Brainsteam

Content tagged with "Phd"

Published on by

#phd #personal

PhD Progress Update 3/7/22: Another 2000 words this week - progress appears slower because I spent most of the tail end of this week preparing a stand alone manuscript of chapter 9 for submission to a journal. Hoping to complete a 1st draft of Chapter 2 this week.

Published on by

#phd #personal

Weekly PhD progress: 2 more 1st draft chapters complete, only one more “main” chapter remains and then moving on to background, intro, conclusion etc. With around 11 weeks left, ‘feeling confident’ is a stretch but things are on track.

Published on by

#phd #personal

Another day of PhD writing in the sun. Aiming for 1000 words today ahead of my now weekly progress report post tonight. Energy provided by a local coffee roaster HICS coffee

Published on by

#phd

Another rainy sunday, another ~1000 words written on the thesis. I’m tracking my progress in a spreadsheet. Very nearly built a web app to track it but decided the half day I’d need to build that was probably better spent actually writing… #phd #thesis

Here be Dragons: Deep Learning Reproducibility

Published on by

#machine-learning #work #phd

A harrowing tale of trying to solve the impossible and failing. Episode 5 in this year’s run at the #100DaysToOffload challenge. See the full series here

Photo by Tim Mossholder from Pexels

Photo by Tim Mossholder from Pexels

That’s So Random: Randomness in Machine Learning

Training Machine Learning and in particular Deep Learning models generally involves a lot of random number generation. If we’re training a supervised classifier or regressor, we tend to randomly split our annotated data training set from our test set. Also, if you are training a new neural network it is fairly standard practice to randomly initialize the connections between the neurons (the weights) with a random number (here’s why).

Read more...

Reproducing 'ancient' experiments with Pytorch inside docker

Published on by

#machine-learning #python #ai #devops #mlops #work #phd #open source

A beige analog compass by Ylanite Koppens

A beige analog compass by Ylanite Koppens

Introduction

Open machine learning research is undergoing something of a reproducibiltiy crisis. In fairness it’s not usually the authors’ fault - or at least not entirely. We’re a fickle industry and the tools and frameworks were ‘in vogue’ and state of the art a couple of years ago are now obsolete. Furthermore, academics and open source contributors are under no obligation to keep their code up to date. It is often left up to the reproducer to figure out how to breathe life back into older work.

Read more...

Spacy Link or “How not to keep downloading the same files over and over”

Published on by

#nlp #python #work #phd

If you’re a frequent user of spacy and virtualenv you might well be all too familiar with the following:

python -m spacy download en_core_web_lg
Collecting en_core_web_lg==2.0.0 from https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-2.0.0/en_core_web_lg-2.0.0.tar.gz#egg=en_core_web_lg==2.0.0
Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-2.0.0/en_core_web_lg-2.0.0.tar.gz (852.3MB)
5% |█▉ | 49.8MB 11.5MB/s eta 0:01:10

If you’re lucky and you have a decent internet connection then great, if not it’s time to make a cup of tea.

Read more...

Uploading HUGE files to Gitea

Published on by

#devops #docker #git #lfs #PhD #Work

I recently stumbled upon and fell in love with Gitea – a lightweight self-hosted Github and Gitlab alternative written in the Go programming language. One of my favourite things about it – other than the speed and efficiency that mean you can even run it on a raspberry pi – is the built in LFS support. For the unfamiliar, LFS is a protocol initially introduced by GitHub that allows users to version control large binary files – something that Git is traditionally pretty poor at.

Read more...