About Yoel Zeldes

Algorithm Engineer at AI21 Labs, in the mission of building AI systems with the capacity to understand and generate natural language.

Yoel Zeldes Posts (7)

  • GPT-3, a giant step for Deep Learning and NLP? - 09 Jun 2020
    Recently, OpenAI announced a new successor to their language model, GPT-3, that is now the largest model trained so far with 175 billion parameters. Training a language model this large has its merits and limitations, so this article covers some of its most interesting and important aspects.
  • Preparing for the Unexpected - 28 Feb 2019
    In some domains, new values appear all the time, so it's crucial to handle them in a good way. Using deep learning, one can learn a special Out-of-Vocabulary embedding for these new values. But how can you train this embedding to generalize well to any unseen value? We explain one of the methods employed at Taboola.
  • Variational Autoencoders Explained in Detail - 30 Nov 2018
    We explain how to implement VAE - including simple to understand tensorflow code using MNIST and a cool trick of how you can generate an image of a digit conditioned on the digit.
  • How to Engineer Your Way Out of Slow Models - 27 Nov 2018
    We describe how we handle performance issues with our deep learning models, including how to find subgraphs that take a lot of calculation time and how to extract these into a caching mechanism.
  • Word Morphing – an original idea - 20 Nov 2018
    In this post, we describe how to utilise word2vec's embeddings and A* search algorithm to morph between words.
  • Using Uncertainty to Interpret your Model - 16 Nov 2018
    We outline why you should care about uncertainty and discuss the different types, including model, data and measurement uncertainty and what different purposes these all serve.
  • Linear Regression in the Wild - 03 Oct 2018
    We take a look at how to use linear regression when the dependent variables have measurement errors.