hsikka

I'm studying CS and Biology, and I'm currently researching disentangling object representations using brain inspired auto encoders

I've been meaning to invest some time into learning Julia. I'll definitely try my hand soon

Incredible, thank you for the guidance! I'll look into these topics more carefully

Fantastic, thank you for the tip! I'll probably prepend Real Analysis to the list!

Awesome, it's heartening to see someone else feel the same way! And great note about the problems, maybe one of the classic textbooks would be a good addition for problems

Hey, author here, I really appreciate the feedback. Are there any specific prerequisites to Real Analysis?

Yeah, it is, its more of a loose goal, I'm doing research and working on finishing 2 Master's alongside it, so we'll see what happens! I really just want to learn and grow, so if it takes months or if it takes years, I'm in!

Yeah you nailed it!

Do you think there is a need for a better written DL textbook? I definitely agreed with the review you linked.

I've always thought that Hands on ML by Geron was great implementation wise, but lacking in the mathematical rigor and depth. While I would have a general sense of what is going on after reading it, and I'd certainly be able to structure and implement a model, I don't know if I would have any deep intuitions.

Great idea, I did that previously for undergrad applied math, thanks for the tip!

I’m confused about a few things:

1. What is slowest based on?

2. Is the comment about people working in the field meant to demonstrate something about slowness or some other point?

I don't have solid mental models about computer architecture and abstractions, and I always feel like I'm catching up on the math that's being employed in a lot of theoretical CS and ML.

Related discussion following a similar question I asked: https://news.ycombinator.com/item?id=18939913

Forgive my ignorance, I may not understand what the problem is, but I was under the impression there are numerous browsers, chrome, firefox, brave, etc

Why does the world need another one?

I'm really excited by the concept of modular neural networks

Ah very good points, thanks for the heads up! I’ll think about this a bit more

I was thinking about completing the MIT applied and pure math major course requirements via open courseware

Ah I see, I think I need to study this stuff a little more carefully

Great points, I think I may be overestimating the speed of Open Source development in my mind, leading to the mistaken assumption that all my time should be used rapidly building better tech. If that isn't the case, and there's bound to be a slow uptake on the OS side, it certainly seems prudent to shift my attention over to communicating and disseminating my work, perhaps through a paper.

They definitely ship code, and people seem to like them. I really like their model, the hacker culture, the holy crap we built a self driving car for <1k, but I don't know if they'll be a real contender in industry.

OP here, the only open source drug discovery library/framework I’ve seen is DeepChem https://github.com/deepchem/deepchem

I’d also love to hear the answer to this :)

This is a really interesting perspective, another HNer said something similar. I’ll spend some time noodling on this.

I’m highly interested in this, and in the capacity of biocomputing in general!

Awesome, I hadn’t come across Luca Cardelli’s work before, I’ll check this out! Thank you :)

This is an awesome detailed response from an informed perspective, thank you! I’ll check out the article.

Do you think that despite the high error resulting from the sheer complexity of those interactions, design tools would be useful to researchers? Or is it mostly just long shot proof of concepts with no practical purpose right now?

Hey thanks, I’ll check out the video! That seems super cool

Wow very cool. I’m actually a graduate student at Harvard getting my master’s in biology and CS, so this is right up my alley. I’m going to dive deeper into Serotiny and check out some of the awesome work you guys are doing. Do you offer internships for folks like me?

I’d heard about Asimov from their original work on Cello at MIT, but SBOL is news to me. I’ll check it out as well.

It sounds like this space is becoming pretty competitive, which is interesting.

My apologies, and thank you, your advice makes a lot of sense!

Ah of course, I'm a US citizen! I went to UCSD for undergrad, and am attending Harvard and Georgia Tech for my master's