Teaching machines to understand video could be the key to giving them common sense
- by 7wData
Yann LeCun says the next frontier in machine vision is software that learns just by observing the world.
Five years ago, researchers made a sudden leap in the accuracy of software that can interpret images. The technology behind it, artificial neural networks, underpins the recent boom in artificial intelligence (see “10 Breakthrough Technologies 2013: Deep Learning”). It is why Google and Facebook now let you search inside your photos, and it has unlocked new applications for facial recognition.
Yann LeCun, director of Facebook’s AI research group and a professor at New York University, helped pioneer the use of neural networks for machine vision. He says there’s still progress to be made—and that it could lead to software with common sense.
Just how good is machine vision now?
If you have an image with a dominant object in it, and the name of the game is to give the category of the object—that just works. As long as you have enough data, on the order of 1,000 objects per category, we can recognize very specific objects like cars of a particular brand or plants of a particular species or dogs of a particular breed. We can also recognize more abstract categories, like whether images are landscapes, sunsets, weddings, or birthday parties. Just five years ago it wasn’t clear this problem was completely solvable. But that doesn't mean vision is solved.
What’s an important problem that isn’t “solved” yet?
People have been playing for a number of years with the idea of generating captions or descriptions for images and video. There have been, on the face of it, impressive demonstrations, [but] those are not as impressive as they look. Their domain of expertise is very limited to whatever universe we train them on. Most of the systems, you show them images with other types of objects or unusual situations they've never seen and they will say complete garbage about it. They don't have common sense.
What’s the connection between vision and common sense?
It depends who you talk to—even within Facebook there are people with different opinions on this.
[Social9_Share class=”s9-widget-wrapper”]
Upcoming Events
Strategies for simplifying complex Salesforce data migrations – Free Webinar
27 March 2024
5 PM CET – 6 PM CET
Read MoreCategories
You Might Be Interested In
Why businesses must make cyber security skills a priority in 2017
13 Jan, 2017The scale of the cyber security skills shortage is a reflection of the attacks businesses face, which continue to grow …
Using ‘Faked’ Data is Key to Allaying Big Data Privacy Concerns
16 May, 2017MIT is out of the blocks first once again with a technological development designed to fix some of the privacy …
How to Successfully Deploy an Enterprise Data Lake
23 Feb, 2018How to Successfully Deploy an Enterprise Data Lake As enterprises try to extract more value from their data, the notion …
Recent Jobs
Do You Want to Share Your Story?
Bring your insights on Data, Visualization, Innovation or Business Agility to our community. Let them learn from your experience.