We have taken our Artificial Intelligence Forecasting System (AIFS) into operations today to run side by side with our physics-based weather forecasts. The #AIFS outperforms traditional models for many measures, at a fraction of energy use. ➡️ www.ecmwf.int/en/about/med...
#AI #MachineLearning
#AI #MachineLearning
February 25, 2025 at 11:07 AM
We have taken our Artificial Intelligence Forecasting System (AIFS) into operations today to run side by side with our physics-based weather forecasts. The #AIFS outperforms traditional models for many measures, at a fraction of energy use. ➡️ www.ecmwf.int/en/about/med...
#AI #MachineLearning
#AI #MachineLearning
October 31, 2025 at 10:53 AM
This illustrates why lumping all ‘AI’ (loosely: #MachineLearning) technology together is problematic. We should at least differentiate between ‘pattern recognition’-based and ‘pattern generation’ forms of #AI. The moral and epistemic issues they raise are somewhat different. #AIEthics #GenAI
May 27, 2025 at 9:38 AM
This illustrates why lumping all ‘AI’ (loosely: #MachineLearning) technology together is problematic. We should at least differentiate between ‘pattern recognition’-based and ‘pattern generation’ forms of #AI. The moral and epistemic issues they raise are somewhat different. #AIEthics #GenAI
A machine learning based scheme for enhancing the detection of position falsification: the part most people miss. Save this for later.
#machinelearning #coherance #joedispenza #yeet #science #logic #dna #molecule #biophoton #fyp #mind #analysis
#machinelearning #coherance #joedispenza #yeet #science #logic #dna #molecule #biophoton #fyp #mind #analysis
September 26, 2026 at 12:00 PM
A machine learning based scheme for enhancing the detection of position falsification: the part most people miss. Save this for later.
#machinelearning #coherance #joedispenza #yeet #science #logic #dna #molecule #biophoton #fyp #mind #analysis
#machinelearning #coherance #joedispenza #yeet #science #logic #dna #molecule #biophoton #fyp #mind #analysis
The #Netflix recommendation engine, analyzes past viewing patterns to predict users’ preferences. #MachineLearning algorithms optimize recommendations based on user interactions. #DataCollection #PredictiveAnalytics #Analytics #DataScience #NewGizmo
www.analyticsvidhya.com/blog/2024/07...
www.analyticsvidhya.com/blog/2024/07...
July 10, 2024 at 3:26 PM
The #Netflix recommendation engine, analyzes past viewing patterns to predict users’ preferences. #MachineLearning algorithms optimize recommendations based on user interactions. #DataCollection #PredictiveAnalytics #Analytics #DataScience #NewGizmo
www.analyticsvidhya.com/blog/2024/07...
www.analyticsvidhya.com/blog/2024/07...
Hello world. I am based in London and interested in the theory and simulation of materials, with elements of #CompChem, #MachineLearning and #AIforScience. It is comforting to see the chemistry community (re)unite on #ChemSky and #CompChemSky 🦋
November 16, 2024 at 8:21 AM
Hello world. I am based in London and interested in the theory and simulation of materials, with elements of #CompChem, #MachineLearning and #AIforScience. It is comforting to see the chemistry community (re)unite on #ChemSky and #CompChemSky 🦋
Boosting molecular dynamics simulations in #CompChem: Socket-based communication slashes computation times tenfold, enhancing efficiency for molecular dynamics, especially with fast #MachineLearning potentials. 🧪
doi.org/10.1021/acs....
doi.org/10.1021/acs....
Accelerating Molecular Dynamics Simulations Using Socket-Based Interprocess Communication
Molecular dynamics (MD) simulations are essential for studying the time evolution of molecular systems. Still, their efficiency is often bottlenecked by file-based interprocess communication (IPC) bet...
doi.org
November 21, 2024 at 5:02 PM
Boosting molecular dynamics simulations in #CompChem: Socket-based communication slashes computation times tenfold, enhancing efficiency for molecular dynamics, especially with fast #MachineLearning potentials. 🧪
doi.org/10.1021/acs....
doi.org/10.1021/acs....
Cell-based crop #phenotyping for future climates
#Viewpoint by Sergey Shabala, et al.
nph.onlinelibrary.wiley.com/doi/10.1111/...
#PlantScience #MachineLearning
#Viewpoint by Sergey Shabala, et al.
nph.onlinelibrary.wiley.com/doi/10.1111/...
#PlantScience #MachineLearning
July 12, 2026 at 11:11 PM
Cell-based crop #phenotyping for future climates
#Viewpoint by Sergey Shabala, et al.
nph.onlinelibrary.wiley.com/doi/10.1111/...
#PlantScience #MachineLearning
#Viewpoint by Sergey Shabala, et al.
nph.onlinelibrary.wiley.com/doi/10.1111/...
#PlantScience #MachineLearning
New blackbox global optimization benchmarks shows that the #julialang BlackBoxOptim.jl (BBO) outperforms the classic C-based NLopt on a wide array of difficult optimization problems.
See the benchmarks for more details: docs.sciml.ai/SciMLBenchma...
#optimization #machinelearning #C #python
See the benchmarks for more details: docs.sciml.ai/SciMLBenchma...
#optimization #machinelearning #C #python
May 31, 2025 at 10:54 AM
New blackbox global optimization benchmarks shows that the #julialang BlackBoxOptim.jl (BBO) outperforms the classic C-based NLopt on a wide array of difficult optimization problems.
See the benchmarks for more details: docs.sciml.ai/SciMLBenchma...
#optimization #machinelearning #C #python
See the benchmarks for more details: docs.sciml.ai/SciMLBenchma...
#optimization #machinelearning #C #python
In 2022 (back when #Twitter was still a thing), I had made this #meme about the state of #urban #climate #research based on an #xkcd comic.
With all the recent changes in the #publication and #funding spaces due to the #AI + #machinelearning hype cycle, here is an updated version.
With all the recent changes in the #publication and #funding spaces due to the #AI + #machinelearning hype cycle, here is an updated version.
March 3, 2026 at 1:19 AM
In 2022 (back when #Twitter was still a thing), I had made this #meme about the state of #urban #climate #research based on an #xkcd comic.
With all the recent changes in the #publication and #funding spaces due to the #AI + #machinelearning hype cycle, here is an updated version.
With all the recent changes in the #publication and #funding spaces due to the #AI + #machinelearning hype cycle, here is an updated version.
💥 AI takes control in space for the first time, helps ISS robot move 60% faster
The system marks the first demonstration of machine learning based control in orbit ▶️
#AI #MachineLearning #Space
#Robotics
interestingengineering.com/ai-robotics/...
The system marks the first demonstration of machine learning based control in orbit ▶️
#AI #MachineLearning #Space
#Robotics
interestingengineering.com/ai-robotics/...
December 12, 2025 at 4:59 PM
💥 AI takes control in space for the first time, helps ISS robot move 60% faster
The system marks the first demonstration of machine learning based control in orbit ▶️
#AI #MachineLearning #Space
#Robotics
interestingengineering.com/ai-robotics/...
The system marks the first demonstration of machine learning based control in orbit ▶️
#AI #MachineLearning #Space
#Robotics
interestingengineering.com/ai-robotics/...
Developed by the multi-talented @pabloarantes.bsky.social & @SouvikSinha members of my lab:
ParametrizANI brings #MachineLearning - based #ForceField parametrization available to everyone
Available on Github: github.com/palermolab/P...
ParametrizANI brings #MachineLearning - based #ForceField parametrization available to everyone
Available on Github: github.com/palermolab/P...
🧠💥 ParametrizANI found a home!
Our paper is now published in JCIM!
Making ML-based force field parametrization open and easy for everyone.
With TorchANI, @rdkit.bsky.social & @openmm.org
🔗 pubs.acs.org/doi/abs/10.1...
@acs.org @giuliapalermo.bsky.social
Our paper is now published in JCIM!
Making ML-based force field parametrization open and easy for everyone.
With TorchANI, @rdkit.bsky.social & @openmm.org
🔗 pubs.acs.org/doi/abs/10.1...
@acs.org @giuliapalermo.bsky.social
October 9, 2025 at 7:44 PM
Developed by the multi-talented @pabloarantes.bsky.social & @SouvikSinha members of my lab:
ParametrizANI brings #MachineLearning - based #ForceField parametrization available to everyone
Available on Github: github.com/palermolab/P...
ParametrizANI brings #MachineLearning - based #ForceField parametrization available to everyone
Available on Github: github.com/palermolab/P...
Looking forward to our upcoming webinar from @csrp.bsky.social on #machinelearning - based models for #suicideprevention Registration can be found here csrp.mgh.harvard.edu/webinars/
November 28, 2024 at 10:02 PM
Looking forward to our upcoming webinar from @csrp.bsky.social on #machinelearning - based models for #suicideprevention Registration can be found here csrp.mgh.harvard.edu/webinars/
The Winter School in #DataAnalytics and #MachineLearning at the University of Fribourg kicked off today with an introductory course using the flowchart-based software #KNIME. A big thank you to all participants for the engaging discussions! #AI #DataScience
February 3, 2025 at 6:33 PM
The Winter School in #DataAnalytics and #MachineLearning at the University of Fribourg kicked off today with an introductory course using the flowchart-based software #KNIME. A big thank you to all participants for the engaging discussions! #AI #DataScience
NEW #openaccess PAPER in Lancet Digital Health “Critical appraisal of fairness metrics for artificial intelligence-based clinical prediction models”
www.thelancet.com/journals/lan...
#predictiveAI #digitaltech #AI #machinelearning #datascience #fairness #healthequity
www.thelancet.com/journals/lan...
#predictiveAI #digitaltech #AI #machinelearning #datascience #fairness #healthequity
May 28, 2026 at 5:14 PM
NEW #openaccess PAPER in Lancet Digital Health “Critical appraisal of fairness metrics for artificial intelligence-based clinical prediction models”
www.thelancet.com/journals/lan...
#predictiveAI #digitaltech #AI #machinelearning #datascience #fairness #healthequity
www.thelancet.com/journals/lan...
#predictiveAI #digitaltech #AI #machinelearning #datascience #fairness #healthequity
OpenAI's o1 marks a major shift in the AI industry, moving away from prediction-based LLMs to reasoning models that aim to overcome their limitations. 🔍🤖 #OpenAI #AI #MachineLearning #ReasoningModels #ArtificialIntelligence #TechInnovation #AIShift
December 8, 2024 at 12:39 AM
OpenAI's o1 marks a major shift in the AI industry, moving away from prediction-based LLMs to reasoning models that aim to overcome their limitations. 🔍🤖 #OpenAI #AI #MachineLearning #ReasoningModels #ArtificialIntelligence #TechInnovation #AIShift
A new #MachineLearning approach is helping to estimate the disease risk of rare genetic variants, researchers report in Science. https://scim.ag/3K3oyYs
Machine learning–based penetrance of genetic variants
Accurate variant penetrance estimation is crucial for precision medicine. We constructed machine learning (ML) models for 10 diseases using 1,347,298 participants with electronic health records, then ...
scim.ag
September 4, 2025 at 4:14 PM
A new #MachineLearning approach is helping to estimate the disease risk of rare genetic variants, researchers report in Science. https://scim.ag/3K3oyYs
Final workshop of our Extreme-scale Mathematically-based Computational Chemistry (EMC2) @erc.europa.eu Synergy project in Roscoff. #ERCSyG #compchem #compchemsky #appliedmathematics #HPC #supercomputing #machinelearning #quantumcomputing
Stay tuned for the next steps!
Stay tuned for the next steps!
July 8, 2026 at 9:14 AM
Final workshop of our Extreme-scale Mathematically-based Computational Chemistry (EMC2) @erc.europa.eu Synergy project in Roscoff. #ERCSyG #compchem #compchemsky #appliedmathematics #HPC #supercomputing #machinelearning #quantumcomputing
Stay tuned for the next steps!
Stay tuned for the next steps!
The normalizing flows paper is my personal test-of-time award. It is still the go-to architecture in simulation-based inference and ML for physics. 🙃
#AI4science #ML4physics #MachineLearning #ICML
#AI4science #ML4physics #MachineLearning #ICML
July 15, 2025 at 6:09 AM
The normalizing flows paper is my personal test-of-time award. It is still the go-to architecture in simulation-based inference and ML for physics. 🙃
#AI4science #ML4physics #MachineLearning #ICML
#AI4science #ML4physics #MachineLearning #ICML
💥 AI-based model can help traffic engineers predict future sites of possible crashes ▶️
#AI #MachineLearning #IoT #5G #SmartCities
techxplore.com/news/2025-10...
#AI #MachineLearning #IoT #5G #SmartCities
techxplore.com/news/2025-10...
October 8, 2025 at 4:59 AM
💥 AI-based model can help traffic engineers predict future sites of possible crashes ▶️
#AI #MachineLearning #IoT #5G #SmartCities
techxplore.com/news/2025-10...
#AI #MachineLearning #IoT #5G #SmartCities
techxplore.com/news/2025-10...
DeepVEST: Deep Learning-based Vessel Segmentation and Erasure in Breast MRI for Improved Lesion Assessment https://doi.org/10.1148/ryai.250630 #MRI #ImageArtifacts #MachineLearning
September 18, 2026 at 7:15 AM
DeepVEST: Deep Learning-based Vessel Segmentation and Erasure in Breast MRI for Improved Lesion Assessment https://doi.org/10.1148/ryai.250630 #MRI #ImageArtifacts #MachineLearning
Apache OpenNLP 2.5.4 is now available for download: buff.ly/UdfP8YZ
The OpenNLP library is a #machinelearning based toolkit for the processing of natural language text. #opensource
The OpenNLP library is a #machinelearning based toolkit for the processing of natural language text. #opensource
April 19, 2025 at 12:20 AM
Apache OpenNLP 2.5.4 is now available for download: buff.ly/UdfP8YZ
The OpenNLP library is a #machinelearning based toolkit for the processing of natural language text. #opensource
The OpenNLP library is a #machinelearning based toolkit for the processing of natural language text. #opensource
Fantastic new paper casting doubt on explainability of explainable AI. To explain complex machine learning algorithms you need reproducibility of the explanation at a minimum academic.oup.com/ehjdh/articl... #machinelearning #Statistics #StatsSky @maartenvsmeden.bsky.social
Signal or noise? Evaluating commonly used attribution methods for explaining deep neural networks in electrocardiogram classification
AbstractAims. Attribution-based explainability methods are widely used in electrocardiogram (ECG) analysis to interpret predictions from ‘black-box’ deep n
academic.oup.com
March 17, 2026 at 12:39 PM
Fantastic new paper casting doubt on explainability of explainable AI. To explain complex machine learning algorithms you need reproducibility of the explanation at a minimum academic.oup.com/ehjdh/articl... #machinelearning #Statistics #StatsSky @maartenvsmeden.bsky.social
I don't know how template-based modeling works, but I'm excited to see it in action someday! 🧪 #RNAsky #machinelearning #bioinformatics
The results are in: top codes in Stanford #RNA 3D Folding @kaggle.com competition are competitive with CASP16-leading humans Vfold, beat AlphaFold 3. Top team’s trick was template-based modeling, not #DeepLearning. Congrats: john, odat, Eigen, + all 1706 participants! www.kaggle.com/competitions...
September 24, 2025 at 6:37 PM
I don't know how template-based modeling works, but I'm excited to see it in action someday! 🧪 #RNAsky #machinelearning #bioinformatics
#julialang GPU-based ODE solvers which are 20x-100x faster than those in #jax and #pytorch? Check out the paper on #sciml DiffEqGPU.jl. Instead of relying on high level array intrinsics that #machinelearning libraries use, it use a direct kernel generation!.
www.sciencedirect.com/science/arti...
www.sciencedirect.com/science/arti...
December 25, 2023 at 1:58 PM
#julialang GPU-based ODE solvers which are 20x-100x faster than those in #jax and #pytorch? Check out the paper on #sciml DiffEqGPU.jl. Instead of relying on high level array intrinsics that #machinelearning libraries use, it use a direct kernel generation!.
www.sciencedirect.com/science/arti...
www.sciencedirect.com/science/arti...