closer to the layperson's idea of "AI," though.

[ Parent | on HN ]
Re:Most companies developing AI capabilities have yet to gai... by bumby on Tuesday October 20, 2020 @02:51PM (#24841003)
>Most ML algorithms boil down to linear regression

I think (particularly with DL) it would probably be more accurate to claim it boils down to nonlinear logistic regression rather than linear regression. To your point, both are relatively old techniques

[ Parent | on HN ]
Re:Most companies developing AI capabilities have yet to gai... by cultus on Tuesday October 20, 2020 @07:29PM (#24843351)
Nonlinear regression is still linear regression with transformed features. Kernel regression, for example, just uses features generated from the data using a supplied kernel function/covariance function. DL just allows the features to be trained.
[ Parent | on HN ]