Facebook Can Read Photos πŸ–ΌοΈ

Big Blue has rolled out a tool called Rosetta that can scan photos for text, extract the text it finds, and then “understand” that text. πŸ‘οΈβ€πŸ—¨οΈ

This is huge as it means the platform can now increase accessibility by reading photos, it can pull out information from photos of menus and street signs, and it can monitor memes and images for destructive written content. And those are just a few examples I’m sure. ♾️

Personally, I’m interested to see how this impacts Facebook’s text content in ad image guidelines. It used to reject any ad that contained more than 20% text based on image size (but used a weird grid-based measuring system). Then it moved to an approach where the more text your image contain the narrower it’s delivery/reach. Facebook’s reason was always that “users preferred images with little to no text”, but I always figured it was more about their inability to automate filtering for content. Users don’t appear to have any issues with text overlays when it comes to organic content. πŸ–ΌοΈ

Their post has a bunch of technical details if you want to nerd out. πŸ€“

Src: Facebook

ELMo Really Does Know His Words πŸ‘Ή

I’m super interested in the world of NLP (natural language processing), so the news that performance increased dramatically with ELMo piqued my interest. πŸ’‘

The biggest benefit in my eyes is that this method doesn’t require labeled data, which means the world of written word is our oyster. 🐚

Yeah, yeah, word embeddings don’t require labeled data either. ELMo can also learn word meanings at a higher level, which I think means it will have far more impact and a wider range of applications. πŸ“Ά

ELMo, for example, improves on word embeddings by incorporating more context, looking at language on a scale of sentences rather than words.

Our cuddly, red muppet still picks up the biases we embed in our writings though. So plenty more work to be done. πŸ› 

Src: Wired

(Compute) Size Doesn’t Matter πŸ“

Fast.ai was recently part of a team that set some new speed benchmarks on the ImageNet image recognition data set. Why is this noteworthy? Because they did it on an AWS instance that cost $40 total. πŸ…

We entered this competition because we wanted to show that you don’t have to have huge resources to be at the cutting edge of AI research, and we were quite successful in doing so. We particularly liked the headline from The Verge: β€œAn AI speed test shows clever coders can still beat tech giants like Google and Intel.”

Jeremy Howard

AI has a mystique about it that makes it seem like it’s only for uber-tech nerds that love math and have access to the biggest computers, but that’s not true. Yes it’s technical, but it’s not impossible. And there are plenty of resources to help those curious get started. It is not nearly as difficult as it seems. We just have a lot of language and storytelling baggage attached to it.Β βš—οΈ

Very few of the interesting ideas we use today were created thanks to people with the biggest computers. And today, anyone can access massive compute infrastructure on demand, and pay for just what they need. Making deep learning more accessible has a far higher impact than focusing on enabling the largest organizations..

Jeremy Howard

Src: fast.ai

The Deciding Tree 🌳

This is a really great description of decision trees with some lovely visuals. It also continues a good overview of overfitting. πŸ‘Œ

Decision trees might not seem as sexy as other algorithmic approaches, but it’s hard to argue with the results. It also strikes me how similar this process seems to the way humans approach a lot of experience-based decision making. βœ”οΈ

The basics: decision trees are flowcharts derived from data. ⏹➑️⏺

Src: Data Science and Robots Blog

When Gradients Explode (or Vanish) πŸ’₯

This is a nice quick read on how to combat exploding or vanishing gradients, a problem that wreak havoc on your deep learning model. πŸ‘Ή

My TL;DR:

  • Exploding gradient? Use gradient clipping. It sets a ceiling on your gradient but keeps the direction. βœ‚οΈ
  • Vanishing gradient? If you’re using an RNN, use an LSTM. βœ”οΈ

Src: Learn.Love.AI.

Dataset Database πŸ—„

What does ML want? Data! When does it want it? All the time! But specifically, whenever you are going to train, test, and deploy a model. Where do you get this data? I’m glad you asked! πŸ˜ƒ

Here is a collection of datasets I’ve come across. I’ll update it as I find more. βž•

Computer Vision

Autonomous Vehicles

Do you feel the need, the need for more data? Check out this list of 50 datasets from Gengo.

Updated: 06.30.18

Unbiased Faces πŸ‘ΆπŸ»πŸ‘©πŸ½πŸ‘΄πŸΏ

IBM will be releasing a data set of faces across all ethnicities, genders, and ages to both avoid bias in future facial recognition systems and test existing systems for bias. Simply put, this is awesome. πŸ™Œ

It’s also interesting to see how ethics, fairness, and openness are being used as positive differentiators by major competitors in this new tech race. πŸƒβ€β™€οΈπŸƒβ€β™‚οΈ

Src: Axios