Accidental Factors
It is a truth universally acknowledged that an airline in possession of an airplane must be in want of engines to make it go. Yet, somewhat surprisingly, they don’t really buy engines. Rolls-Royce were the notable innovator here in selling not an engine, but instead what they call power by the...
Accidental Factors
When we started building LLMs, we mostly focused on them knowing things. They had information encoded in their weights, and they could spit it out when given sufficient prompts. But an agent doesn’t just need to know things; it needs to combine several kinds of knowledge. A lot of that is still...
Diana Pfeil
Some of my clients are highly competent product and engineering organizations. They have a proven rhythm for building and shipping software. But when they start building AI or ML features for the first time, that rhythm necessarily gets disrupted. Their new process can feel chaotic, less...
Diana Pfeil
I’ve been working with two clients recently who are building recommender systems. (Think: recommending fitness classes based on people’s goals. Not a real client example, but you get the idea.) The instinct is to jump straight to building: What data do we have? What model should we try? I love...
Adam Scherlis
Epistemic status: whimsical Bees: a new unit of measurement for ML model size Talking about modern ML models inevitably leads to a bunch of hard-to-intuit large numbers, especially when it comes to parameter count. To address this, Lawrence Chan and I propose that we adopt a new,...
Adam Scherlis
As seen on Alignment Forum and LessWrong Alternate title: “Somewhat Contra Scott On Simulators”. Scott Alexander has a recent post up on large language models as simulators. I generally agree with Part I of the post, which advocates thinking about LLMs as simulators that can emulate a...
Martín Villalba
Does this situation sound familiar to you? You are a data scientist, you developed an ML model in Python (using PyTorch, TensorFlow, or something like that), and you'd like your users to interact with it, You would like to make either an API or a web interface to your model, Your model is...
blank
Introduction What This blog post is short article about my master thesis “Molecular Graph Learning in the Optimal Transport Geometry” done at ETH Zurich under the supervision of Prof. Thomas Hofmann (ETH), Dr. Octavian Ganea (MIT) and Dr. Gary Bécigneul (ETH) (10/10/2020). Parts of this work were...
Suresh Alse
When I was a kid, I really loved solving Where's Waldo. There were few books (it used to be called Where's Wally) in our school library on which I spent hours finding Waldo. For people who do not know what it is, basically Waldo - a unique character is hidden among hundreds of other characters and...
Suresh Alse
I have been meddling with google's deeplearn.js lately for fun. It is surprisingly good given how new the project is and it seems to have a sold roadmap. However it still lacks something like tf.layers and tf.contrib.layers which have many higher level functions that has made using tensorflow so...
Suresh Alse
With the rise in popularity of face recognition systems with deep learning and it's application in security/ authentication, it is important to make sure that it is not that easy to fool them. I recently finished the 4th course on deeplearning.ai where there is an assignment which asks us to build...
Suresh Alse
It has been a while since google released Tensorflow support for java. Even though it is still in its infancy, I feel like it has everything we need. Build computation graphs - check, run session and compute stuff - check, GPU support - check. Now if you have all the time in the world to reinvent...
Suresh Alse
Although I have worked on several deep learning projects in the past, I still consider myself to be a newbie in deep learning because of all the new things that keep coming up and it is so hard to keep up with all that. So, I decided to take part in "The 2017 Deep Learning Hackathon" by...