Archive

We’re having a proper “news” issue this week! Let’s look at the machine learning news!

The Latest Fashion

• People are trying out GPT-4, and it’s pretty fun to play around with!
• This tool helps you benchmark your Pytorch DataLoaders.
• Pytorch 2.0 is the fastest Pytorch yet, and even more Pythonic (whatever that means)!

Got this from a friend? Subscribe here!

it’s been a week! I have been polishing my new projects to give them their best, but first, some machine learning!

The Latest Fashion

• This ML training handbook by Google is quite handy, albeit not the newest.
• Tips for structuring your research group’s Python packages
• Finally, a proper stable diffusion fork for Macs!

Got this from a friend? Subscribe here!

I was a bit under the weather this week, but next week we’re finally releasing my MOOC segment on deep learning! Let’s dive into some other machine learning first!

The Latest Fashion

• This paper predicts images we are thinking of from brain scans! Fascinating but terrifying.
• Hackathon winner creates a dark ship detector with stable diffusion and GANs to detect illegal over-fishing
• These animations for neural network education are amazing!

***Thanks to David for sending in the brain scan paper!***

How are you doing today? We’ve got some fresh, hot machine learning right from the source today!

The Latest Fashion

• CNet ran a bunch of AI-generated articles and found errors in more than 50% in hindsight
• Pyvista looks really nice for 3D visualization in Python
• You can write GPT from scratch in 60 lines

Got this from a friend? Subscribe here!

what a week! I’ve been working really hard to finish up my content for the ECMWF MOOC and wrote a massive piece on “quick wins” to make machine learning models in science. Let’s look at some other machine learning first, though!

The Latest Fashion

• You too can train Transformers at scale like Microsoft trained Bing
• How to achieve success in an ML PhD? Just know stuff (maybe)
• Arxiv teamed up with Hugging Face to bring implementation right to you on Arxiv

Got this from a friend? Subscribe here!

What a week of announcements. Announcements and failures! Often a theme emerges when I collect my favourite links, and this issue sure is filled with learnings and failures. Let’s dive right in!

The Latest Fashion

• Google lost $100 billion in stock value over factual mistakes in a half-baked chatGPT competitor announcement
• In a terrifying display, developers built a police sketch app on top of DALL-E 2, enforcing unethical biases
• “A Categorical Archive of ChatGPT Failures” documents problems even from the best model we currently have

Got this from a friend? Subscribe here!

the trial month of 2023 is over. How did it go? I’m neither entirely disappointed nor jumping with joy. But let’s jump right into some machine learning instead!

The Latest Fashion

• There’s a new Coursera by Deepmind on the mathematics of machine learning
• Looks like the self-driving Tesla video was fudged at request of Elon Musk, reported by Bloomberg
• Huggingface debuted their own machine learning competition platform with “AI or Not”

Got this from a friend? Subscribe here!

what a week, it looks like tech is further imploding. Let’s look at some machine learning instead!

The Latest Fashion

• Stability AI is being sued by artists over Stable Diffusion publicly.
• This book about Understanding Deep Learning goes deep.
• This “course” about learning prompt engineering was really insightful.

Got this from a friend? Subscribe here!

it’s been a week… I am still struggling with burnout, but that won’t keep us from an awesome issue packed with machine learning goodies. Let’s dive right in!

The Latest Fashion

• Quincy Larson, the person behind freecodecamp wrote a book about learning to code and getting a job as a dev. And it’s free!
• If you’re into Python, you know the GIL is the bane of many performance enthusiasts. This PEP suggests making it optional and asks for comments.
• This list has chatGPT prompts and uses I haven’t seen before, which is pretty neat!

Got this from a friend? Subscribe here!

some really nice links for you today. From reviews to embeddings to “is it AI or is it art?!”. Let’s dive right in!

The Latest Fashion

• I’m a sucker for annual review posts, so this collection of reviews in AI was a lovely find
• Enrich knowledge of data embeddings with fancy embedded background data by Gael and folks!
• The NeurIPS talks are online and freely available now

Got this from a friend? Subscribe here!

the first week of 2023 is finding its end. I got a late Christmas present and we’re now over 1000 subscribers in this little newsletter! Welcome everyone! Let’s look at some machine learning.

The Latest Fashion

• NeRF Studio is an easy way to play around with neural radiance fields
• Putting machine learning into production seems never easy, this interview study gives a nice overview of making it suck a little less.
• Want inspiration for AI art? Lexica is a searchable gallery of generated images! (Possibly NSFW)

Got this from a friend? Subscribe here!

I had a problem with my email distributor last week. Please check your spam folder. It looks like only 10% of you actually got the last email! But with this email, we should be back on track! I hope you had a lovely holiday season! 2023 is almost here, so let’s hit the ground running with some fascinating machine learning!

The Latest Fashion

• Everyone is publishing their 2022 reviews, and I quite enjoyed this thread on ML papers in 2022

• Learn about transformers from Stanford in CS25 for free

• There’s an entire Crash Course on data literacy for free as well, which is fantastic!

Got this from a friend? Subscribe here!

it’s been a while! I have burnt out, but let’s look at some machine learning, before I talk about that!

The Latest Fashion

• This book is fascinating: Parables of AI in/from the majority world

• I have been reading about git etiquette a bit, so this article about The Perfect Commit struck a chord.

• Deep neural nets are notorious for being overly confident. Fortuna tries to introduce some proper uncertainty quantification.

Got this from a friend? Subscribe here!

the year is almost over, and SO MUCH is happening. Check out the workshop and my giveaway! But before that, some machine learning!

The Latest Fashion

• Do you look at Pytorch tensors to figure out what’s wrong? Try lovely-tensors to get an intuitive overview instead!
• I have been reading more about git recently. This Idiot proof git workflow was quite interesting to follow!
• I found this intersectional AI toolkit quite fascinating! A good resource to keep around and make AI more equitable.

Got this from a friend? Subscribe here!

lots of awesome things are happening here, I have a workshop coming up with some awesome speakers and much more! But let’s start with some machine learning!

The Latest Fashion

• Parsing PDFs is a holy grail in business ML, Parsr tries to approach this problem quite successfully.
• AI is this moving goalpost, but how about a roadmap instead outlining steps towards general artificial intelligence?
• This library of learned optimisers for neural networks seems quite interesting.

Got this from a friend? Subscribe here!

what an eventful week. Twitter seems to be dying slowly, and winter has eventually arrived. Let’s warm our hearts with some machine learning!

The Latest Fashion

• Facebook created a “scientific AI” called Galactica, and it was terrible and pulled after only 3 days.
• Quantus is an explainable AI kit that uses different XAI techniques.
• Notion has developed a writing AI, and you can sign up for the Beta Waitlist now!

Got this from a friend? Subscribe here!

it’s a lovely day and the weekend is near. Let’s enjoy some machine learning together!

The Latest Fashion

• Stable Diffusion has made quite the stride in just a few months. This Twitter thread gives a nice overview.
• Alternatives to Github Copilot are rare, for now. Huggingface is inviting AI researchers to contribute to BigCode.
• Difftastic is a diff program that understands syntax!

Got this from a friend? Subscribe here!

I’m unfortunately still not doing well, so we’ll have a shorter issue today. So let’s enjoy some machine learning!

The Latest Fashion

• The next level in using Stable Diffusion is installing a WebGUI instead of using Huggingface spaces and this InvokeAI fork is pretty comprehensive and open source!
• Writing tests for machine learning can feel daunting. This article makes writing robust tests for data and ML more accessible!
• This AI4Code Kaggle challenge is very nice to read through (and there’s 7 days left).

Got this from a friend? Subscribe here!

your eyes do not deceive you; this is a new issue on an actual Friday! I’m sick at home, so let’s cheer up with some machine learning!

The Latest Fashion

• This website explains any part of any paper that you highlight and allows follow-up questions.
• The Follower connects open camera data with AI to find live footage of influencers in the wild. Yes, it’s as creepy as it feels.
• I’m low-key obsessed with Stable Diffusion; here is a collection of open prompts.

Got this from a friend? Subscribe here!

this week had more deadlines than days and I’m severely jetlagged. However, this is the 100th issue of this newsletter! How could I not share more awesome things?! Let’s dive into some machine learning!

The Latest Fashion

• I love a good “Awesome List” and this one is on Diffusion Models!
• Scikit-learn and huggingface join forces to serve classical ML models
• Registrations opened for a new MOOC for machine learning in weather & climate prediction

Got this from a friend? Subscribe here!

if you go back and analyse how many newsletters were late and which ones mention that I’m stressed, I think there’s some overlap. But regardless, there has been some amazing machine learning going one, so let’s check those out for a break!

Also welcome to all those 100s new subscribers! We’re over 850 now!

The Latest Fashion

• The State of AI report for 2022 just dropped.
• Selecting features in data science is important. LOFO-importance for feature selection automates this selection by leaving a feature out and retraining.
• Kaggle published their data from the 2022 ML and data science survey.

I’m back in the office playing catch-up. The last quarter of the year has started, and I feel behind on everything. I know I tend to do too much, but is it finally catching up to me? Anyways, let’s catch up on some awesome machine learning!

The Latest Fashion

• Can AI discover new scientific insight? Well, Deepmind just published a paper discovering new efficient ways to multiply matrixes that are larger than 2x2!
• I love the illustrated guide to transformers. Here’s the new illustrated guide to stable diffusion.
• You’ve just learned about stable diffusion? How about using it to generate whole videos. Incredible.

Got this from a friend? Subscribe here!

it’s been a while! My vacation made me forget the time, as it should, so I completely missed last week. Apologies! But I’m back at my desk now. Full of energy. Ready to take on the world of machine learning! So let’s dive in.

The Latest Fashion

• You know the advice to not “copy and paste commands” because it’s unsafe and you still always do? Shellfirm tries to secure your shell for risky command patterns like deleting everything with rm -rf *
• This article uses language as a means to explain machine learning generalization with neat illustrations!
• Gaussian Processes sometimes seem to be on the fringes of modern machine learning, but they’re incredibly useful.

Got this from a friend? Subscribe here!

I’m still on vacation in Mozambique. Went for my first dives and it’s a blast. But that won’t keep us from some awesome machine learning! Masks on, regulators in, let’s dive into it!

The Latest Fashion

• Quantus is an explainable AI library that looks very promising with different metrics across different factors of XAI
• The Scipy 2022 Machine Learning & Data Science talks are on Youtube!
• Ever wanted to learn CUDA? You could try these GPU puzzles to get started.

Got this from a friend? Subscribe here!

I just emerged on a beautiful beach in Mozambique after 3 days of travelling, apologies for the delay! The next few newsletter issues will be reduced to still share awesome things with you, while honoring that I am on vacation. But I genuinely enjoy writing these issues too much to skip them completely, so let’s dive into some machine learning!

The Latest Fashion

• How about a $250,000 USD cash grant for your AI-native product idea to kick things off? The AI grant is by some awesome people for awesome people so check it out!
• This Hacker News thread on the proper way to get into ML in 2022 was fun to browse
• How about giving your torch tensor dimensions names instead of guessing the index?

Got this from a friend? Subscribe here!

I’m on my way home from Euroscipy and it was a blast. But that won’t stop us from awesome machine learning, right? Let’s dive right in!

The Latest Fashion

• Wanted to use Imagen or Dall-E 2 but not an AI influencer? The Stable Diffusion release enables anyone to try state-of-the-art text-to-image diffusion models (even in Colab!).
• Reproduce recent papers in the paperswithcode reproducibility challenge.
• Dreamworks open-sourced their rendering engine for you to play around with.

Got this from a friend? Subscribe here!

it’s been 2 years of this newsletter! 🥳

In these anniversary issues, I like to go through the last year of writing this weekly newsletter and see what everyone liked. So, in case you missed these awesome links, this is what everyone else enjoyed!

The Latest Fashion

• The Explainer Dashboard for interactive exploration of machine learning models
• Messing up code is easy, and https://dangitgit.com to find the right command to untangle the mess
• Everyone loved the idea of easier matplotlib subplots with mosaics.

finally, I’m coping with the heat. I’m back to writing regularly and contributing at work and in my projects. Lovely! So let’s look at some machine learning!

The Latest Fashion

• This collection of over 200 machine learning flashcards is really neat.
• Never Trust A Number – was a fascinating piece of insight.
• Chip Huyen wrote an intro to streaming data for data scientists.

Got this from a friend? Subscribe here!

it’s been a rough week over here. But it feels like I’m just recovering in time to share some awesome machine learning with you! Let’s dive in!

The Latest Fashion

• This is a fantastic comparison of state-of-the-art computer vision models.
• Andrew Ng has a new machine learning course, updating the classic Coursera course everyone took.
• For production-grade graphs of neural networks, I love PlotNeuralNet.

Got this from a friend? Subscribe here!

it’s finally cooling down over here. The sun is nice and all, but above 20°C, my brain just stops working. But that shouldn’t stop us from finding some awesome machine learning and some Python this week! Let’s dive right in!

The Latest Fashion

• The creator of XKCD started playing around with DALL-E 2 exploring Pokemon cards throughout the ages.
• Matplotlib has a Mosaic API that seems really cool for subplots I didn’t know about!
• Truss promises to serve ML models without boilerplate. Enticing!

Got this from a friend? Subscribe here!

It’s been a good week over here. There are now 600+ people reading these weekly emails, which is incredible. Hope you have a great start into the weekend. Now for some machine learning!

The Latest Fashion

• Version 5 of the Practical Deep Learning for Coders course just dropped.
• I guess today is a Jeremy Howard issue since his guide to matrix calculus for deep learning is really great.
• This repo has PyTorch code, models, and pre-trained weights for all your favourite deep learning vision architectures.

Got this from a friend? Subscribe here!

it’s my birthday today! 🎂 So, before I’m off to celebrate, let’s look at some awesome machine learning!

The Latest Fashion

• Last week I shared the Dall-E 2 prompt book. Now you can sign up to the open Dall-E 2 beta.
• Most practitioners know tabular data is for xgboost. This new paper by Gael Varoquaux et al backs this up.
• Meta of all places launches a tool Wikipedia is using for fact-checking. It’s so weird, I lapped up the article about it.

Got this from a friend? Subscribe here!

I’m running late! I got carried away building a new website. But that shouldn’t keep us from this awesome machine learning on a Friday!

Also, we’re over 555 people now! Incredible! Big Hello to all these new nerds as well. Enjoy the links!

The Latest Fashion

• Normally, I’m tired of new large language models, but the BLOOM big science model was created collaboratively by over 1000 researchers in 59 languages. That’s pretty neat.

• Ever mess up in git and spiral down a rabbit hole of StackOverflow answers? Dangit, Git?! is a nice overview of the most common fixes you may need.

• Playing with DALL-E and imagen can be tricky. This DALL-E 2 prompt book teaches you how to get better outputs by thoughtful prompt design.

we’re now over 500 people on this niche newsletter! Incredible! Welcome to all the new machine learning enthusiasts. Hope you find something new! So let’s dive right into some machine learning!

The Latest Fashion

• Quickly deploy a dashboard with extensive explainability for your ML models.
• Data Structures and Algorithms is easily the most impactful class in computer science class I have taken, here is a fantastic study guide.
• There’s a new $1000 monthly Kaggle award when you replicate an ML research paper.

Got this forwarded by a friend? Subscribe here!

it's been a mixed bag of a week. The weather is great and I made fantastic progress, but the state of the world is still shocking. Anyways, let's look at some machine learning.

The Latest Fashion

• Pen and Paper Exercises in Machine Learning just dropped. It’s fairly basic with a focus on math instead of applied ML or models, but insightful in that regard and great for preparation for technical interviews.

• Google Brain have published a paper on their reinforcement learning efforts to aide designing chips for the latest generation of TPU chips.

• Still wonder what these transformers are all about? Here’s an opinionated guide to transformers, from basics to implementation and theory.

My Current Obsession

I went viral this week and put a massive amount of effort into creating content. I would say it already paid off. We are now 400 subscribers strong. Welcome to all the new folks! Let’s dive into some machine learning awesomeness!

The Latest Fashion

• Jeremy Howard wrote an excellent overview of how he reached the top 1 on a current kaggle competition with notebooks and videos!

• Want faster vector operations? Bolt compresses real-valued vectors and speeds up computation 10x.

• I shared prettymaps before, and here’s an interactive Streamlit app for easy usage. _{^{(tag @jesperdramsch on Twitter if you post some!)}}

Got this forwarded by a friend? Subscribe here!

the economy is taking a nose-dive, so let’s make sure we can do an extra-good job and be un-fireable for the foreseeable future with these awesome papers and libraries!

The Latest Fashion

• I enjoyed this paper about retrieving a meteorite fall with drones and machine learning!

• Regex is difficult and a bit old. Rulex tries to fix what wasn’t great about Regex and transpiles to Regex for maximum compatibility.

• Do you need data for tests, but bundling it in a Github repo is bad? Try Pooch to retrieve data for you!

My Current Obsession

I got really inspired by all the projects people presented at the ITU this week. So let’s carry over this excitement and dive right in:

The Latest Fashion

• Validating deep learning models can be complicated. Deepchecks provides a full suite (even on computer vision and tabular tasks) of checks to run against your system, including correlation and drift checks! Here’s the quickstart notebook.
• Lying with statistics is dangerous. But here are 6 ways people discredit valid statistical results and data science results without an actual basis.
• Testing Python code with production data can be a privacy nightmare. Faker is a package that generates believable but fake data for all your fake data needs.

My Current Obsession

I hope my Americans and Brits had a nice short week! I had five full days to collect some fantastic machine learning for you! Let’s go:

The Latest Fashion

• Computers that create realistic images from a text prompt seems like magic. Naturally, the new imagen is taking Twitter by storm, and there’s a Pytorch implementation.

• A new standardized metric library is on the block. From the forges of Huggingface, no less!

• Thought about trying Observable? Here’s a neat plot cheat sheet to get you started.

My Current Obsession

it was a 3-day week over here in Germany. I did some spring cleaning physically and digitally. So let’s explore some squeaky-clean machine learning awesomeness:

The Latest Fashion

• This AI learns traffic patterns from camera footage, making traffic jams a distant memory from the past.

• Models don’t always have to get bigger and badder, try the Efficient Deep Learning book instead.

• Aren’t we all curious why Deepmind loves Jax so much? Well here’s a Jax 101 tutorial.

My Current Obsession

I had a fairly frustrating week, dealing with things breaking and some migraines from the rapid weather changes. But that won’t keep us from some awesome machine learning, now does it? Here we go!

Also check out the new segment on data stories!

The Latest Fashion

• Deepmind was inspired by the successes of large language models lately, so they extended this innovation to reinforcement learning, introducing a general agent that can perform many different tasks out of the box.
• Pytorch is now ready to train on Mac M1 chipsets.
• Need a data visualization but the standard ones don’t quite fit? The Data Viz Project collects and lists visualization types for you to choose from.

the weather over here has been incredible this week, so I have been going out as much as possible. Additionally, I have started writing more again, which feels great. But let’s dive into our weekly machine learning:

The Latest Fashion

• Setting up Cuda on new architecture often is a nightmare, and cog is trying to solve this with pre-built containers for machine learning training
• Inspect intermediate layers of your Pytorch models with a little ML surgery without modifying the model code.
• Ever work with tabular data, this paper has done the work in comparing all machine learning models for your convenience.

My Current Obsession

coming live from the UK, I bring to you some fun machine learning!

The Latest Fashion

• Python in the browser? Not new. Including pandas, numpy or even folium? That’s PyScript and very new and exciting!

• Make pretty 3D visualizations in a oneliner from your keras model architecture with visualkeras.

• Google published a newer bigger Large Language Model. Their analysis of which improvements come from sheer size is insightful.

My Current Obsession

it’s been a long week back in the office after my week off. But I’m glad I had a few teleworking days saved up to get an easier transition. Regardless, let’s look at some learning machines!

The Latest Fashion

• I used to code telegram bots to send me ML training statistics on the go, with mlnotify you can do this in a single callback.
• This glossary of statistics jargon is a fantastic resource from Cassie Kozyrkov
• A new notebook competition for visualizations and some machine learning on Earth observation data was launched by EUMETSAT.

My Current Obsession

I’ve had a nice nature fix this week exploring the forests and hills around my home. But that shouldn’t keep us from some awesome machine learning!

The Latest Fashion

• Andrew Ng announced that the latest iteration of the Machine Learning Specialization, the course every ML practitioner took, is launching soon.

• The Stanford AI Index for 2022 was published with some interesting insights. Did you know the cost to train an image classifier is down 64%?

• Machine learning is a dual technology, yet, I was still surprised how AI drug discovery is turned into a bioweapon.

My Current Obsession

it was a nice short week here in Germany with a 4-day weekend coming in strong. Now, if just the clouds would disperse. But that doesn’t keep us from some awesome machine learning!

The Latest Fashion

• This Machine Learning Compendium is still in the making, but I’m excited about where it’s headed.

• Ever wonder if you could visually link Jupyter cells? I have, and PyFlow seems like an interesting attempt at this!

• Smaller ML models are important on the edge and in production. FasterAI is a library to help you accomplish smaller neural nets.

My Current Obsession

this week just blasted by me, barely enough time to sit down for a minute. So let’s dive into some recreational machine learning!

The Latest Fashion

• When you’re teaching machine learning, this Hugging Face 🤗  educational toolkit is great for understanding NLP
• Investigate your data with this clustering library for gaining insights.
• Remove personally identifiable data from your data set with Spacy’s scrubadub

My Current Obsession

isn’t Spring nice? The better weather and light outside is genuinely great for my mood. So are these machine learning links:

The Latest Fashion

• Pick up a free “draft” copy and all code of the book Probabilistic Machine Learning.

• This Twitter Thread by Aurélien Geron goes into his favourite parts of Python 3.x

• Midjourney is the latest image generation experiment, so try out the beta!

My Current Obsession

the weather outside is amazing, perfect timing for the weekend. But first let’s check out some awesome machine learning and Python links!

The Latest Fashion

• Bringing ConvNets to the 2020s went viral and now the code is released too!
• Automate your EDA and visualize your pandas DataFrames automatically with lux
• Explainable AI is all the rage, here’s a gentle introduction to Shapley values.

My Current Obsession

I’m back! Apologies for the one-week hiatus, but the anxiety around the current world got the better of me causing some health issues. Regardless, we have some great links (and things that might help if you too are suffering). Let’s do some machine learning!

The Latest Fashion

• This interactive exploration of transformer attention really helps understand the intricacies of transformers on language!

• TorchGeo is a Pytorch extension with datasets, transformations, and models for geospatial data

• The Deepmind podcast with Hannah Fry has started its second season!

My Current Obsession