Deep Learning: Adding EQ to the IQ of Today’s Technology

The world of Deep Learning* (Artificial Intelligence/Machine Learning) and the implementations are growing fast and this inspires me to think about more and more possible areas that might benefit of these technologies.

There are a lot of cool and interesting examples available on current implementations and developments. One I ran into last week which I would like to share with you is about Deep Learning for human emotion based on more than 12 billion of emotion data points collected from 2.9 million face videos.

The Ted Talk by “Rana el Kaliouby” is about this Deep learning algorithm and using it in an app that knows how you feel – from the look on your face.

Abstract of the Ted Talk:

Our emotions influence every aspect of our lives — how we learn, how we communicate, how we make decisions. Yet they’re absent from our digital lives; the devices and apps we interact with have no way of knowing how we feel. Scientist Rana el Kaliouby aims to change that. She demos a powerful new technology that reads your facial expressions and matches them to corresponding emotions. This “emotion engine” has big implications, she says, and could change not just how we interact with machines — but with each other.

[youtube_sc url=”https://www.youtube.com/watch?v=o3VwYIazybI”]

http://www.ted.com/talks/rana_el_kaliouby_this_app_knows_how_you_feel_from_the_look_on_your_face

What is especially interesting is that they share this technology to use within applications via SDK’s & API’s. (See http://www.affectiva.com/ for more information)
This opens a lot of potential and I already can think of a lot of options for implementations in current applications and use in different processes. I will definitely write some Graduation projects on this topic for graduation students at Info Support in the upcoming days. So if you’re looking for a graduation assignment about data Science, Deep Learning or using the outcome of these algorithms. Feel free to contact me to create a cool graduation assignment together.
But to give you an idea of my thoughts about the possible implementations for this EQ example I can think of at this moment:

• Emotion Based usability testing (even more powerful combined with eye tracking)
• Emotion based development of applications which initiate action based on your emotion
• Search engines that see the reaction of the search result and can better filter and search based on the emotion feedback
• Etc.

* Deep learning (deep machine learning, or deep structured learning, or hierarchical learning, or sometimes DL) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using model architectures, with complex structures or otherwise, composed of multiple non-linear transformations. {Source: https://en.wikipedia.org/wiki/Deep_learning}