James Padolsey that’s a bit worrying for me considering I intended this for software engineers, not…
Sachin Abeywardana
11

First — what you’re doing here is great, and definitely lowers the barrier to accessibility for newcomers to DL, so thank you!

It’s impossible to cater to all different levels. I guess you just have to pick a specific level and cater really well to that.

Lesson 0 seemed to start of well enough but it very quickly became complicated, and littered with concepts I didn’t understand. E.g. The following sentence:

> the best fitting function $f(x_i|w,b)$ such that we minimising the loss function by varying $w$ and $b$

I’m already lost. Like, I don’t understand what we’re actually doing here. I am a programmer, but not a mathematician. And this is lesson 0. But we’re already having to understand complex equations and loss functions and single-letter variables with spurious relations to real-life context.

I think it would help to slowly explain a bunch of the foundational ideas here. Just with language and fun examples/diagrams. For example I found this really understandable: https://ml.berkeley.edu/blog/2016/11/06/tutorial-1/

I hope this feedback is helpful.

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.