Why do tree-based models still outperform deep learning on tabular data?
While deep learning has enabled tremendous progress on text and image datasets, its superiority on tabular data is not clear. We contribute extensive benchmarks of standard and novel deep learning...
Why AI and machine learning are drifting away from the cloud
Cloud computing isn’t going anywhere, but some companies are shifting their machine learning data and models to their own machines they manage in-house. Adopters are spending less money and getting better performance.
How I Used DALL·E 2 to Generate The Logo for OctoSQL
Everybody has heard about the latest cool thing™, which is DALL·E 2 (henceforth called Dall-e). A few months ago, when the first previews started, it was basically everywhere. Now, a few weeks ago, the floodgates have been opened and lots of people on the waitlist got access - that group included me.
I’ve spent a day playing around with it, learned some basics (like the fact that adding “artstation” to the end of your phrase automatically makes the output much better…), and generated a bunch of (even a few nice-looking) images.
Practical Deep Learning for Coders - Practical Deep Learning
A free course designed for people with some coding experience, who want to learn how to apply deep learning and machine learning to practical problems.
OpenAI expands access to DALL-E 2, its powerful image-generating AI system – TechCrunch
OpenAI is expanding access to DALL-E 2, its image-generating AI system, with the goal of onboarding around 1 million people from the waitlist within weeks.
One of my favourite uses for the GPT-3 AI language model is generating explanations of how code works. It’s shockingly effective at this: its training set clearly include a vast …
A new AI draws delightful and not-so-delightful images
OpenAI’s DALL-E 2 is incredible at turning text into images. It also highlights the problem of AI bias — and the need to change incentives in the industry.
Experiments I conducted with DALL·E 2 from @OpenAI replicating styles of well known portrait photographers using photo-realistic AI. 🧵1. Dorothea Lange pic.twitter.com/845AzE51xu— Michael Green (@triplux) June 30, 2022
WandB is a central dashboard to keep track of your hyperparameters, system metrics, and predictions so you can compare models live, and share your findings.
Reliance on metrics is a fundamental challenge for AI
Optimizing metrics is a central aspect of most current artificial intelligence (AI)
approaches, yet overemphasizing metrics leads to manipulation, short-termism, and
other negative consequences. This poses a fundamental challenge within AI. We review
how metrics can go wrong in practice, and we put forward an evidence-based framework
toward mitigating these harms.
Enterprise Data Analytics for a Connected Multi-Cloud World
Teradata Vantage is the connected multi-cloud data platform for enterprise analytics that delivers actionable answers and predictive intelligence. Learn more.
Training a collaborative filtering based recommendation system on a toy dataset is a sophomore year project in colleges these days. But where the rubber meets the road is building such a system at scale, deploying in production, and serving live requests within a few hundred milliseconds while the user is waiting for the page to load. To build a system like this, engineers have to make decisions spanning multiple moving layers like:
GitHub - dair-ai/ML-Notebooks: A series of code examples for all sorts of machine learning tasks and applications.
:fire: A series of code examples for all sorts of machine learning tasks and applications. - GitHub - dair-ai/ML-Notebooks: A series of code examples for all sorts of machine learning tasks and app...
