David Sweet, author of “Tuning Up: From A/B testing to Bayesian optimization”, introduces Dan and Chris to system tuning, and takes them from A/B testing to response surface methodology, contextual bandit, and finally bayesian optimization. Along the way, we get fascinating insights into recommender systems and high-frequency trading!
SpeechBrain is an open-source and all-in-one speech toolkit based on PyTorch.
The goal is to create a single, flexible, and user-friendly toolkit that can be used to easily develop state-of-the-art speech technologies, including systems for speech recognition, speaker recognition, speech enhancement, multi-microphone signal processing and many others.
Currently in beta.
Our Slack community wanted to hear about AI-driven drug discovery, and we listened. Abraham Heifets from Atomwise joins us for a fascinating deep dive into the intersection of deep learning models and molecule binding. He describes how these methods work and how they are beginning to help create drugs for “undruggable” diseases!
If you’re adventurous and you want to learn to distinguish between couch #1 and couch #2 (i.e. 2 meters apart), it is the most robust when you switch locations and train in turn. E.g. first in Spot A, then in Spot B then start again with A. Doing this in spot A, then spot B and then immediately using “predict” will yield spot B as an answer usually. No worries, the effect of this temporal overfitting disappears over time. And, in fact, this is only a real concern for the very short distances. Just take a sample after some time in both locations and it should become very robust.
In this Fully-Connected episode, Chris and Daniel discuss low code / no code development, GPU jargon, plus more data leakage issues. They also share some really cool new learning opportunities for leveling up your AI/ML game!
Hamza Tahir on HackerNoon:
By now, chances are you’ve read the famous paper about hidden technical debt by Sculley et al. from 2015. As a field, we have accepted that the actual share of Machine Learning is only a fraction of the work going into successful ML projects. The resulting complexity, especially in the transition to “live” environments, lead to large amounts of failed ML projects never reaching production.
Elad Walach of Aidoc joins Chris to talk about the use of AI for medical imaging interpretation. Starting with the world’s largest annotated training data set of medical images, Aidoc is the radiologist’s best friend, helping the doctor to interpret imagery faster, more accurately, and improving the imaging workflow along the way. Elad’s vision for the transformative future of AI in medicine clearly soothes Chris’s concern about managing his aging body in the years to come. ;-)
This is an exciting development that brings Elixir into areas it hasn’t been used before. We also talk about what this means for Elixir and the community going forward. A must listen!
Queue up this episode and/or stay tuned for an upcoming episode of The Changelog where we’ll sit down with José after his LambdaDays demo to unpack things even more.
John Myers of Gretel puts on his apron and rolls up his sleeves to show Dan and Chris how to cook up some synthetic data for automated data labeling, differential privacy, and other purposes. His military and intelligence community background give him an interesting perspective that piqued the interest of our intrepid hosts.
Daniel and Chris sniff out the secret ingredients for collecting, displaying, and analyzing odor data with Terri Jordan and Yanis Caritu of Aryballe. It certainly smells like a good time, so join them for this scent-illating episode!
This piece by Mark Saroufim on the state of ML starts pretty salty:
Graduate Student Descent is one of the most reliable ways of getting state of the art performance in Machine Learning today and it’s also a fully parallelizable over as many graduate students or employees your lab has. Armed with Graduate Student Descent you are more likely to get published or promoted than if you took on uncertain projects.
BERT engineer is now a full time job. Qualifications include:
- Some bash scripting
- Deep knowledge of pip (starting a new environment is the suckier version of practicing scales)
- Waiting for new HuggingFace models to be released
- Watching Yannic Kilcher’s new Transformer paper the day it comes out
- Repeating what Yannic said at your team reading group
It’s kind of like Dev-ops but you get paid more.
But if you survive through (or maybe even enjoy) the lamentations and ranting, you’ll find some hope and optimism around specific projects that the author believes are pushing the industry through its Great Stagnation.
I learned a few things. Maybe you will too.
MLCommons launched in December 2020 as an open engineering consortium that seeks to accelerate machine learning innovation and broaden access to this critical technology for the public good. David Kanter, the executive director of MLCommons, joins us to discuss the launch and the ambitions of the organization.
In particular we discuss the three pillars of the organization: Benchmarks and Metrics (e.g. MLPerf), Datasets and Models (e.g. People’s Speech), and Best Practices (e.g. MLCube).
While looking for these MLOps tools, I discovered some interesting points about the MLOps landscape:
- Increasing focus on deployment
- The Bay Area is still the epicenter of machine learning, but not the only hub
- MLOps infrastructures in the US and China are diverging
- More interests in machine learning production from academia
American Express is running what is perhaps the largest commercial ML model in the world; a model that automates over 8 billion decisions, ingests data from over $1T in transactions, and generates decisions in mere milliseconds or less globally. Madhurima Khandelwal, head of AMEX AI Labs, joins us for a fascinating discussion about scaling research and building robust and ethical AI-driven financial applications.
Bharat Sandhu, Director of Azure AI and Mixed Reality at Microsoft, joins Chris and Daniel to talk about how Microsoft is making AI accessible and productive for users, and how AI solutions can address real world challenges that customers face. He also shares Microsoft’s research-to-product process, along with the advances they have made in computer vision, image captioning, and how researchers were able to make AI that can describe images as well as people do.
Graph neural networks (GNNs) belong to a category of neural networks that operate naturally on data structured as graphs. Despite being what can be a confusing topic, GNNs can be distilled into just a handful of simple concepts.
Practical uses of GNNS include making traffic predictions, search rankings, drug discovery, and more.
Unsplash has released the world’s largest open library dataset, which includes 2M+ high-quality Unsplash photos, 5M keywords, and over 250M searches. They have big ideas about how the dataset might be used by ML/AI folks, and there have already been some interesting applications. In this episode, Luke and Tim discuss why they released this data and what it take to maintain a dataset of this size.
Machine learning is a trendy topic, so naturally it’s often used for inappropriate purposes where a simpler, more efficient, and more reliable solution suffices. The other day I saw an illustrative and fun example of this: Neural Network Cars and Genetic Algorithms. The video demonstrates 2D cars driven by a neural network with weights determined by a generic algorithm. However, the entire scheme can be replaced by a first-degree polynomial without any loss in capability. The machine learning part is overkill.
Yet another example of a meta-trend in software: You might not need
$X is a popular tool or technique that is on the upward side of the hype cycle).
Lucy D’Agostino McGowan, cohost of the Casual Inference Podcast and a professor at Wake Forest University, joins Daniel and Chris for a deep dive into causal inference. Referring to current events (e.g. misreporting of COVID-19 data in Georgia) as examples, they explore how we interact with, analyze, trust, and interpret data - addressing underlying assumptions, counterfactual frameworks, and unmeasured confounders (Chris’s next Halloween costume).
What’s it like to try and build your own deep learning workstation? Is it worth it in terms of money, effort, and maintenance? Then once built, what’s the best way to utilize it? Chris and Daniel dig into questions today as they talk about Daniel’s recent workstation build. He built a workstation for his NLP and Speech work with two GPUs, and it has been serving him well (minus a few things he would change if he did it again).
Weights & Biases is coming up with some awesome developer tools for AI practitioners! In this episode, Lukas Biewald describes how these tools were a direct result of pain points that he uncovered while working as an AI intern at OpenAI. He also shares his vision for the future of machine learning tooling and where he would like to see people level up tool-wise.
Craig Kerstiens told me about this on our recent Postgres episode of The Changelog and my jaw about dropped out of my mouth.
… earlier today I was starting to wonder why couldn’t I do more machine learning directly inside [Postgres]. Yeah, there is madlib, but what if I wanted to write my own recommendation engine? So I set out on a total detour of a few hours and lo and behold, I can probably do a lot more of this in Postgres than I realized before. What follows is a quick walkthrough of getting a recommendation engine setup directly inside Postgres.
Craig doesn’t necessarily suggest you put this kind of solution in production, but he doesn’t come out and say don’t do it either. 😉
Hamish from Sajari blows our mind with a great discussion about AI in search. In particular, he talks about Sajari’s quest for performant AI implementations and extensive use of Reinforcement Learning (RL). We’ve been wanting to make this one happen for a while, and it was well worth the wait.
Adrian Colyer walks us through a paper from SageDB that’s taking machine learning and applying it to old Computer Science problems such as sorting. Here’s the big idea:
Suppose you had a model that given a data item from a list, could predict its position in a sorted version of that list. 0.239806? That’s going to be at position 287! If the model had 100% accuracy, it would give us a completed sort just by running over the dataset and putting each item in its predicted position. There’s a problem though. A model with 100% accuracy would essentially have to see every item in the full dataset and memorise its position – there’s no way training and then using such a model can be faster than just sorting, as sorting is a part of its training! But maybe we can sample a subset of the data and get a model that is a useful approximation, by learning an approximation to the CDF (cumulative distribution function).