Log inSign up
Martin Görner
1,291 posts
user avatar
Martin Görner
@martin_gorner
AI/ML engineer. Previously at Google: Product Manager for Keras and TensorFlow and developer advocate on TPUs. Passionate about democratizing Machine Learning.
France
Joined May 2016
6,105
Following
13.4K
Followers

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • user avatar
    Martin Görner
    @martin_gorner
    Dec 5, 2022
    Thought-provocative new paper from @geoffreyhinton: what if we could replace backpropagation with something better?
  • user avatar
    Martin Görner
    @martin_gorner
    Feb 4, 2022
    This is sweet 🥧 ! arxiv.org/abs/2202.01197 Finally a solid way of of teaching a neural network to know what it does not know. (OOD = Out Of Domain, i.e. not one of the classes in the training data.) Congrats @SharonYixuanLin @xuefeng_du @MuCai7
  • user avatar
    Martin Görner
    @martin_gorner
    May 7, 2019
    #io19 I wrote four short deep learning codelabs to get you started with neural networks. With TPUs you can now train and iterate in minutes. That's faster learning for our bio brains too! Head to the #codelabs area at I/O.
    00:00
  • user avatar
    Martin Görner
    @martin_gorner
    Nov 24, 2021
    Self-supervised learning techniques on images are making steady progress. Here are Masked Auto Encoders: arxiv.org/abs/2111.06377 I's impressive how much the neural network can reconstruct.
  • user avatar
    Martin Görner
    @martin_gorner
    Jun 16, 2020
    The classic "Tensorflow without a PhD" tutorial has been updated for Keras and Tensorflow 2.2: codelabs.developers.google.com/codelabs/cloud… After many years, still a good place to start learning about neural networks, relu, softmax, cross-entropy, learning rates, dropout, batch norm, ... Enjoy!
  • user avatar
    Martin Görner
    @martin_gorner
    Sep 16, 2024
    Personal update: I'h joining Hugging Face today!
    69K
  • user avatar
    Martin Görner
    @martin_gorner
    Jan 19, 2017
    I believe a dev can get up to speed on neural networks in 3h and then learn by himself. Ready for a crash course? youtu.be/qyvlt7kiQoI /1
  • user avatar
    Martin Görner
    @martin_gorner
    Jan 23, 2023
    A fascinating overview of research into "Dataset Distillation" arxiv.org/abs/2301.07014 How to train a neural network on fewer data points and achieve the same performance as when training on the original dataset.
    130K
  • user avatar
    Martin Görner
    @martin_gorner
    Dec 29, 2022
    Large Language Models are getting good at formal logic: arxiv.org/abs/2212.13894 LAMBADA: Backward Chaining for Automated Reasoning.
    102K
  • user avatar
    Martin Görner
    @martin_gorner
    Jan 4, 2019
    Here is an end-to-end canonical sample for training a model on Cloud TPUs in Keras. It has full code for loading the data from scratch using tf.data.Dataset and also exporting the trained model to ML Engine for inference. Colab notebook: colab.research.google.com/github/GoogleC…
  • user avatar
    Martin Görner
    @martin_gorner
    Jul 29, 2021
    The book is out🎉😄🎉. Official announcement from O'Reilly.
    user avatar
    O'Reilly Media
    @OReillyMedia
    Jul 29, 2021
    [NEW RELEASE] Practical Machine Learning for Computer Vision -- Learn how to design, train, evaluate, and predict with models written in TensorFlow or Keras, w/ experts @lak_gcp @martin_gorner & Ryan Gillard oreil.ly/4ugsQ #OReillyExperts #NewBook
    00:00
  • user avatar
    Martin Görner
    @martin_gorner
    Oct 11, 2022
    This looks like the Vision Transformers architecture we have been waiting for: MaxViT arxiv.org/abs/2204.01697 1/ State of the Art accuracy on ImageNet (no pre-training on huge datasets) 2/ Linear complexity wrt. image size (thanks to a clever attention design)
  • user avatar
    Martin Görner
    @martin_gorner
    Dec 5, 2022
    Replying to @martin_gorner and @geoffreyhinton
    And finally, Hinton points out that FF is easily implementable with very power-efficient analog circuits. This could allow us to run very large language models in a fraction of a Watt! Read the paper for more Hinton's thoughts I have omitted. cs.toronto.edu/~hinton/FFA13.…
  • user avatar
    Martin Görner
    @martin_gorner
    Feb 13, 2019
    TPUs in Google Colaboratory, now with less boilerplate code. See the Keras TPU sample here: colab.research.google.com/github/GoogleC… google.colab.auth.authenticate_user() to propagate your credentials to the backend and the TPU. TPUClusterResolver() to find your TPU. That's it!
    Colab logo
    colab.research.google.com
    Keras MNIST TPU end-to-end - training, saved model and online inference
    Run, share, and edit Python notebooks