from Hacker News

NLP Architect by Intel AI Lab

by tsaprailis on 1/10/19, 2:51 PM with 11 comments

  • by jph on 1/10/19, 5:57 PM

    This AI toolkit works on popular Intel CPUs, and is a big step forward for the new Intel Nervana Neural Network Processor (NNP-I) hardware chip akin to a GPU.

    The Intel AI Lab has an introduction to NLP (https://ai.intel.com/deep-learning-foundations-to-enable-nat...) and optimized Tensorflow (https://ai.intel.com/tensorflow/)

    One surprising research result for this NLP is that a simple convolutional architecture outperforms canonical recurrent networks, often. See: CMU lab, Sequence Modeling Benchmarks and Temporal Convolutional Networks (TCN) https://github.com/locuslab/TCN

    If you're interested in Nervana, here are some specifics: the chip is for hardware neural network acceleration, for inference-based workloads. Notable features include fixed-point math, Ice Lake cores, 10-nanometer fabs, on-chip memory management by software directly, and hardware-optimized inter-chip parallelism.

    I've worked for Intel, and I'm stoked to see the AI NLP progress.

  • by continuations on 1/10/19, 9:10 PM

    How does this compare to word2vec or fasttext?
  • by ___cs____ on 1/10/19, 10:54 PM

    Yet another interface on top of Pytorch/TF/Gensim.