Sandeep Sharma

@sandeepkaushik

Passionate about Customer & Marketing Analytics, Healthcare and Machine Learning.

Vrijeme pridruživanja: travanj 2008.

Tweetovi

Blokirali ste korisnika/cu @sandeepkaushik

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

  1. proslijedio/la je Tweet

    I'm looking forward to seeing AI agents that: - Have a model of the world - Assume others do too - Use some form of language to update models on each side ... As well as many others things you use language for. It doesn't matter if their syntax is terrible.

    Prikaži ovu nit
    Poništi
  2. Tesla potentially opening a whole new ecosystem of solutions to build on its dataset. Any privacy concerns here ?

    Poništi
  3. 30. sij

    Some of the most successful products are highly opinionated and may have been considered unscientific basis available research at the time. Yet they command a large following today. I would like to invite examples of such products... anything but Apple please 🙏

    Poništi
  4. 29. sij

    Keras Tuner optimizes model hyperparameters. A complex element of model training undergoes abstraction. Has wider applicability beyond Keras, TF and Scikit-learn

    Poništi
  5. 28. sij

    Why is this making news? A teaser by Dan Becker. I will talk more in days to come..

    Poništi
  6. 27. sij

    Skydiving .. and then the king of skies pays a visit

    Poništi
  7. 24. sij

    Bunch of great ideas. Very impressed by the responses 👍

    Poništi
  8. proslijedio/la je Tweet
    23. sij

    Google Dataset Search is now officially out of beta. "Dataset Search has indexed almost 25 million of these datasets, giving you a single place to search for datasets & find links to where the data is." Nice work, Natasha Noy and everyone else involved!

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    23. sij

    Hello, world! This is the official account for NumPy, the fundamental package for scientific computing with Python. Follow us for news, info and content related to NumPy!

    Poništi
  10. 20. sij

    Very interested to know more about Sideways and it's role in Deep learning.

    Poništi
  11. 18. sij
    Poništi
  12. proslijedio/la je Tweet
    18. sij

    Book recommendation : Thinking, Fast and Slow; by Daniel Kahneman. For anyone interested in behavioural and decision sciences. It provides detailed & research backed analysis of various decisions, thoughts and situations.

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

    A thread of classifiers learning a decision rule. Dashed line is optimal boundary. Animations with by and . Logistic regression {stats::glm} with each class having normally distributed features. (1/n)

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    17. sij

    The reason why I love GoodRx so much is because it’s the first widespread consumer tool that clearly exposes nonsensical healthcare prices.

    Poništi
  15. proslijedio/la je Tweet
    16. sij
    Odgovor korisnicima i sljedećem broju korisnika:

    Guess question was addressed in pt 5. End to end solutions and pipelined archtectures isn't scalable for use cases in future. We need models to plug in and out much like the microservices world.

    Poništi
  16. proslijedio/la je Tweet
    14. sij

    New in Habitat: Vision-and-Language Navigation. VLN task/dataset (by ) asks an agent to follow human nav-instructions in new buildings. Habitat Port Courtesy: (students at ), w/

    Prikaži ovu nit
    Poništi
  17. 14. sij

    FB's Automatic Speech Recognition is now open-sourced. wav2letter@anywhere - highly efficient, supports RNN and CNNs, aces speech performance benchmarks. Ready to go. Currently trained on English.

    Poništi
  18. proslijedio/la je Tweet
    9. pro 2019.
    Odgovor korisnicima

    #1 Consumption is way over limits. Reduce it in all possible ways. #2 Use recyclable or degradable packaging as much as possible.

    Poništi
  19. proslijedio/la je Tweet
    10. pro 2019.
    Odgovor korisnicima i sljedećem broju korisnika:

    Multiple Unsupervised and RL models are performing better than Supervised learning. Maybe a stretch, but curious if these results could take us to the next stage i.e. form the building blocks of AGI? In the near term, it creates many distillation opportunities.

    Poništi
  20. proslijedio/la je Tweet
    18. pro 2019.
    Odgovor korisniku/ci

    Congratulations and !! This will definitely rank in the top achievements of this century.

    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:

    ·