Artificial intelligence-driven microRNA signature for early detection of gastric cancer: discovery and clinical functional exploration https://www.byteseu.com/924972/ #AI #ArtificialIntelligence #Biomedicine #CancerModels #CancerResearch #ComputationalScience #DiagnosticMarkers #DrugResistance #epidemiology #GastricCancer #General #miRNAs #MolecularMedicine #Oncology
https://www.europesays.com/1974372/ Energy efficient task scheduling for heterogeneous multicore processors in edge computing #ComputationalScience #COMPUTERSCIENCE #DVFS #EdgeComputing #Energy #EnergyEfficientTaskScheduling #HeterogeneousMulticoreProcessors #HumanitiesAndSocialSciences #InformationTechnology #multidisciplinary #PerformanceOptimization. #science #TaskMapping #TaskPriorityAssignment
On this note: are you interested in #tech, #selfHosting, #science, #computationalScience, #HPC, #liberatoryTech, or just #POSIX in general but otherwise lack the resources, financial or otherwise? Get in touch with me and we can have a chat about maybe getting you some time. I can't promise when things will be ready or how much I can offer, but.
No generative AI training, please. 'Classic' ML that doesn't generate trash, contribute to surveillance, or rely on stolen data is fine though.
RE: https://fire.asta.lgbt/notes/a3911f2wi43200mf
https://www.europesays.com/1759609/ Intelligent skin disease prediction system using transfer learning and explainable artificial intelligence #AI #AndLayerWiseRelevancePropagation(LRP) #ArtificialIntelligence #ArtificialIntelligenceAI #Chickenpox #ComputationalScience #COMPUTERSCIENCE #DeepLearning(DL) #ExplainableArtificialIntelligence(XAI) #HumanitiesAndSocialSciences #MachineLearning(ML) #Measles #monkeypox #multidisciplinary #science #SkinCancer #Software #TransferLearning(TL) #VGG16
New preprint on our "collaborative modelling of the brain" (COMOB) project. Over the last two years, a group of us (led by @marcusghosh) have been working together, openly, online, with anyone free to join, on a computational neuroscience research project
https://www.biorxiv.org/content/10.1101/2024.07.19.604252v1
This was an experiment in a more bottom up, collaborative way of doing science, rather than the hierarchical PI-led model. So how did we do it?
We started from the tutorial I gave at @CosyneMeeting 2022 on spiking neural networks that included a starter Jupyter notebook that let you train a spiking neural network model on a sound localisation task.
https://neural-reckoning.github.io/cosyne-tutorial-2022/
https://www.youtube.com/watch?v=GTXTQ_sOxak&list=PL09WqqDbQWHGJd7Il3yVxiBts5nRSxvJ4&index=1
Participants were free to use and adapt this to any question they were interested in (we gave some ideas for starting points, but there was no constraint). Participants worked in groups or individually, sharing their work on our repository and joining us for monthly meetings.
The repository was set up to automatically build a website using @mystmarkdown showing the current work in progress of all projects, and (later in the project) the paper as we wrote it. This kept everyone up to date with what was going on.
https://comob-project.github.io/snn-sound-localization/
We started from a simple feedforward network of leaky integrate-and-fire neurons, but others adapted it to include learnable delays, alternative neuron models, biophysically detailed models, incorporated Dale's law, etc.
We found some interesting results, including that shorter time constants improved performance (consistent with what we see in the auditory system). Surprisingly, the network seemed to be using an "equalisation cancellation" strategy rather than the expected coincidence detection.
Ultimately, our scientific results were not incredibly strong, but we think this was a valuable experiment for a number of reasons. Firstly, it shows that there are other ways of doing science. Secondly, many people got to engage in a research experience they otherwise wouldn't. Several participants have been motivated to continue their work beyond this project. It also proved useful for generating teaching material, and a number of MSc projects were based on it.
With that said, we learned some lessons about how to do this better, and yes, we will be doing this again (call for participation in September/October hopefully). The main challenge will be to keep the project more focussed without making it top down / hierarchical.
We believe this is possible, and we are inspired by the recent success of the Busy Beaver challenge, a bottom up project of mathematics amateurs that found a proof to a 40 year old conjecture.
We will be calling for proposals for the next project, engaging in an open discussion with all participants to refine the ideas before starting, and then inviting the proposer of the most popular project to act as a 'project lead' keeping it focussed without being hierarchical.
If you're interested in being involved in that, please join our (currently fairly quiet) new discord server, or follow me or @marcusghosh for announcements.
I'm excited for a future where scientists work more collaboratively, and where everyone can participate. Diversity will lead to exciting new ideas and progress. Computational science has huge potential here, something we're also pursuing at @neuromatch.
Let's make it happen!
Very interesting and detailed paper by Thimbleby (2024) on how to improve computational methods in science (software engineering principles, reproducible analytic pipelines, enhancing the role of code in the scientific workflow etc).
Paper is #OpenAccess here: https://academic.oup.com/comjnl/article/67/4/1381/7235536?login=false
There's also a version with a long appendix that summarizes software engineering best practices: https://www.harold.thimbleby.net/paper-seb.pdf
Interesting new comment by Hocquet et al (2024) on the underappreciated role of software in science: https://www.nature.com/articles/s43588-024-00651-2
In a nutshell, we talk a lot about results, but very little about how and where they came from.
The article is #OpenAccess
Last chance to apply as a TA for this year's Climatematch Academy! Applications close at midnight TONIGHT (March 17) in the last time zone on earth. Don't miss out on this amazing opportunity!
"We thus model the committed evolution of all glaciers in the European Alps up to 2050 using present-day climate conditions, assuming no future climate change. We find that the resulting committed ice loss exceeds a third of the present-day ice volume by 2050, with multi-kilometer frontal retreats for even the largest glaciers."
Cook, S. J., Jouvet, G., Millan, R., Rabatel, A., Zekollari, H., & Dussaillant, I. (2023). Committed ice loss in the European Alps until 2050 using a deep-learning-aided 3D ice-flow model with data assimilation. Geophysical Research Letters, 50, e2023GL105029. https://doi.org/10.1029/2023GL105029 #OpenAccess #OA #Research #Science #STEM #Glaciers #Climate #Data #AI #Europe #ComputationalScience #ClimateChange #Environment #Artificialintelligence #Academia #Academic #Academics @science @climate
I'm organizing a one day workshop on #ComputationalScience and #Sustainability right now.
So, what are the grand challenges in sustainability that can be solved using computational science or where computational science can give huge contributions?
8/
A clear introduction on intrinsic #uncertainty in #ComputationalScience modelling (and epistemic humility) by Richard de Neufville (MIT #OpenCourseWare, Risk and Decision Analysis):
- Flaw of Averages: why central #OneDimensionalMetrics in non-trivial systems may mislead
https://ocw.mit.edu/courses/ids-333-risk-and-decision-analysis-fall-2021/resources/unit-2-flaw-o-f-averages-video-5/
- unexpected surprises in the real world
https://ocw.mit.edu/courses/ids-333-risk-and-decision-analysis-fall-2021/resources/unit-2-forecast-always-wrong-video-1/
- Porcupine Graphs: how "often experts don't learn", think "they know better" and miss evident mental biases
https://ocw.mit.edu/courses/ids-333-risk-and-decision-analysis-fall-2021/resources/unit-2-porcupine-graphic-video-3/
https://www.rug.nl/about-ug/work-with-us/job-opportunities/?details=00347-02S000AI7P
Fully-paid PhD position Narratives in Argumentation (1.0 FTE) - computational approaches
Come work with me in the Netherlands!
Revised preprint: "Establishing trust in automated reasoning"
https://osf.io/preprints/metaarxiv/nt96q/
More and more scientific reasoning is automated via software and machine learning. Users of these tools rarely understand their inner workings in detail. They are exempt from peer review. Can we trust them? On what basis? Under which conditions? Can we do better? These are the questions I address in this paper.
#MetaScience #ComputationalScience
A little summary 
New paper out: The Nature of Computational Models
https://doi.org/10.1109/MCSE.2023.3286250
Preprint: https://hal.science/hal-04148865
Computational models lie at the heart of computational science, yet few scientists have a clear idea of what a computational model actually is. I argue that in the most general case, computational models are formal specifications. I explain the relations between specifications, algorithms, software, and mathematical functions and equations, and I discuss examples.
New preprint: "Establishing trust in automated reasoning".
https://osf.io/preprints/metaarxiv/nt96q/
Feedback welcome!
Most research uses software, but scientific software is not reviewed. Can we trust it? Which software can be reviewed (but isn't)? Which software cannot be reviewed with reasonable effort? Is there something we can do about this?
On the way to #PASC23!
#HPC #ComputationalScience
Yesterday, Gil Strang gave his final lecture at MIT. It was monumental enough to be live streamed with guests coming in to talk about his influence. The fact that it was a normal class lecture is so appropriate. It is the end of an era in #teaching.
I only visited MIT once, for an ASA conference, but Strang has affected my life deeply. His teaching of linear algebra is the best I have ever seen, full stop.
The Calls for Workshops and Papers for eScience 2023 are out!
- Workshop proposals are due on February 10, 2023
- Paper submissions are due on May 26, 2023
Seeking #successfactors for #ComputationalScience #software projects, a @NSF funded project looking at on what computational science projects exist & which might be called "better" than others, is seeking #survey participants https://docs.google.com/forms/d/e/1FAIpQLSeTapJFaiaXTtc-CqvmUBOJ9clGy4IgFFUZbT1Xy8s8cWYNcw/viewform
Fully funded 4 year #PhD in my group, supported by EPSRC available!
Come work on the cutting edge of understanding how mutations alter the #aging tissue and influence #cancer development. Study how mutant clones spread and interact in the tissue with #computationalscience.
Recent graduates have been highly successful taking positions in industry and academia.
See my lab web page to learn more about our work- https://www.hall-lab.com
https://ucl-epsrc-dtp.github.io/2023-24-project-catalogue/projects/2228bd1101.html
