We have compared the performance of Simple U-Net, Residual Attention U-Net, and Vgg16-U-Net for Inventory Inland Water Bodies based on Sentinel-2 data, and we found Vgg16-U-Net has better results in comparison to others; you can read our preprint here: https://dx.doi.org/10.2139/ssrn.4505885 #RemoteSensing #deepleaning
I am looking forward to working with a #machineLearning / #deepLeaning product, as I hope that it will give me purpose in my own efforts of following #fastai 's #PracticalDeepLearningForCoders.
The good thing about working at an early stage start up is that boundaries are fuzzy, and despite being a #Ruby engineer, I hope to get my paws dirty hacking some #tensorFlow / #pytorch
#machinelearning #deepleaning #fastai #PracticalDeepLearningForCoders #ruby #tensorflow #pytorch
In der ProSiebenSat.1 Media SE-Sendung „Zervakis & Opdenhövel. Live.“ geht es heute Abend um #künstlicheIntelligenz und den neuen Chatbot #ChatGPT. Die Dreharbeiten fanden im Vorfeld auch bei uns in Jülich statt. So ließ sich etwa Joerg Bienert, Vorstandsvorsitzender des KI Bundesverband, vom Jülicher KI-Experten Stefan Kesselheim den Jülicher Supercomputer #JUWELS und damit die deutschlandweit stärkste Plattform für KI und #DeepLeaning zeigen. /mb
#kunstlicheintelligenz #chatgpt #JUWELS #deepleaning