Unsupervised Learning Quotes

Pretend I asked, now answer the question.

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.

When I started out, there were a lot of things I knew I couldn't do, and a lot of things I only found out I couldn't do by going and doing it. And no-one was watching, and nobody cared.

In Portugal the coach would sit on the bench and not say a word. We'd just play. It was a matter of us making mistakes and learning from them by ourselves. You understand the game a lot better that way.

You have to teach your algorithm what it can do and what it cannot do because, otherwise, there is a risk that the algorithms will learn the tricks of the old cartels.

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.

Looking back, I realise it wasn't only gym I dreaded at school. Every class was a torment. It wasn't knowledge I objected to but instruction. Why couldn't they just tell us what books to read and leave us to get on and read them?

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.

My dad was lackadaisical on the discipline front. I dropped out of everything at school.

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.

Machine learning is the science of getting computers to learn without being explicitly programmed.

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

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.

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

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

Deep learning doesn't shine.

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

Experiments show that children in unsupervised groups are capable of answering questions many years ahead of the material they're learning in school. In fact, they seem to enjoy the absence of adult supervision, and they are very confident of finding the right answer.

I soon gave up instruction for self-teaching.

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.

I just had to plod along without having any teaching, which was a pity.

You grow up faster in a place where anything goes.

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.

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.