My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch.

fleuret.org/dlc/

And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)

fleuret.org/lbdl/

cronicl.org has collaborative features designed for wildlife recording communities 📷🌼

You can join a group session to:
- see all your recordings on a shared map
- get notifications for what others have recorded
- see statistics and summary information when you're finished

There were great conversations at #NBNconf24 surrounding what additional data to gather for wildlife observations (weather, scenery, habitat, etc.).

We are designing the data structure for our biodiversity monitoring app cronicl.org, what data would the #bsky #uknature community like to record?

On the second day of Christmas my true love sent to me...

Another example of our custom AI model in cronicl.org 🕊️🕊️we are launching in early 2025, you can sign up for the demo on our website!

#WildlifeRecording #Biodiversity #Wales #Nature

Our biodiversity monitoring platform cronicl.org has a custom image classifier to help determine the species you've found in your local green spaces.

I thought I'd do some festive testing today using our AI demo 🐦🍐

#WildlifeRecording #Biodiversity #Wales #Nature

For anyone interested in nature recording, we're launching cronicl.org next year, a collaborative biodiversity monitoring app. We'd love to hear your feedback, so please sign up on our website if you want to try our platform.

#WildlifeRecording #Biodiversity #Wales #Nature

I had a great time attending #NBNconf24, it was great to chat to passionate people about recording and citizen science.

We're launching our biodiversity monitoring platform cronicl.org early next year, you can register your interest for access!🌻

#WildlifeRecording #Nature #Wales

Hi, just sharing an updated version of the PyTorch 2 Internals slides: drive.google.com/file/d/18YZV.... Content: basics, jit, dynamo, Inductor, export path and executorch. This is focused on internals so you will need a bit of C/C++. I show how you can export and run a model on a Pixel Watch too.

Excited to attend #NBNconf24 this week in Liverpool - it will be great to hear other perspectives on using tech to engage and inspire citizen science 🌿