Why average can get your predictions very wrong (ep. 102)

04/19/20 • 14 min

Whenever people reason about probability of events, they have the tendency to consider average values between two extremes.
In this episode I explain why such a way of approximating is wrong and dangerous, with a numerical example.

We are moving our community to Slack. See you there!

We are moving our community to Slack. See you there!

Previous Episode

Activate deep learning neurons faster with Dynamic RELU (ep. 101)

In this episode I briefly explain the concept behind activation functions in deep learning. One of the most widely used activation function is the rectified linear unit (ReLU).
While there are several flavors of ReLU in the literature, in this episode I speak about a very interesting approach that keeps computational complexity low while improving performance quite consistently.

This episode is supported by pryml.io. At pryml we let companies share confidential data. Visit our website.

Don't forget to join us on discord channel to propose new episode or discuss the previous ones.

References

Dynamic ReLU https://arxiv.org/abs/2003.10027

Next Episode

Pandemics and the risks of collecting data (Ep. 103)

Codiv-19 is an emergency. True. Let's just not prepare for another emergency about privacy violation when this one is over.

Join our new Slack channel

This episode is supported by Proton. You can check them out at protonmail.com or protonvpn.com

If you like this episode you’ll love

ITSPmagazine Podcasts

Joomla Beat Podcast | Web design, development, online marketing, social media & website management

Aspen Ideas to Go

Pivot

How to Fix Democracy

Episode Comments

Generate a badge

Get a badge for your website that links back to this episode

Select type & size

Copy