Mastodawn

(Open) Webinar - Introduction to ML/DL Theory - Explore the foundational theory behind Machine Learning (ML) and Deep Learning (DL) in a geospatial context
--
https://events.teams.microsoft.com/event/f6f7b736-1fa2-4934-aee9-895685232fb4@05c95b33-90ca-49d5-b644-288b930b912b <-- shared webina registration
--
H/T Eric Loubier | DG, Canada Centre for Mapping and Earth Observation
“🌎 GeoAI Webinar Series
March 5, 2026 (11:00 am–3:00 pm ET)
Module #1: Introduction to ML/DL Theory
• Explore the foundational theory behind Machine Learning (ML) and Deep Learning (DL) in a geospatial context…”
#webinar #open #free #GeoAI #UNGGIM #ArtificialIntelligence #Geospatial #Webinar #Canada #Americas #eLearning #onlinelearning #AI #NorthAmerica #Algorithms #Architectures #ML #DL #GIS #spatial #mapping #machinelearning #deeplearning #usecase #workflow #spatialdata #remotesensing

Media Japan 17h ago

https://www.wacoca.com/media/588651/ テレ東、『孤独のグルメ』第11弾放送決定約3年半ぶりの新シーズン松重豊「諸事情により続投します」【コメントあり】 – オリコンニュース # #DL #OD #television #tv #TVPrograms #テレビ #テレビ番組

Radio Onda D'Urto 2d ago

DL (IN)SICUREZZA: IL TESTO VOLUTO DALLE DESTRE DIVENTA LEGGE. IL COMMENTO DI ITALO DI SABATO (OSSERVATORIO REPRESSIONE) https://www.radiondadurto.org/2026/02/25/dl-insicurezza-il-testo-voluto-dalle-destre-diventa-legge-il-commento-di-italo-di-sabato-osservatorio-repressione/ #fermodipolizia #malapolizia #scudopenale #INEVIDENZA #NAZIONALI #sicurezza #Rogoredo #voghera #milano #coin #roma #dl

DL (IN)SICUREZZA: IL TESTO VOLUTO DALLE DESTRE DIVENTA LEGGE. IL COMMENTO DI ITALO DI SABATO (OSSERVATORIO REPRESSIONE)

Diventa legge il decreto (in)sicurezza dopo 20 giorni di tensioni anche dentro la destra. Cambiano, lievemente, tre articoli, tra cui due tra i più liberticidi (fermo preventivo e scudo penale per le forze dell'ordine, sulla scorta di quanto accaduto a Rogoredo, Voghera e alla Coin di Roma Termini, con 21 poliziotti e carabinieri indagati per...furti) senza un impianto che rimane comunque da stato di polizia. L'analisi delle ultime modifiche al testo e la valutazione complessiva, su Radio Onda d'Urto, di Italo Di Sabato, compagno di Osservatorio Repressione.

Radio Onda d`Urto

screwlisp 6d ago

Yeesh, okay it is out and I can stop telling you I am going to write it.

https://screwlisp.small-web.org/complex/lisp-feedforward-deep-learning-example/

#deepLearning #symbolic #ffnn pure ansi #commonLisp

The example deliberately causes a hallucination programmed into the training data via simple #roc reasoning. To my knowledge the ROC interpretation of ffnn inference is original to me, here.

The hallucination is in both lockstep and single #neuralnet activations.

Be the first to complain my #DL works on subregions of jagged lists! #programming

Ricardo Barros Lourenço Feb 12

For those doing #HPC #DL model trainings, I need some suggestions. I want to use #horovod in a multi-gpu, multimode setting, but using #Apptainer (or #Docker) containers, due to cluster policy issues. Any reference to share? Issue here: github.com/horovod/horo...

Reference for multigpu HPC model training using docker /singularity · horovod horovod · Discussion #4316

Hi everyone! I'm looking for a reference implementation. In my situation, I want to run a multinode, multigpu model training, based in containers (preferably Singularity, but Docker can be ok). It'...

GitHub

HGPU group Feb 8

HetCCL: Accelerating LLM Training with Heterogeneous GPUs

#LLM #DeepLearning #DL

https://hgpu.org/?p=30545

HetCCL: Accelerating LLM Training with Heterogeneous GPUs

The rapid growth of large language models is driving organizations to expand their GPU clusters, often with GPUs from multiple vendors. However, current deep learning frameworks lack support for co…

hgpu.org

screwlisp Feb 8

As someone who now has a feedforward neural network of a single hidden layer implementation (in #commonLisp) I learned a lot about what has a spot to be stuck into the algorithm.

https://screwlisp.small-web.org/fundamental/sharpsign-sharpsign-input-referential-ffnn-dl-data/

Something that turns out to be easy to stick in is making training data which copies data out of the current context or even to simply point the training data definition into the #deepLearning inference input context though I did not prove convergence for the latter case.

#ai #programming #dl