New project aims to 'reverse-engineer' the brain

The goal is to make computers learn the way humans do

Teaching computers to learn the way we do is widely considered an important step toward better artificial intelligence, but it's hard to achieve without a good understanding of how we think. With that premise in mind, a new $US12 million effort launched on Wednesday with aims to "reverse-engineer" the human brain.

Led by Tai Sing Lee, a professor in Carnegie Mellon University's Computer Science Department and the Center for the Neural Basis of Cognition (CNBC), the five-year project seeks to unlock the secrets of neural circuitry and the brain's learning methods. Ultimately, the goal is to improve neural networks, the computational models often used for AI in applications including self-driving cars, automated trading, and facial and speech recognition.

"Today's neural nets use algorithms that were essentially developed in the early 1980s," Lee said. "Powerful as they are, they still aren't nearly as efficient or powerful as those used by the human brain."

A computer might need to be shown thousands of labeled examples in order to learn to recognize an object, for example, while a human would require only a handful.

Trying to figure out why that's so will use a technique called two-photon calcium imaging microscopy. Researchers will record the signaling of tens of thousands of individual neurons in mice as they process visual information.

"By incorporating molecular sensors to monitor neural activity in combination with sophisticated optical methods, it is now possible to simultaneously track the neural dynamics of most, if not all, of the neurons within a brain region," said team member Sandra Kuhlman, assistant professor of biological sciences at Carnegie Mellon and the CNBC.

A massive data set will result, offering a detailed picture of how neurons in one region of the visual cortex behave, she added.

The project is funded by the Intelligence Advanced Research Projects Activity (IARPA) through its Machine Intelligence from Cortical Networks (MICrONS) research program, which is working to advance President Obama's BRAIN Initiative.

The CMU-led team will collaborate with other related projects and make multiple vast databases publicly available for research groups all over the world.

"The hope is that this knowledge will lead to the development of a new generation of machine-learning algorithms that will allow AI machines to learn without supervision and from a few examples, which are hallmarks of human intelligence," Lee said.

Another IARPA-funded project launched recently at Harvard shares a similar goal.

Join the newsletter!

Error: Please check your email address.
Show Comments

Blog Posts

How can a brand remain human in a digital world?

Some commentators estimate that by 2020, 85 per cent of buyer-seller interactions will happen online through social media and video*. That’s only two years away, and pertinent for any marketer.

James Kyd

Global head of brand strategy and marketing, Xero

​Relevance and substance are the keys to marketing’s future

Marketing’s evolution and increased value-add to organisations is making headway in one essential direction: Driving brands to achieve maximum relevance in the heart and minds of customers.

Jean-Luc Ambrosi

Author, marketer

Why doing your job well is the key to innovation

The words ‘power company’ and ‘innovation’ probably don’t seem like a natural combination. In fact, when I first went for a marketing role with an electricity company, I semi-dreaded the work I thought I’d be doing.

Catherine Anderson

Head of marketing, Powershop Australia

When you’re marketing to a customer, a bunch of that marketing data is actually also peace data. You just haven't looked at it that way,”...

Bill Hopkins

CMOs urged to use ‘peace data’ to create brand purpose while affecting positive social change

Read more

eHarmony should be closed forever for fraud!The success rate of eHarmony is less than 10%.eHarmony is ONLY a 17+ years old obsolete site...


eHarmony: How machine learning is leading to better and longer-lasting love matches

Read more ICO relaunch March 14 - April 14 2018. Building a bigger community and more holders will surely move Krios to top exchan...

Mark Dalton

Blockchain pitched as answer to influencer marketing management

Read more

Lok knocks it out the park and predicts the future...“People are starting to understand they own their own data, and this will come to a ...


Data regulation key to marketing innovation

Read more

It needs to come from the top. It's not just about buy-in from the leadership team, leadership should be part of the development process ...

Stephen Houraghan

Why getting intimate is key to creating a great customer experience and optimising customer value

Read more

Latest Podcast

More podcasts

Sign in