This is a clip from a conversation with Jeremy Howard on the Artificial Intelligence podcast. You can watch the full conversation here: http://bit.ly/2NG4qwr If you enjoy these, consider subscribing, sharing, and commenting below.

Full episode: http://bit.ly/2NG4qwr
Full episodes playlist: http://bit.ly/2EcbaKf
Clips playlist: http://bit.ly/2JYkbfZ
Podcast website: https://lexfridman.com/ai

Jeremy Howard is the founder of fast.ai, a research institute dedicated to make deep learning more accessible. He is also a Distinguished Research Scientist at the University of San Francisco, a former president of Kaggle as well a top-ranking competitor there, and in general, he's a successful entrepreneur, educator, research, and an inspiring personality in the AI community.

Subscribe to this YouTube channel or connect on:
- Twitter: https://twitter.com/lexfridman
- LinkedIn: https://www.linkedin.com/in/lexfridman
- Facebook: https://www.facebook.com/lexfridman
- Instagram: https://www.instagram.com/lexfridman
- Medium: https://medium.com/@lexfridman
- Support on Patreon: https://www.patreon.com/lexfridman

So what advice do you have for someone who wants to get started in deep learning?

So like, so I would, you know, I think, it's not just me, I think our course is very good, but also lots of people independently have said it's very good.

It recently won the CogX award for AI courses as being the best in the world.

I'd say come to our course, course.fast.ai.

And the thing I keep on hopping on in my lessons is train models, print out the inputs to the models, print out to the outputs to the models, like study, you know, change the inputs a bit, look at how the outputs vary, just run lots of experiments to get a, you know, an intuitive understanding of what's going on.

To get hooked, do you think, you mentioned training, do you think just running the models inference, like if we talk about getting started?

So that's the critical thing, because at that point you now have a model that's in your domain area.

So there's no point running somebody else's model, because it's not your model.

So it only takes 5 minutes to fine-tune a model for the data you care about.

And in lesson 2 of the course, we teach you how to create your own dataset from scratch by scripting Google Image Search.

And we show you how to actually create a web application running online.

So I create 1 in the course that differentiates between a teddy bear, a grizzly bear, and a brown bear.

And it does it with basically 100% accuracy.

Took me about 4 minutes to scrape the images from Google search in the script.

There's a little graphical widgets we have in the notebook that help you clean up the data set.

There's other widgets that help you study the results to see where the errors are happening.

And so Now we've got over a thousand replies in our share your work here thread of students saying here's the thing I built.

And so there's people who like, and a lot of them are state of the art.

Like somebody said, Oh, I tried looking at Devan Gari characters and I couldn't believe it.

The thing that came out was more accurate than the best academic paper after lesson 1.

And then there's others which are just more kind of fun, like somebody who's doing Trinidad and Tobago hummingbirds.

She said that's kind of their national bird and she's got something that can now classify Trinidad and Tobago Hummingbirds.

So yeah, train models, fine-tune models with your dataset and then study their inputs and outputs.

Okay, once a person understands the basics, trains a bunch of models, if we look at the scale of years, what advice do you have for someone wanting to eventually become an expert?

Specifically, train lots of models in your domain area.

We don't need more expert, like, create slightly evolutionary research in areas that everybody's studying.

We need experts at using deep learning to diagnose malaria.

Or we need experts at using deep learning to analyze language to study media bias.

Or we need experts in analyzing fisheries to identify problem areas in, you know, the ocean.

So like, become the expert in your passion area.

And this is a tool which you can use for just about anything.

And you'll be able to do that thing better than other people, particularly by combining it with your passion and domain expertise.

Even if you do want to innovate on transfer learning or active learning, your thought is, I mean it's 1 I certainly share, is you also need to find a domain or data set that you actually really care for.

If you're not working on a real problem that you understand, how do you know if you're doing it any good?

You know, how do you know if your results are good?

How do you know if you're getting bad results?

Like, how do you know you're doing anything useful?

Yeah, the only, to me, the only really interesting research is, not the only, but the vast majority of interesting research is like, try and solve an actual problem and solve it really well.


Speaker 0: So what advice do you have for someone who wants to get started in deep learning?

Speaker 1: Train lots of models. That's how you learn it. So like, so I would, you know, I think, it's not just me, I think our course is very good, but also lots of people independently have said it's very good. It recently won the CogX award for AI courses as being the best in the world. I'd say come to our course, course.fast.ai.

And the thing I keep on hopping on in my lessons is train models, print out the inputs to the models, print out to the outputs to the models, like study, you know, change the inputs a bit, look at how the outputs vary, just run lots of experiments to get a, you know, an intuitive understanding of what's going on.

Speaker 0: To get hooked, do you think, you mentioned training, do you think just running the models inference, like if we talk about getting started?

Speaker 1: No, you've got to fine tune the models. So that's the critical thing, because at that point you now have a model that's in your domain area. So there's no point running somebody else's model, because it's not your model. So it only takes 5 minutes to fine-tune a model for the data you care about. And in lesson 2 of the course, we teach you how to create your own dataset from scratch by scripting Google Image Search.

And we show you how to actually create a web application running online. So I create 1 in the course that differentiates between a teddy bear, a grizzly bear, and a brown bear. And it does it with basically 100% accuracy. Took me about 4 minutes to scrape the images from Google search in the script. There's a little graphical widgets we have in the notebook that help you clean up the data set.

There's other widgets that help you study the results to see where the errors are happening. And so Now we've got over a thousand replies in our share your work here thread of students saying here's the thing I built. And so there's people who like, and a lot of them are state of the art. Like somebody said, Oh, I tried looking at Devan Gari characters and I couldn't believe it. The thing that came out was more accurate than the best academic paper after lesson 1.

And then there's others which are just more kind of fun, like somebody who's doing Trinidad and Tobago hummingbirds. She said that's kind of their national bird and she's got something that can now classify Trinidad and Tobago Hummingbirds. So yeah, train models, fine-tune models with your dataset and then study their inputs and outputs.

Speaker 0: How much is Fast.ai courses? Free.

Speaker 1: Everything we do is free. We have no revenue sources of any kind. It's just a service to the community.

Speaker 0: You're a saint. Okay, once a person understands the basics, trains a bunch of models, if we look at the scale of years, what advice do you have for someone wanting to eventually become an expert?

Speaker 1: Train lots of models. Specifically, train lots of models in your domain area. So an expert what? Right? We don't need more expert, like, create slightly evolutionary research in areas that everybody's studying.

We need experts at using deep learning to diagnose malaria. Or we need experts at using deep learning to analyze language to study media bias. Or we need experts in analyzing fisheries to identify problem areas in, you know, the ocean. You know, that's, that's what we need. So like, become the expert in your passion area.

And this is a tool which you can use for just about anything. And you'll be able to do that thing better than other people, particularly by combining it with your passion and domain expertise. So

Speaker 0: that's really interesting. Even if you do want to innovate on transfer learning or active learning, your thought is, I mean it's 1 I certainly share, is you also need to find a domain or data set that you actually really care for.

Speaker 1: Right. If you're not working on a real problem that you understand, how do you know if you're doing it any good? You know, how do you know if your results are good? How do you know if you're getting bad results? Why are you getting bad results?

Is it a problem with the data? Like, how do you know you're doing anything useful? Yeah, the only, to me, the only really interesting research is, not the only, but the vast majority of interesting research is like, try and solve an actual problem and solve it really well. You

See all Lex Fridman transcripts on Youtube

Deep Learning: Advice on Getting Started with fast.ai - Jeremy Howard | AI Podcast Clips