At ICSE @icseconf 2025? Check out Jiannan Wang’s D3 talk at 2:30 PM today Friday in Room 215 about how we find real-world bugs in production distributed systems code! https://bsky.app/profile/lin-tan.bsky.social/post/3ljvkq4fjzk23 #deepleanring #distributed #testing
Lin Tan (@lin-tan.bsky.social)

🚀 Thrilled to share our #TSE journal-first paper D3: Differential Testing of Distributed Deep Learning (DL)! @Jianan will present it at #ICSE2025. D3 detects 21 bugs (12 new!) in PyTorch and TensorFlow. 🔗 https://www.cs.purdue.edu/homes/lintan/publications/d3-tse25icse25.pdf #DeepLearning #SoftwareTesting @cerias.bsky.social

Bluesky Social
Glacial Lake Mapping Using Remote Sensing Geo-Foundation Model
--
https://doi.org/10.1016/j.jag.2025.104371 <-- shared paper
--
HIGHLIGHTS:
• Proposed U-ViT model based on Prithvi GFM for multi-sensor glacial lake mapping.
• Achieved an F1 score of 0.894 on Sentinel-1&2, surpassing CNNs scoring below 0.8.
• Maintains strong performance with 50% less training data, proving efficiency.
• Excels in detecting small lakes (<0.01km²) and handling clouds and complex terrains..."
#GIS #spatial #mapping #glaciallake #GeospatialFoundationModel #satellite #Sentinel #GaoFen #remotesensing #earthobservation #model #modeling #climatechange #glacial #glacier #melt #melting #UViT #deepleanring #AI #framework #performance #metrics #opensource

Today we post a tutorial on backpropagaion, an important topic to #deepleanring and #machinelearning in general - trying to get this out in time as people review for finals.

https://youtu.be/Xjb6_y4IIME

@ASU @ASUEngineering @asu_gsi @SCAI_ASU #AI

Backpropagation: Training Deep Neural Networks

YouTube

Today we post a tutorial on gradient descent, an important topic to #deepleanring and #machinelearning in general - trying to get this out in time as people review for finals.

https://youtu.be/-Np5Eu9cLrc

@ASU @ASUEngineering @asu_gsi @SCAI_ASU #AI

Introduction to Gradient Descent

YouTube