fastbook

The FastAI lessons on tabular data are highly relevant here. https://github.com/fastai/fastbook/blob/master/09_tabular.ip... https://docs.fast.ai/tutorial.tabular.html https://docs.fast.ai/tabular.model.html

I think FastAI lesson 3 in "Practical Deep Learning for Coders", has one of the most intuitive buildups of gradient descent and loss that I've seen. * Lecture [1] Book Chapter [2] It doesn't go into the math but I don't think that's a bad thing for beginners. If you want mathematical, 3blue1brown has a great series of videos [3] on the topic. [1] https://www.youtube.com/watch?v=hBBOjCiFcuo&t=1932s [2] https://github.com/fastai/fastbook/blob/master/04_mnist_basi... [3] https://www.youtube.com/watch?v=aircAruvnKk * I've been messing around with this stuff since 2016 and have done a few different courses like the original Andrew Ng course and more.

So that is why lecture 2 in the fast.ai course is a bear detector that also can detect if it is a real bear or a teddy bear https://github.com/fastai/fastbook/blob/master/02_production...

Link to book (read online): https://course.fast.ai/Resources/book.html https://github.com/fastai/fastbook

"Practical Deep Learning for Coders" 2022: https://github.com/fastai/course22 "Deep Learning for Coders with Fastai and Pytorch: AI Applications Without a PhD" (2020) https://github.com/fastai/fastbook There's also a new nbdev; nbdev v2: https://github.com/fastai/nbdev and nbdev-template to start new projects with: https://github.com/fastai/nbdev-template

The fastai book actually makes a nice comparison between the systems described in PDP and modern deep learning. > In fact, the approach laid out in PDP is very similar to the approach used in today's neural networks. From: https://github.com/fastai/fastbook/blob/master/01_intro.ipyn...

For the purpose of this question, you might search for pre-trained models that predict what you want to predict, and use them. https://modelzoo.co/ https://github.com/tensorflow/models https://cv.gluon.ai/model_zoo/index.html If there are no pre-trained models, you could take a look at fast.ai courses: https://course18.fast.ai/ml.html (for Machine Learning (ML)) https://www.fast.ai (for others "DL" (Deep Learning)) This courses is targeted towards programmers, and they dive right into the code to use ML (train models and use them) with Jupyter notebooks. They also have a book whose notebooks are here: https://github.com/fastai/fastbook If you have some maths background (high-school, or first year university), check out Stanford's CS229 with Andrew Ng: https://www.youtube.com/playlist?list=PLoROMvodv4rMiGQp3WXSh... I think it's better than

I used fastai book: https://github.com/fastai/fastbook It also exists as hardcover

We're experimenting with `nbdev`[0], especially in our effort to support fast.ai's[1] latest course 'fastbook'[2] on iko.ai[3], to test their notebooks faster. Though scheduling notebooks on our platform is a breeze[4][5] and we could launch the 20 notebooks really fast even manually and check their output while running (some fail that way as they required user interaction for FileUpload or something, and we decided to use fixtures). - [0]: https://github.com/fastai/nbdev - [1]: https://www.fast.ai/ - [2]: https://github.com/fastai/fastbook - [3]: https://iko.ai - [4]: https://iko.ai/docs/notebook/#long-running-notebooks - [5]: https://pbs.twimg.com/tweet_video/Entg8COXcAIDdTI.mp4

In case it's of interest, we wrote a system for converting Jupyter Notebooks to asciidoc, which we used to publish an O'Reilly book. This is the book: https://www.amazon.com/Deep-Learning-Coders-fastai-PyTorch/d... This is the nb->asciidoc convertor: https://github.com/fastai/fastdoc These are the source notebooks: https://github.com/fastai/fastbook/

I do recommend getting the book that just came out (I did, it is fantastic) https://www.amazon.com/Deep-Learning-Coders-fastai-PyTorch/d... that said: fast.ai also released a draft of the book available here (including the notebooks) https://github.com/fastai/fastbook edit: if you can afford it, getting the book is a great way to support the authors

You can see the syllabus: http://ethics.fast.ai/syllabus/ . There's a free book chapter that covers a subset of the material, so you might that a more focused approach if that's what you're looking for: https://github.com/fastai/fastbook/blob/master/03_ethics.ipy...

The perfect example of a textbook as a collection of Jupyter notebooks may be the Deep Learning for Coders book: https://github.com/fastai/fastbook