Ian Goodfellow: Adversarial Machine Learning (ICLR 2019 invited talk)




[ad_1]

Speaker: Ian Goodfellow

Abstract:

Until about 2013, most researchers studying machine learning for artificial intelligence all worked on a common goal: get machine learning to work for AI-scale tasks. Now that supervised learning works, there is a Cambrian explosion of new research directions: making machine learning secure, making machine learning private, getting machine learning to work for new tasks, reducing the dependence on large amounts of labeled data, and so on. In this talk I survey how adversarial techniques in machine learning are involved in several of these new research frontiers.

Presented at ICLR2019

Source


[ad_2]

Comment List

  • Steven Van Vaerenbergh
    December 12, 2020

    amazing !!

  • Steven Van Vaerenbergh
    December 12, 2020

    Thanks Ian for this excellent talk.

  • Steven Van Vaerenbergh
    December 12, 2020

    Can you tell me a latest research direction on Adversarial Attacks amd defense. I am going to pursue my PhD this year and I want conduct research on this topic.

  • Steven Van Vaerenbergh
    December 12, 2020

    There is a glitch at https://youtu.be/sucqskXRkss?t=1739. I don't know if there is a section of the video missing there? If so maybe someone knows of another version of this video somewhere?

  • Steven Van Vaerenbergh
    December 12, 2020

    Amazing

  • Steven Van Vaerenbergh
    December 12, 2020

    OH MY GOODNESS! Exelent talk from may- and still streaming live?!?! Commitment bro!

  • Steven Van Vaerenbergh
    December 12, 2020

    Excellent talk!! Ian is smart but also a good, clear speaker – he uses well-chosen words and timely anecdotes/analogies to clarify truly complicated topics.

Write a comment