Adventures with MakerSuite and PaLM 2

Continuing the theme of something new/interesting being released daily - this month we look at what is new and cool in the Google ecosystem, and what has recently been announced at Google Cloud Next for Generative AI.

Talks:

"Fine Tuning PaLM 2 for Fun and Profit" - Sam Witteveen

In this talk Sam will show how you can fine tune models for various tasks and uses using Google's Vertex and get MakerSuite to help in creating data for various Fine Tunes.

"The Hidden Power of XAI: From Bias Detection to Model Optimization" - Florian Kowarsch

In this lightning talk about Explainable AI (XAI), Florian will go into why XAI is necessary, and how can it be used to benefit training overall. He will also describe his personal journey and how he ended up doing XAI.

"LLMs and Reasoning" - Martin Andrews

Language Models appear to have increasing abilities to do reasoning tasks, but is this an illusion? In this talk, Martin will discuss the limitations of LLMs, and highlight some of the methods through which researchers are attempting to enhance models with more robust reasoning tools. Expect demos using PaLM API / MakerSuite!

***

Talks will start at 6:45pm and end at around 8:30pm, 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_core, TensorFlow, 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 and enthusiastic beginner: Given the responses we have had to previous talks, we're sure there are lots of people who would be interested to hear what you've been playing with. If you're interested in talking, please just introduce yourself to Sam or Martin at one of the events.