How to Use classifier in a Sentence

classifier

noun

• And some, perhaps, with flaws—which would be clues to the classifier’s knowledge gaps.
  — Paul Voosen, Science | AAAS, 6 July 2017
• The team used those photos and open-source image classifier files from Google to train the model and the custom camera system to sense and record trains passing.
  — Smithsonian Magazine, 5 Sep. 2023
• The chip uses a simple form of machine learning called a naive Bayesian classifier.
  — The Economist, 12 Sep. 2019
• Since such attributes are hard to detect from keywords alone, the app also collects signals from users to train its classifiers.
  — IEEE Spectrum, 1 Feb. 2021
• But since the Rohingya genocide, Facebook has built a hate-speech classifier in Burmese by pouring resources toward the project.
  — Billy Perrigo, Time, 26 Nov. 2019
• The fastText language classifier was used trained on a simplified word list from Wikipedia.
  — Daniel Wolfe, Washington Post, 20 Apr. 2023
• But that’s a lot easier than building a classifier for something like hate speech.
  — Nilay Patel, The Verge, 19 Jan. 2021
• As scammers develop new methods to trick the AI … YouTube engineers will update the classifiers to overcome those tricks.
  — Los Angeles Times, 4 Sep. 2019
• The facts in Li (undisputed by the whistleblower) were that the whistleblower’s submission was rejected by the WBO classifier and was never sent to the field.
  — Dean Zerbe, Forbes, 17 Aug. 2022
• On a landscape-mode display, accuracy of the classifiers was much lower, with a first-guess success rate of only 40.8 percent.
  — Sean Gallagher, Ars Technica, 28 Aug. 2018
• Plus, there’s a good chance that many of the singles putting their Myers-Briggs classifier in their app bios aren’t quite grasping what their personality type even means.
  — Allie Volpe, Washington Post, 15 Aug. 2019
• For example, Meta chose not to build a classifier to detect minors under 13.
  — Jon Brodkin, Ars Technica, 27 Nov. 2023
• What’s new with this type of AI is that, historically, these technologies were classifiers.
  — Todd Moore, Forbes, 17 July 2023
• In one document from May 2020, an employee said a hate speech text classifier that was available wasn’t being used or maintained.
  — NBC News, 18 Nov. 2021
• GANs, then, naturally create classifiers that can be used to tell the difference between real and fake.
  — Nick Thieme, Slate Magazine, 21 July 2017
• But OpenAI warned that its classifier is not very reliable when analyzing texts of less than 1,000 words—so good luck with those phishing emails.
  — Byjeremy Kahn, Fortune, 1 Feb. 2023
• In fact, the problems with Facebook’s ad tool are not mysterious or complicated, and they aren’t buried in layers of machine-learning classifiers or neural nets.
  — Will Oremus, Slate Magazine, 20 Sep. 2017
• In one case, Ouster fed intensity and depth data from a drive around San Francisco into a pixel-level classifier.
  — Timothy B. Lee, Ars Technica, 4 Sep. 2018
• Take one of its most common applications, as an image classifier.
  — Jordana Cepelewicz, WIRED, 10 Feb. 2019
• Of course, these initial examples can’t cover everything a classifier encounters in the wild.
  — Katy Steinmetz, Time, 8 July 2019
• The method works for any classifier — whether it’s designed to categorize text, images or numerical data.
  — Ben Brubaker, Quanta Magazine, 2 Mar. 2023
• This way, the system ended up with different certainty levels on different classifiers.
  — Jacek Krywko, Ars Technica, 16 July 2018
• Before it was shut down, the AI classifier performed particularly poorly for pieces of text under 1,000 characters written in non-English languages.
  — Emily Dreibelbis, PCMAG, 25 July 2023
• And that accuracy is achieved with really simple classifiers.
  — Quanta Magazine, 10 Mar. 2023
• Finally, the image classifier itself was tuned to improve its performance.
  — Peter Bright, Ars Technica, 27 June 2018
• So Adaptive and Microsoft are continuing to improve the classifier.
  — Katie Palmer, STAT, 9 Mar. 2021
• Given a single facial image, a classifier could correctly distinguish between gay and heterosexual men in 81% of cases, and in 74% of cases for women.
  — John Paul Brammer, NBC News, 13 Sep. 2017
• Blakeley Payne Another activity that explains algorithmic bias is the training of a cat-dog classifier.
  — Jenny Anderson, Quartz, 4 Sep. 2019
• So those two factors — the lack of ambiguity and data availability — allow classifiers to perform really well.
  — Quanta Magazine, 10 Mar. 2023
• The best performing aggregate score classifier performed slightly better—coming in at 0.65.
  — IEEE Spectrum, 17 May 2023

Last Updated: 27 Jun 2024