Andrew Ng Quotes

As commentators like the American psychologist Gary Marcus have noted, it's extremely difficult to teach a computer to recognise cats. And that's not for want of trying.

Graphics has lately made a great shift towards machine learning, which itself is about understanding data.

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

The deep learning techniques, while relatively easy to learn, are quite foreign to traditional engineering modalities. It takes a different mindset and a relaxation of the presumption of control. The practitioners are like magi, sequestered from the rest of a typical engineering process.

I think the first wave of deep learning progress was mainly big companies with a ton of data training very large neural networks, right? So if you want to build a speech recognition system, train it on 100,000 hours of data.

With the Google Brain project, we made the decision to build deep learning processes on top of Google's existing infrastructure.

We now think of internal representation as great big vectors, and we do not think of logic as the paradigm for how to get things to work. We just think you can have these great big neural nets that learn, and so, instead of programming, you are just going to get them to learn everything.

Deep learning is a subfield of machine learning, which is a vibrant research area in artificial intelligence, or AI.

Pretend I asked, now answer the question.

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

The thing that's going to make artificial intelligence so powerful is its ability to learn, and the way AI learns is to look at human culture.

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.

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.

Beyond helping other people build AI systems with Deeplearning.ai, I also hope to build some AI systems myself!

When you have a large amount of data that is labeled so a computer knows what it means, and you have a large amount of computing power, and you're trying to find patterns in that data, we've found that deep learning is unbeatable.

AIs are only as good as the data they are trained on.

The paradigm shift of the ImageNet thinking is that while a lot of people are paying attention to models, let's pay attention to data. Data will redefine how we think about models.

Take any old classification problem where you have a lot of data, and it's going to be solved by deep learning. There's going to be thousands of applications of deep learning.

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.

All you need is lots and lots of data and lots of information about what the right answer is, and you'll be able to train a big neural net to do what you want.

Deep learning doesn't shine.

In deep learning, the algorithms we use now are versions of the algorithms we were developing in the 1980s, the 1990s. People were very optimistic about them, but it turns out they didn't work too well.

The strange flavour of AI work is that people try to put together long sets of rules in strict formalisms which tell inflexible machines how to be flexible.

We really believe that long-term, the way AI will drive is similar to the way humans drive - we don't break the problem down into objects and vision and localization and planning. But how long it will take us to get there is questionable.

The challenge for what everybody's seeing in deep learning - the software richness is really quite high. In training, you have to wait days and weeks before it comes back to tell you whether your model works or not. And in the beginning, they all don't work.