The technology behind our platforms

October 17, 2024
Visualisation of an artificial neural network (ANN)
Coert van Gemeren
Written by

Coert van Gemeren

In short...

The artificial neural network powering expoze.io was first exposed to millions of images to learn to detect objects, and subsequently trained on thousands of images to learn to generate the correct attention heatmaps.

It uses all this experience when generating the attention prediction results for your image or video. That is why it is possible that when you click “create new heatmap” your attention heatmap matches real eye tracking results with an accuracy of 95%.

Download the whitepaper

Click here to read the whitepaper

Related Insights
A cutting board with a cabbage cut in half, that looks like a brain and the knife on its side

How Might Businesses Use Cognitive Biases To Their Advantage

Learn how businesses can use cognitive biases to influence decisions, boost sales, and create stronger customer connections.

READ MORE
Two men arm wrestling and YouTube AdWars, supermarkets edition written on the center of the image

YouTube AdWars: Battle of the Brands - Supermarkets Edition

We compared YouTube ads from 5 top supermarket brands—Aldi, Walmart, Lidl, Tesco (Whoosh) and Penny—to see which performs best on junbi’s ad platform.

READ MORE
A laptop showing the junbi platform with Samsung ad results

How to Interpret junbi.ai’s Results and Elevate Your Ad Performance

Learn how to optimize your ad in minutes using junbi.ai scores. Make small changes for big improvements without the need for a complete ad overhaul!

READ MORE

Subscribe to our monthly newsletter.

Stay ahead of the competition with a monthly summary of our top articles and new scientific research.