Here's the result: https://github.com/hangtwenty/dive-into-machine-learning
I want this guide to be a good resource for other people like me, who are curious to get into Machine Learning by this process:
2) coming to understand what you hacked
3) more structured, in-depth learning
It can be intimidating to approach Machine Learning this way. For a long time it felt like I couldn't do steps 1 or 2... and had to start with 3. That's intimidating!
Pull requests welcome, I want this to be a good resource! Thanks all.
Recently, deep learning changed this. Finding the right network architecture allows the net to learn the features by itself.
syllogism 264 days ago
Deep learning needs feature engineering too.
You still need to transform your context into a vector of boolean or real values, somehow. And that transform is going to encode assumptions about what information is relevant to the problem, and what's not.
Let's say you're trying to predict house prices. There's no end of geo-tagged data you might pull in. And if you have a cleverer idea than the next guy, your model will be more accurate. And, probably, if the next guy's at least competent, it'll be your feature ideas that set you apart.
In a linear model, you need to come up with a clever set of conjunction features, that balances bias and variance. You don't need to do that for a deep learning model, and that's a big advantage. But that's not the same as saying there's no feature engineering.