desku

I’d doubt it’s even that complicated, a few if-statements would be enough.

How is £$165/year not nutty? That is more than I pay per year for Amazon Prime, Spotify, Disney+, MLB or The Economist. All for basically being able to just write text in a browser and store it.

Ah yes, can't wait for a 250 page book that should've been a blog post full of high-level content that you can easily find online, padded out with tenuously linked anecdotes.

And how does this company make money? Harvesting and selling all of my data?

I’ve been interested in making an open source version of the Seeing AI app (https://www.microsoft.com/en-us/ai/seeing-ai) with a more limited scope. Contact me if this sounds inline with your ideas.

Can’t figure out a way to contact you from your About section —- I’m a ML engineer with an early interest in algorithmic trading, would be interested in brainstorming ideas.

I’m looking for collaborators for re-implementing “modern” machine learning and deep learning models/papers. Modern is in quotes as I’d actually like to focus less on the super recent, and more on those around ~5 years old, as the compute required is usually more feasible. As well as the implementation (which will be open sourced, well written and documented), I’d also like https://distill.pub/ style articles to go along with the implementations.

I’d also like to get into algorithmic trading, but this is something I’m at the very early stages of researching into.

If any of that sounds interesting, contact details are in my profile.

Nobody should feel alone at Christmas. If anyone needs someone to talk to, about anything at all, feel free to contact me. Details in my profile.

This looks great. Is it possible to get this as an RSS feed instead of an e-mail newsletter?

Here's a paper on how BERT (a large Transformer model trained using self-supervised learning) implicitly learns the traditional NLP pipeline: https://arxiv.org/abs/1905.05950

Is there actually a new PyTorch version? I can't seem to find anything about it online.

What niche libraries do you think PyTorch is lacking? Do you have some examples of ones that exist in Tensorflow with no PyTorch equivalent?

I very much enjoyed, and would recommend, White Noise and Mao II.

As for adjacent authors, I think I'd probably list: David Foster Wallace, Pynchon, Franzen and Roth.

The link to the .pdf seems to be broken though.

I'm not sure how to interpret the argument of the article or the results in the appendix here.

The first table shows AdamW having the best results, which follows the argument of the article. However, the following three tables all have plain Adam producing the best results.

The way the article is written it seems to be championing AdamW, but the results just seem to conclude that AMSGrad is bad and Adam is the best with AdamW having negligible performance increase over Adam in a single task.

It's probably domain/industry/company dependent, but the vast majority (>90%) of NLP work I do nowadays is sequence-to-sequence models.

I actually found this to be one of the best explanations on this topic I've read. Fully recommend the author's book too.

Also recommend this as it follows it/is an alternative: https://arxiv.org/abs/1703.01619

gameaibook.org

It's bloat due to 'introns' (useless statements that don't effect the output, like x = x * 1). And yes, just adding a fitness function to shorten program length isn't optimal. I've found it easier to evolve successful programs (letting the bloat happen) and then keep removing statements from correctly generated programs whilst checking if the output is the same. Probably not optimal either but I feel like it gives better results.

I don't think it'll ever be finished.

I get this too. Haven't been able to get references to work for a single paper yet.

I'd argue that's exactly what computer science is.

If you're into AI/ML: Import AI and The Wild Week in AI.

MIT had a short, week-long 'Intro to Deep Learning' course that had some labs in Tensorflow.

http://introtodeeplearning.com/

I believe there's bindings for: C++, Java, Rust, Haskell and Go.