Hacker Blogs
Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #3385

N

nervanasys.com

Company blog · nervanasys.comaihardware

nervanasys.com is the company blog at nervanasys.com, writing about ai and hardware. Since 2014, 23 different Hacker News readers have linked it 25 times, most often “Deep Reinforcement Learning Explained”. No feed was found, so read it on the site itself.

No feed foundOpen in the Web Archive Try the live site
25mentions?
23HN people?
2014–2017first – last linked?
Links on Hacker News per year · peak 20 in 2016

Too few sampled comments (11) to say how often HN recommends it.?

Why HN links it

HN readers link Nervana Systems' blog for its deep reinforcement learning explainers, a starting point for recent methods, and posts on Winograd optimisations in its neon framework.

Summarised by Claude from a sample of 11 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Most-linked posts?

  1. Deep Reinforcement Learning Explained
    4 people · 4 mentions · first linked 2016-01-01
  2. Tech preview of Nervana Graph – optimizing Deep Learning on different platforms
    3 people · 3 mentions · first linked 2016-11-18
  3. /demystifying-deep-reinforcement-learning/
    2 people · 2 mentions · first linked 2016-06-27
  4. /nervana-engine-delivers-deep-learning-at-ludicrous-speed/
    2 people · 2 mentions · first linked 2016-08-10
  5. Job openings at Nervana (hardware for machine learning)
    2 people · 2 mentions · first linked 2014-04-24

What Hacker News says?

  1. Drdrdrq · 2017-01-04Recommends
    ...later found this nice explanation of RL concepts if it helps someone: https://www.nervanasys.com/demystifying-deep-reinforcement-l...

    Comment linking /demystifying-deep-reinforcement-learning/

    on “TensorKart: self-driving MarioKart with TensorFlow”
  2. ktRolster · 2016-04-17

    Submitted Deep Reinforcement Learning Explained as a story · 121 points

    HN discussion
  3. binarybana · 2017-06-01
    Intel | Compiler/Software Engineers | San Diego, Santa Clara, San Francisco, Folsom OR | REMOTE/VISA for strong candidates. Full-time. Currently in deep learning, if one wants to implement a low level kernel (LSTM, batch-norm etc), you're either going to be writing CUDA or device specific low level code. Join us as we grow the Intel Nervana Graph project ( https://www.nervanasys.com/intel-nervana-graph-preview-relea…

    Comment linking /intel-nervana-graph-preview-release/

    on “Ask HN: Who is hiring? (June 2017)”
  4. tim_sw · 2016-06-30

    Submitted The inside scoop on Nervana’s Winograd kernels as a story · 22 points

    HN discussion
  5. kmike84 · 2016-06-27Recommends
    If one doesn't want to dive deep in RL, and just want to start with recent methods then https://www.nervanasys.com/demystifying-deep-reinforcement-l... blog posts provide a very good starting point.

    Comment linking /demystifying-deep-reinforcement-learning/

    on “How to Start Learning Deep Learning”
  6. hurrycane · 2016-08-09

    Submitted Intel buys Deep Learning chip maker Nervana as a story · 21 points

    HN discussion
  7. emcq · 2015-12-11
    To be fair, the goal of those new computing architectures is not to advance algorithms. That at best is a side benefit. Those algorithmic performance improvements seen in DNN have come from improved datasets and training. Numenta and IBM arent focusing on training AFAIK. Google's Quantum Annealing [0] is the only hardware I'm aware of focused on training, although there are rumors Nervana Systems may produce somethi…

    Comment linking /about/

    on “Facebook to open-source AI hardware design”
  8. smhx · 2016-03-04

    Submitted “Not so fast, FFT”: Winograd as a story · 18 points

    HN discussion
  9. dharma1 · 2016-10-14Recommends
    Check out the Winograd optimisations used in Nervana's neon - very fast https://www.nervanasys.com/winograd-2/

    Comment linking /winograd-2/

    on “Keras.js – Run trained Keras models in your browser”
  10. jennifermyers · 2016-11-20

    Submitted Tech preview of Nervana Graph – optimizing Deep Learning on different platforms as a story · 6 points

    HN discussion
  11. pjscott · 2016-08-10
    > simplified memory architecture (no cache?) No automatic cache hierarchy. There is local memory, which you manage explicitly. More info here: https://www.nervanasys.com/nervana-engine-delivers-deep-lear...

    Comment linking /nervana-engine-delivers-deep-learning-at-ludicrous-speed/

    on “Intel to buy deep-learning startup Nervana Systems for at least $350M”
  12. mrry · 2016-11-18

    Submitted Preview Release: Intel Nervana Graph as a story · 4 points

    HN discussion
  13. ssvss · 2016-11-25
    They aren't rebranded x86 cores, This is from Nervana systems which was acquired by Intel few months back. More details about Nervana architecture. https://www.nervanasys.com/nervana-engine-delivers-deep-lear...

    Comment linking /nervana-engine-delivers-deep-learning-at-ludicrous-speed/

    on “Intel Unveils Strategy for State-Of-the-Art Artificial Intelligence”
  14. bottombutton · 2016-03-22

    Submitted Demystifying Deep Reinforcement Learning as a story · 4 points

    HN discussion
  15. Smerity · 2016-07-21
    Some people are noting that TensorFlow evens the playing field, allowing other companies to poach Google's employees. Whilst that is true to some light degree, there are amazingly large caveats - Google still have the major advantage when it comes to poaching. The other important note is that open sourcing TensorFlow is likely more important for attracting recent graduates in machine learning than it is for attracti…

    Comment linking /

    on “Google Sprints Ahead in AI Building Blocks, Leaving Rivals Wary”
  16. jessiclr · 2016-07-18

    Submitted Nervana releases 'deep learning course' for neon and AI cloud as a story · 3 points

    HN discussion
  17. betelgeusem · 2016-05-05
    Nervana Systems http://www.nervanasys.com/products/ is using Titan X's for their cloud.

    Comment linking /products/

    on “Train Your TensorFlow Models on Rescale”
  18. DiabloD3 · 2016-01-07

    Submitted Demystifying Deep Reinforcement Learning as a story · 3 points

    HN discussion
  19. rhb · 2014-04-30
    Not a general purpose CPU/GPU, but related: http://www.nervanasys.com/ Founded by experts in machine learning, neuroscience, processor architecture, and chip design, Nervana Systems is bringing unprecedented scale and simplicity to the application of brain-inspired algorithms. Deep learning has emerged as the leading strategy for making sense of a wide variety of data but is very computationally intensive. We are de…

    Comment linking /

    on “Ask HN: Are there new hardware startups working on new CPUs or GPUs?”
  20. jonbaer · 2016-01-01

    Submitted Demystifying Deep Reinforcement Learning as a story · 3 points

    HN discussion
  21. bottombutton · 2016-03-22
    Part two: http://www.nervanasys.com/deep-reinforcement-learning-with-n...

    Comment linking /deep-reinforcement-learning-with-neon/

    on “Demystifying Deep Reinforcement Learning”
  22. dsr12 · 2016-12-18

    Submitted End-to-end speech recognition with neon as a story · 2 points

    HN discussion
  23. jessiclr · 2016-07-01

    Submitted Neon v1.5 just released as a story · 2 points

    HN discussion
  24. nefitty · 2016-03-03

    Submitted Nervana Cloud: Scalable deep learning on demand as a story · 2 points

    HN discussion
  25. etiam · 2014-04-24

    Submitted Job openings at Nervana (hardware for machine learning) as a story · 1 points

    HN discussion

Search all of HN for nervanasys.com

Linked by the same people?