• Explore
    • Contact Us
  • Faculty
  • Research
    • Research Areas
    • Research Centers
  • Graduate Degrees
    • Computer Science Programs
    • Current Graduate Students
  • Undergraduate Degrees
  • News & Events
    • News
    • Seminar Series
    • Distinguished Lecture Series
    • Research Showcase
  • Apply Now
    • Undergraduate Admissions
    • Graduate Admissions
    • Faculty Candidates

Husky or wolf? Using a black box learning model to avoid adoption errors

August 24, 2017

Say you want to adopt a dog, from a picture, and you task your machine learning system to classify the image as either a husky, which would be safe to adopt, or a wolf, which probably is not a good idea. Can you get that photograph classified with certainty? “Because researchers don’t have insights into what is going on they can easily be misled,” said Sameer Singh, assistant professor in the UCI Department of Computer Science. “Classification is core to machine learning,” said Singh, describing ‘black box’ machine learning predictions at the Association for Computing Machinery (ACM) July 12 meeting at the Cove. Machine learning is pervasive in our lives—from email to games. “It’s in our phones,” said Singh, a machine learning and natural language processing expert. “It is in our houses. It is basically everywhere.”One of his students created a wolf/dog classifier in a few hours that seemed to work—at first.

Read the full story on the UCI Applied Innovation website.

« Dutt, Levorato awarded NSF grant for healthcare IoT research
ACM SIGMM Records: “An interview with Prof. Ramesh Jain” »

Latest news

  • Identifying the Building Blocks of Attention in Deep Learning March 21, 2023
  • Faculty Spotlight: Jennifer Wong-Ma and the Power of Community March 20, 2023
  • Computer Science Ph.D. Candidate Takami Sato Named Public Impact Fellow March 14, 2023
  • Irani Builds New Collaborations as Associate Director of the Simons Institute March 6, 2023
  • UC Irvine Partners With Linux Foundation to Welcome New Open Source Projects from Peraton Labs to Scale 5G Security March 3, 2023
  • © 2023 UC Regents
  • Feedback
  • Privacy Policy