Announcing: Slashdot Deals - Explore geek apps, games, gadgets and more. (what is this?)

Thank you!

We are sorry to see you leave - Beta is different and we value the time you took to try it out. Before you decide to go, please take a look at some value-adds for Beta and learn more about it. Thank you for reading Slashdot, and for making the site better!



Research Highlights How AI Sees and How It Knows What It's Looking At

StephenBenoit Training classifiers require "rejectable" samples (130 comments)

The DNN examples were apparently trained to discriminate between a members of a labeled set. This only works when you have already cleaned up the input stream (a priori) and guarantee that the image must be an example of one of the classes.

These classifiers were not trained on samples from outside the target set. This causes a forced choice: given this random dot image, which of the classes have the highest confidence? Iterate until confidence is sufficiently high, and you have a forgery with the same features the classifier is looking for.

For example, the digit training set (0,1,2...9) would need to be augmented with pictures of 'A', 'D', a smiley face, a doodle of a tree, a silhouette of Alfred Hitchcock and some spider webs. The resulting classifier would be more robust. The target classes (0,1,2,...9) would be counterbalanced with a null class (everything else). Looking inside the receptive fields of a robust image classifier is rather satisfying: you will find eigenimages that project back to image structures that are human recognizable, too.

The lesson in training your classifier is to either verify your assumption (all incoming samples must be a member of the chosen classes) or train (expose) your classifier to out-of-class samples.

about a month and a half ago

Gigapixel Tapestries & Gigadecimal Pi

StephenBenoit Duck to avoid Pi in the face (215 comments)

Consulting my Fisher Price Workstation, I have determined that the 3 Billionth digit of Pi is "5".


More or less.

Seriously, the actual value is not the issue. Pi is irrational and the challenge is to encode a very large string of digits without using all previous digits to compute the next few digits.

more than 9 years ago


StephenBenoit hasn't submitted any stories.


Slashdot Login

Need an Account?

Forgot your password?