Ever since its introduction in the 2017 paper, Attention is All You Need, the Transformer model architecture has taken the deep-learning world by storm. Initially introduced for machine translation, it has become the tool of choice for a wide range of domains, including text, audio, video, and others. Transformers…
Faizan Muhmmad is a Software Engineer at Google
The homepage of Lux: professional artist, game developer, educator, and pixel provocateur.
I really want to make a game along the line of Myst. I have been collecting puzzles for years, and I have almost enough. I am flexible about the visual style. I’ve considered making sets out of lego, or cardboard , or cut paper. And I’ve considered AI-generated art.
Or "Why we're all in denial about the robot apocalypse"
Mimicry but not thought, sophistry but not understanding
(Disclaimer: I am a transhumanist skeptic these days, not to mention a singularity curmudgeon and a critic of Mars colonization, but I still find these ideas nice to chew on sometimes.)
The image alignment and registration pipeline takes two input images that contain the same scene from slightly different viewing angles. The picture above displays both input images side by side with the common scene (object) being the painting Las Meninas (1656) by Velázquez, currently at the Museo del Prado in…
I wondered how GPT-3 might do on the following problem: given a partially-connected graph, find a path between two nodes, or determine that no path exists. I wrote some code to automate generating …
1990: gradient descent learns subgoals. 1991: multiple time scales and levels of abstraction. 1997: world models learn predictable abstract representations...
I am very happy to say that I have recently received a generous grant from the Astera Institute to set up a small group to work on automatic theorem proving, in the first instance for about three y…
Lighting, perspective, variation chaining, and other tricks to try with DALL·E.
a bare minimum introduction to modern program synthesis
I will try to solve all of the advent of code with as little human input as possible
Machine-learning generated content has major implications on the Metaverse, because it brings the marginal cost of production to zero.
Describe the image you want, and the app makes it for you.
I discuss the messy state of MLOps today and how we are still in the early phases of a broader transformation to bring machine learning value to enterprises globally.
Machine Learning with PyTorch and Scikit-Learn has been a long time in the making, and I am excited to finally get to talk about the release of my new book…
Python-based calculations, especially those that use NumPy, can run much faster by using the Numba library.
I recently came up with what I think is an intuitive way to explain Bayes’ Theorem. I searched in google for a while and could not find any article that explains it in this particular way.
Occasionally, I share research papers proposing new deep learning approaches for tabular data on social media, which is typically an excellent discussion…
My chat with Cristóbal Valenzuela, Cofounder & CEO of Runway .
How deep learning models are moderated
Full stack software engineer / entrepreneur specialized in AI agents, cybersecurity and graphics. In my free time I enjoy surfing, free diving, and contributing to open source software.
A while ago there was an interesting thread on the Julia Discourse about the “state of machine learning in Julia”. I posted a response discussing the differences between Julia and Python (both JAX and PyTorch), and it seemed to be really well received! Since then this topic seems to keep coming up, so I thought I’d…
