For sure I could write heuristics for parsing each format. I was kind of hoping that ML algorithms had advanced to the state where they could handle messy tables in documents. (By the way if they have, that could be big for the companies with good structuring models. Financial data is unbelievably expensive and a lot of it is publicly available but badly organized, so structuring companies could conceivably eat that those markets as just one application of their tools. Starting with cheap stuff for hobbyists/students who can't afford the commercial solutions).
The complex includes 20 or so funds, so each file includes a "hot spot" with data that I'd like to extract. Within a filing the holdings tables all look the same. The format of the document changes from year to year. Unfortunately the tables aren't really formatted as tables in the html, so I thought rendering to pdf and passing off to an LLM might be the best thing to do. I posted links to a few examples below.
> you're pretty dismissive of it without actually reading the details of how they went about things...
I wasn't really trying to be dismissive (other than saying that I personally would not recommend it to a young person interested in programming and deep learning). I was mostly trying to start a discussion about the best way to teach/learn this subject. I hoped to attract more knowledgeable commenters (such as yourself). A day later I still stand by my personal opinion that it's probably best to learn the mathematics first, and to use the lingua franca of the domain.
I'd like to add that, from my perspective, this pseudo-critique was a very small part of my comment. I was mostly trying to say "It's very important and difficult to keep early students' interest. Bravo on the novel approach taken in the book. It's much better than what I had as a college student." That might not have been clear in my comment.
> You're not quite judging a book by its cover, but you're not that far beyond that.
Fair. But there wasn't anything else to read in the submission and I was trying to start a curious conversation. Despite my good intentions it was a bad comment.
I'm a huge fan of project based learning like the approach taken in this book. But I'm not sure if it's a good idea to introduce early stage students to Scheme before Python, or deep learning before calculus.
I studied pure math in college, and we were required to take 2 "Computer Science" classes as part of that program. Mainly memorizing textbook algorithms and data structure implementations in Java. I hated programming for years after that, until during graduate school I came up with a project of my own that organically required knowledge of Matlab and later Python. I loved programming after that.
I hope books like this can help new students avoid the trough of disillusionment that can sometimes happen if you're forced to learn a cool subject (like programming) in a very uncool way.
Personally, I would not recommend this book to a young person interested in deep learning and programming (based on the table of contents). I would probably recommend they first learn calculus and use Python to make plots while doing so. Then read Fleuret's "The Little Book of Deep Learning" and try to implement simple models in PyTorch.
One of my favorite parts of the 2024 series on Youtube was when Prof B explained her excitement just before introducing UCB algorithms (Lecture 11): "So now we're going to see one of my favorite ideas in the course, which is optimism under uncertainty... I think it's a lovely principle because it shows why it's provably optimal to be optimistic about things. Which is kind of beautiful."
Those moments are the best part of classroom education. When a super knowledgeable person spends a few weeks helping you get to the point where you can finally understand something cool. And you can sense their excitement to tell you about it. I still remember learning Gauss-Bonnet, Stokes Theorem, and the Central Limit Theorem. I think optimism under uncertainty falls in that group.
For sure I could write heuristics for parsing each format. I was kind of hoping that ML algorithms had advanced to the state where they could handle messy tables in documents. (By the way if they have, that could be big for the companies with good structuring models. Financial data is unbelievably expensive and a lot of it is publicly available but badly organized, so structuring companies could conceivably eat that those markets as just one application of their tools. Starting with cheap stuff for hobbyists/students who can't afford the commercial solutions).
The complex includes 20 or so funds, so each file includes a "hot spot" with data that I'd like to extract. Within a filing the holdings tables all look the same. The format of the document changes from year to year. Unfortunately the tables aren't really formatted as tables in the html, so I thought rendering to pdf and passing off to an LLM might be the best thing to do. I posted links to a few examples below.
https://www.sec.gov/Archives/edgar/data/36405/00011046592508...
https://www.sec.gov/Archives/edgar/data/36405/00009324710500...