AI News, Machine Learning @ Teads (part 2)
- On Sunday, June 3, 2018
- By Read More
Machine Learning @ Teads (part 2)
Our training jobs are scheduled by Jenkins, their dependencies are handled by Coursier, and they run on AWS Elastic Map Reduce with training logs and resulting models stored on S3.
Our specific use cases require to be able to work with large streams of ad delivery events such as bid requests, impressions or complete views and continuously update our models.
The runtime is still based on Spark and our library acts as an abstraction layer between Spark and underlying implementations from Breeze and embeds our custom algorithms.
This library is part of a more general prediction framework that enables to test new experimental approaches and guarantees that the same code is used both online and offline.
The generated application logs are then used, together with other sources of data (DMPs, etc.) to build training sets .
For the training jobs , these data sets are randomly split into several partitions that are balanced to avoid hotspots.
A/B tests aim at deciding which algorithm, which home page, which user interface, etc., provides the best results in terms of relevant criteria such as traffic and revenue.
We usually split the population into three and define one small population to be able to identify if there is a major issue with the experiment.
This validation is made by iterations to be as close as possible to the production cycle, as illustrated in the following chart (3 iterations).
Thus, we focus on the MSE of the expected revenue (Cost per View or CPV) and not the MSE of a billable probability: We created a tool, called Datakinator, to facilitate the creation of homogeneous experiments that all respect the same testing protocol.
- On Friday, July 19, 2019
SPSS for questionnaire analysis: Correlation analysis
Basic introduction to correlation - how to interpret correlation coefficient, and how to chose the right type of correlation measure for your situation.
But what *is* a Neural Network? | Chapter 1, deep learning
Subscribe to stay notified about new videos: Support more videos like this on Patreon: Special .
Understanding the p-value - Statistics Help
With Spanish subtitles. This video explains how to use the p-value to draw conclusions from statistical output. It includes the story of Helen, making sure that the ...
12 Finding the Right Model
Download the sample tutorial files at
Long Term Effects of Exercise
Recommended Revision Guide BTEC First in Sport Unit 4: The Sports Performer in Action Check out my website for .
Lecture 09 - The Linear Model II
The Linear Model II - More about linear models. Logistic regression, maximum likelihood, and gradient descent. Lecture 9 of 18 of Caltech's Machine Learning ...
Ever wonder how Bitcoin (and other cryptocurrencies) actually work?
Bitcoin explained from the viewpoint of inventing your own cryptocurrency. These in-depth videos are made possible by patreon: ...
MIT 6.S094: Deep Reinforcement Learning for Motion Planning
This is lecture 2 of course 6.S094: Deep Learning for Self-Driving Cars taught in Winter 2017. This lecture introduces types of machine learning, the neuron as a ...
Lecture 15 - Kernel Methods
Kernel Methods - Extending SVM to infinite-dimensional spaces using the kernel trick, and to non-separable data using soft margins. Lecture 15 of 18 of ...
The Ultimate Truth
Skip to Part 2: Research sources: .