Kian Katanforoosh

@kiankatan

Founder & CEO , Founding Member , Co-Creator of the Deep Learning Specialization , Lecturer of Computer Science

California, USA
cs230.stanford.edu
Vrijeme pridruživanja: srpanj 2013.
21 fotografija ili videozapis Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @kiankatan

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

  1. Prikvačeni tweet
    14. kol 2019.

    Releasing a new AI Note: Parameter optimization in neural networks. Play with three interactive visualizations and develop your intuition for optimizing model parameters.

    7 replies 174 proslijeđena tweeta 584 korisnika označavaju da im se sviđa
    Poništi
  2. 13. sij

    +1

    I've been at this startup for less than a month and I've been exposed to so many problems I didn't even know existed. I'm of the increasing belief that everyone should try a startup early in their career, e.g. within the first 3 years/before settling into complacency.
    7 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    13. sij

    Monday Quiz: A 64 by 64 RGB image is passed as a valid input to a 2D convolution layer which has twenty filters with (height, width) = (2, 2) and a stride of (1, 1). How many parameters (weights and biases) does the convolutional layer have?

    8 replies 1 proslijeđeni tweet 23 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. 11. sij

    Noting that.. the US gov just released a rule controlling the export of AI software automating the analysis of geospatial imagery with CNNs. Export licenses are required for all foreign nationals, except Canadians, whether they are in the US or abroad.

    3 proslijeđena tweeta 15 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    9. sij

    I love learning by visualization: it is fun and efficient. This is one of my favorite blog posts from about .

    1 reply 22 proslijeđena tweeta 50 korisnika označava da im se sviđa
    Poništi
  6. 9. sij

    Our AI Career Pathways report is up: Learn about: - The types of AI organizations - The most common tasks done by AI teams - How these tasks are typically split between different roles - The skills recruiters look for

    21 proslijeđeni tweet 94 korisnika označavaju da im se sviđa
    Poništi
  7. 9. sij

    Agreed

    On misallocated rewards in universities:
    3 proslijeđena tweeta 13 korisnika označava da im se sviđa
    Poništi
  8. 17. pro 2019.

    Companies everywhere are building AI teams, but it’s still unclear what aspiring MLEs should focus on when applying for ML jobs. We hope this report can help you navigate your career and prioritize your learnings. Download it here:

    You've spent hours studying AI and building projects. What's the next step? This report from , a company, walks you through the different AI career tracks and the skills recruiters are looking for. Download the report:
    3 proslijeđena tweeta 30 korisnika označava da im se sviđa
    Poništi
  9. 17. pro 2019.

    Our newest Specialization is live on ! The two first courses focus on browser-based and device-based models in Tensorflow.

    Courses 1 & 2 of ‘s newest Specialization is now available on ! Training a model is only one step in building a working AI system. These courses teach you how to navigate some key deployment scenarios. Enroll here:
    9 proslijeđenih tweetova 54 korisnika označavaju da im se sviđa
    Poništi
  10. 20. stu 2019.

    Iran’s protests and internet shut down (for >3 days) led to TOEFL/GRE exam cancellations. Bright students face difficulties meeting universities’ application deadlines. If you’re a university admin, please consider (reasonably) relaxing deadlines for affected applicants. Thanks!!

    1 reply 14 proslijeđenih tweetova 66 korisnika označava da im se sviđa
    Poništi
  11. 3. stu 2019.

    L’éducation ne peut attendre آموزش نمی تواند صبر کند!

    How do you say in your language? Please RT & comment with reply with your answer (and name of the language) to let us know! Wishing you all a nice weekend! pic:
    2 proslijeđena tweeta 34 korisnika označavaju da im se sviđa
    Poništi
  12. 22. lis 2019.

    Great blog post on the progress being made to achieve a good cost:value ratio for intelligent robots. is a great friend and former student from whom I learn a lot.

    I wrote a blog post about how we can build increasingly intelligent robots & deploy them in the real world, outside of factories. It cites a bunch of awesome research from a lot of really smart friends/colleagues! Part 1 Part 2
    Prikaži ovu nit
    1 proslijeđeni tweet 7 korisnika označava da im se sviđa
    Poništi
  13. 17. lis 2019.

    I'm honored that this group is helping learners access CS230 summary notes in Japanese! High-tech education needs to be accessible to anyone rather than restricted to a few hubs or languages. Kudos to my friend and former TA for writing these clean notes.

    A team has been translating material for Stanford's CS 230 Deep Learning course from English into Japanese. We're excited to share our work and hope that it'll be useful for Japanese speakers studying ML/DL. 深層学習のチートシートは日本語で利用可能になりました。
    Prikaži ovu nit
    8 proslijeđenih tweetova 42 korisnika označavaju da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    17. lis 2019.

    Over the last few weeks I've been reading The Batch, a new newsletter from . Lots of interesting articles, including one this week on the relative popularity of PyTorch and TensorFlow in research/industry.

    0:05
    In this week's Batch, we've got TensorFlow vs. PyTorch, autonomous drone races, and NLP for rare languages. Read this week's issue:
    3 proslijeđena tweeta 23 korisnika označavaju da im se sviđa
    Poništi
  15. 3. lis 2019.

    Will save *thousands of hours. :p Thank you !

    Tweet je nedostupan.
    1 reply 10 proslijeđenih tweetova 36 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    5. ruj 2019.

    [1/2] Our lab has 3 papers accepted to NeurIPS 2019: 1. HYPE: Human Eye Perceptual Evaluation of Generative Models. Zhou and Gordon et al. (Oral) 2. SOCIAL-BIGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks. Kosaraju et al.

    7 proslijeđenih tweetova 65 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    1. ruj 2019.

    brings you this fascinating video compilation of the conference that featured the Keynote speakers . You can not lose this!

    3 proslijeđena tweeta 9 korisnika označava da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    27. kol 2019.

    New AI Notes tutorial! The optimization algorithm that you choose is important to minimizing your loss function. But how do different optimizers behave? Play with the interactive visualizations in our tutorial to find out:

    1 reply 150 proslijeđenih tweetova 454 korisnika označavaju da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    12. kol 2019.

    Check out our new blog post on our paper! A ~10min story on how to correctly debug your ML systems, with the help of our Errudite tool. Joint work with , and ; Posted on the blog.

    9 proslijeđenih tweetova 82 korisnika označavaju da im se sviđa
    Poništi
  20. 13. kol 2019.

    We’re starting The Batch, a weekly newsletter to help you follow valuable news in AI research and applications.

    7 proslijeđenih tweetova 48 korisnika označava da im se sviđa
    Poništi

@kiankatan još nije objavio nijedan Tweet.

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:

    ·