Inmos has directly and indirectly led to many British companies, including Graphcore:

https://www.economist.com/britain/2011/08/06/how-the-west-wa...

https://www.wired.co.uk/article/graphcore-ai-intelligence-pr...

Myrtle has a similar series that includes discussion about batch normalisation: https://myrtle.ai/learn/how-to-train-your-resnet/

https://twitter.com/dcpage3/status/1141700299071066112

Disclaimer: I work at Myrtle!

I looked at it, and it is very good: good baselines, explanations, visualizations and going deeper than a typical "it is a black box but if you copy & paste it will work".

I was surprised by the nice network vis (and I did dive into the subject before: https://medium.com/inbrowserai/simple-diagrams-of-convoluted...). The only thing that looks clunky is the text logs for training (a shameless plug: https://github.com/stared/livelossplot).

You should check out our blog post related to finding the optimal learning rate, batch size, and momentum setting:

https://www.myrtle.ai/2018/09/24/how-to-train-your-resnet-5/

Security is more than just confidentiality - availability is a factor too.

Standard Chartered has over 3 million lines of Haskell code and Facebook uses it to fight spam - there's definitely more than you think out there :-)

http://hauptwerk.blogspot.co.uk/2017/04/four-openings-for-ha...

https://code.facebook.com/posts/745068642270222/fighting-spa...

> Standard Chartered has over 3 million lines of Haskell code

Not exactly, they have their own closed source fork of GHC, which is strictly evaluated. Given that the codebase is proprietary it's unknown what other differences there are beyond having dumped lazy evaluation. It's a Haskell-like language, but far different than the Haskell that the public has access to.

I don't think a spam filter would be the first thing you'd prove correct if you wanted to go down that road..

Third year CS Major interested in solving complex problems via machine learning/AI!

Location: CA, USA

Remote: No

Willing to relocate: Yes

Technologies: Haskell, Go, Java, C

Résumé/CV: https://samgd.com/files/sam_davis_cv.pdf

Email: [email protected]

sed 's/\s*$//g'

Funnily, that doesn't work as expected on OS X due to a rather old version of sed installed by default that doesn't support \s. Try the following instead:

  sed 's/[[:blank:]]*$//g'