deep learning
Preparing for the Unexpected
Yoel Zeldes | 27 Jan 2019 | Machine Learning
Some of the problems we tackle using machine learning involve categorical features that represent real world objects, such Read More...
Think your Data Different
Zohar Komarovsky and Yoel Zeldes | 21 Jan 2019 | Machine Learning
In the last couple of years deep learning (DL) has become a main enabler for applications in many Read More...
Deep Multi-Task Learning – 3 Lessons Learned
Zohar Komarovsky | 06 Jan 2019 | Data Science
For the past year, my team and I have been working on a personalized user experience in the Read More...
The Story of a Bad Train-Test Split
Yoel Zeldes | 16 Dec 2018 | Data Science
About a year ago we incorporated a new type of feature into one of our models used for Read More...
How to Engineer Your Way Out of Slow Models
Yoel Zeldes | 28 Oct 2018 | Data Science
So you just finished designing that great neural network architecture of yours. It has a blazing number of Read More...
Zooming Past the Competition
Yoel Zeldes and Amir Keren | 10 Oct 2018 | Data Science
Imagine you’re walking down the street and you see a nice car you’re thinking of buying. Just by Read More...
Uncertainty for CTR Prediction: One Model to Clarify Them All
Yoel Zeldes and Inbar Naor | 21 Aug 2018 | Data Science
In the first post of the series we discussed three types of uncertainty that can affect your model Read More...
Recommender Systems: Exploring the Unknown Using Uncertainty
Yoel Zeldes and Inbar Naor | 14 Aug 2018 | Data Science
Now that we know what uncertainty types exist and learned some ways to model them, we can start Read More...
Neural Networks from a Bayesian Perspective
Yoel Zeldes and Inbar Naor | 06 Aug 2018 | Data Science
Understanding what a model doesn’t know is important both from the practitioner’s perspective and for the end users Read More...
Using Uncertainty to Interpret your Model
Yoel Zeldes and Inbar Naor | 30 Jul 2018 | Data Science
As deep neural networks (DNN) become more powerful, their complexity increases. This complexity introduces new challenges, including model Read More...
Using Word2Vec for Better Embeddings of Categorical Features
Inbar Naor | 25 Apr 2018 | Data Science
Back in 2012, when neural networks regained popularity, people were excited about the possibility of training models without Read More...
To Predict Article Performance, Use Machine Learning Models
Matt Meng | 17 Sep 2017 | Data Science
Introduction Newsrooms are under constant pressure to deliver the most up to date, relevant, and engaging information possible. Read More...
Deep Learning – from Prototype to Production
Erez Kashi | 30 Jul 2017 | Big Data
About 8 months ago my team and I were facing the challenge of building our first Deep Learning Read More...
More than one Graph – Code Reuse in TensorFlow
Jenia Gorokhovsky | 02 Jul 2017 | Big Data
Large production pipelines in TensorFlow are quite difficult to pull off. Training small models is easy, and we Read More...
5 Simple tips for boosting your Jenkins performance