Arijit K

@rijitK

Data management for emerging problems in large networks. Assistant Professor @ NTU, Singapore. Big-graphs, Big-data, Graph-systems.

Vrijeme pridruživanja: svibanj 2012.

Tweetovi

Blokirali ste korisnika/cu @rijitK

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @rijitK

  1. Prikvačeni tweet
    26. sij
    Poništi
  2. proslijedio/la je Tweet
    2. velj

    "Machine Learning doesn’t have to be a black box anymore. What use is a good model if we cannot explain the results to others. Interpretability is as important as creating a model." A neat kernel on "Intrepreting Machine Learning models" by

    Poništi
  3. proslijedio/la je Tweet
    2. velj

    As you prepare your CVPR rebuttal, consider this quote from Aronszajn’s preface to ‘Theory of Reproducing Kernels’ 1948 - “Due to wartime conditions we were not able ... to take into account all the earlier investigations...related to our work” Now that is a rebuttal!

    Poništi
  4. proslijedio/la je Tweet

    So an Indian heads Microsoft, heads Google, heads Adobe and now heads IBM. Such a nice feeling.

    Poništi
  5. proslijedio/la je Tweet
    30. sij

    Jack Ma, Alibaba founder and China's richest man, has donated 100 million yuan ($14.4 million) through his foundation to help find a vaccine for the Wuhan coronavirus.

    Poništi
  6. proslijedio/la je Tweet
    25. sij

    The workshops list is finally up: , w/ 10 workshops spanning HILDA and graphs, to end-to-end ML data mgmt. and db war stories. Thanks to everyone who submitted proposals! Cc:

    Poništi
  7. proslijedio/la je Tweet
    16. sij

    5th for Graphs (DL4G) workshop, co-located at WEBCONF 2020. You are invited to submit your relevant research results and participate to this event. See the exciting (and growing) keynote speakers list:

    Poništi
  8. 11. sij

    This 2020 paper is based on my undergraduate student Xi Tong Lee's final year project (FYP). Super proud of our hard working and motivated students.

    Prikaži ovu nit
    Poništi
  9. 11. sij

    We discuss their similarities and differences with social networks and the Web, draw interesting conclusions, and highlight important, future research directions.

    Prikaži ovu nit
    Poništi
  10. 11. sij

    Each interaction network provides us with a different perspective on the Ethereum blockchain, and our analyses on the networks reveal new insights by combining information from the four networks. We perform an in-depth study of these networks based on several graph properties.

    Prikaži ovu nit
    Poništi
  11. 11. sij

    Ethereum blockchain network is cohabited by both human users and autonomous agents (smart contracts). We looked into all interactions: user-to-user, user-to-contract, contract-to-user, and contract-to-contract.

    Prikaži ovu nit
    Poništi
  12. 11. sij

    Our paper on Ethereum Blockchain network mining is accepted as full research paper in Web Conference'20 (formerly ) : "Measurements, Analyses, & Insights on the Entire Ethereum Blockchain Network" -Xi Tong Lee, Arijit Khan, Sourav Sen Gupta, Yu Hann Ong, & Xuan Liu

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    8. sij

    If 1024 fair coins are each tossed 10 times, chances are good (> 63%) that at least one will come up heads 10 times in a row; and that coin will be proud to explain how its skill, faith, guts & determination made its achievement possible, and how that combo can work for you too.

    Prikaži ovu nit
    Poništi
  14. 24. pro 2019.
    Poništi
  15. proslijedio/la je Tweet
    22. pro 2019.

    If you are on the academic market or planning for a future academic career, consider casting a wide net, & look at places that may not be your obvious “top N.” You may be pleasantly surprised. My thoughts on how rank doesn’t matter as much as people think.

    Poništi
  16. proslijedio/la je Tweet
    18. pro 2019.
    Poništi
  17. 14. pro 2019.

    My post-doc, Dr. Tianxing Wu () is joining Southeast University as an assistant Professor. Congratulations, Tianxing!

    Poništi
  18. 26. stu 2019.
    Poništi
  19. proslijedio/la je Tweet

    Much of what’s being sold as "AI" today is snake oil. It does not and cannot work. In a talk at MIT yesterday, I described why this happening, how we can recognize flawed AI claims, and push back. Here are my annotated slides:

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    Odgovor korisniku/ci

    I am currently offering a course on ML interpretability. It pretty much captures a lot of important references (sub topic wise) on ML interpretability:

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·