Image Recognition Quotes

One thing ImageNet changed in the field of AI is suddenly people realized the thankless work of making a dataset was at the core of AI research.

I've always been very interested in the question of how computation can fundamentally advance the things that we can see. This led me to have a fascination with medical imaging, especially things like MRI and scanning, and eventually computer graphics.

When I was a graduate student in computer science in the early 2000s, computers were barely able to detect sharp edges in photographs, let alone recognize something as loosely defined as a human face.

By developing deep learning solutions that are faster, easier, and less expensive to use, Nervana is democratizing deep learning and fueling advances in medical diagnostics, image and speech recognition, genomics, agriculture, finance, and eventually across all industries.

There is great potential to use computer vision technology in a constructive and benevolent way.

But I think we're also just talking about the literacy of the audience. The visual literacy of the audience. They've seen so many images now, especially here in the States. There's so much to look at, to watch. So the visual storytelling literacy is harder to impress.

In the past, Google has used teams of humans to 'read' its street address images - in essence, to render images into actionable data. But using neural network technology, the company has trained computers to extract that data automatically - and with a level of accuracy that meets or beats human operators.

In Silicon Valley, there are a lot of startups using computer vision for agriculture or shopping - there are a lot for clothes shopping. At Baidu, for example, if you find a picture of a movie star, we actually use facial recognition to identify that movie star and then tell you things like their age and hobbies.

If computers remain far worse than us at image recognition, a certain over-confident combination of man and machine can elsewhere take inaccuracy to a whole new level.

I want to build the next CNN with 'VICE' - it's within my grasp.

I think we choose gear by the way that it looks. We choose lots of things by the way that it looks. I don't like bands that look like roadies. I don't like when I can't tell who's the guitar tech and who's the guitar player.

I think when your image becomes so big that it's hard for a viewer to see a character, then I think you're in danger as an actor of being unable to perform what you should be doing.

Very quickly a painting is turned into a facsimile of itself when one becomes so familiar with with it that one recognizes it without looking at it.

Algorithms learn by being fed certain images, often chosen by engineers, and the system builds a model of the world based on those images. If a system is trained on photos of people who are overwhelmingly white, it will have a harder time recognizing nonwhite faces.

Artificial intelligence is one of 50 things that Watson does. There is also machine learning, text-to-speech, speech-to-text, and different analytical engines - they're like little Lego bricks. You can put intelligence in any product or any process you have.

Understanding vision and building visual systems is really understanding intelligence.

Without images we can neither think nor understand anything.

Want to train a machine translation system? Train it on a gazillion pairs of sentences of parallel corpora, and that creates a lot of breakthrough results. Increasingly, I'm seeing results on small data where you want to try to take in results even if you have 1,000 images.

The real use of AI in industry is generally for very narrow pattern-matchers - a better search algorithm, an object-detection algorithm, etc. These things are tools which we can use - for good or evil. But they're nothing like self-aware beings.

The revolution in deep nets has been very profound. It definitely surprised me, even though I was sitting right there.

The future of Windows is to let the computer see, listen and even learn.

All images generated by imaging technology are viewed in a walled-off location not visible to the public. The officer assisting the passenger never sees the image, and the officer viewing the image never interacts with the passenger. The imaging technology that we use cannot store, export, print or transmit images.

The possibilities that come with thinking about the camera as a portal into the realm of information and services are attractive not only to Snap but also to every other big player in the tech world. Facebook, for instance, has slowly been enhancing the visual capabilities of its Messenger.

I think the way we're doing computer vision is just wrong.

Deep learning is already working in Google search and in image search; it allows you to image-search a term like 'hug.' It's used to getting you Smart Replies to your Gmail. It's in speech and vision. It will soon be used in machine translation, I believe.