LLMs for Software and Wetware

This month's event has a bit of a Nature twist : The evolution of programs; and using programs to help design medicines.

Talks:

"Evolving GPU Kernels" - Martin Andrews

As mentioned at our last meetup, AMD is currently running a competition to create high-performance GPU kernels (along the lines of DeepSeek's open source releases for Nvidia). In his talk, Martin will discuss some of the complexities of kernel programming, and whether Gemini Pro can tackle the task. Then, taking it a step further, we'll look at how a Quality/Diversity evolutionary process could power the search for effective solutions.

"A Deep Learning Approach for Nanomedicine Design" - Alvin Chan

The success of COVID-19 mRNA vaccines is driven by a new class of medicine based on Lipid nanoparticles (LNPs), but designing these multi-component drug delivery systems is still a major challenge. In this talk, Alvin will share how COMET (a transformer-based deep learning model) was built. By capturing the molecular structures, ratios, and synthesis parameters of LNPs, COMET can predict their efficacy and accelerate the design of next-generation RNA medicines.

---

Talks will start at 7:00pm and end at around 8:45pm, at which point people normally come up to the front for a bit of a chat with each other, and the speakers.

As always, we're actively looking for more speakers - both '30 minutes long-form', and lightning talks. For the lightning talks, we welcome folks to come and talk about something cool they've done with keras, PyTorch, JAX and/or Deep Learning for 5-10mins (so, if you have slides, then #max=10). We believe that the key ingredient for the success of a Lightning Talk is simply the cool/interesting factor. It doesn't matter whether you're an expert or an enthusiastic beginner: Given the responses we have had to previous talks, we're sure there are lots of people who would love to hear what you've been playing with. If you're interested in talking, please just introduce yourself to Martin at one of the events.