Intelligence, Inside and Outside.

Why Artificial Neural Networks Have A Long Way To Go Before They Can ‘See’ Like Us

Artificial neural networks were created to imitate processes in our brains, and in many respects – such as performing the quick, complex calculations necessary to win strategic games such as chess and Go – they’ve already surpassed us. But if you’ve ever clicked through a CAPTCHA test online to prove you’re human, you know that our visual cortex still reigns supreme over its artificial imitators (for now, at least). So if schooling world chess champions has become a breeze, what’s so hard about, say, positively identifying a handwritten ‘9’? This explainer from the US YouTuber Grant Sanderson, who creates maths videos under the moniker 3Blue1Brown, works from a program designed to identify handwritten variations of each of the 10 Arabic numerals (0-9) to detail the basics of how artificial neural networks operate. It’s a handy crash-course – and one that will almost certainly make you appreciate the extraordinary amount of work your brain does to accomplish what might seem like simple tasks.

 

This feature originally appeared in Aeon.

Read More  What Are The Ethical Consequences Of Immortality Technology?

For enquiries, product placements, sponsorships, and collaborations, connect with us at [email protected]. We'd love to hear from you!
Share this article
Shareable URL
Prev Post

Google I/O 2019 | Federated Learning: Machine Learning on Decentralized Data

Next Post

Algorithms Are Opinions, Not Truth Machines, And Demand The Application Of Ethics

Read next