!function(){try{var d=document.documentElement,c=d.classList;c.remove('light','dark');var e=localStorage.getItem('theme');if('system'===e||(!e&&true)){var t='(prefers-color-scheme: dark)',m=window.matchMedia(t);if(m.media!==t||m.matches){d.style.colorScheme = 'dark';c.add('dark')}else{d.style.colorScheme = 'light';c.add('light')}}else if(e){c.add(e|| '')}if(e==='light'||e==='dark')d.style.colorScheme=e}catch(e){}}()FeedSharePathsWhat's new?FeedbackAboutPrivacyTermsHomeLoginSign upDocument your learning so others can learn fasterCollect and connect helpful learning contents to help others find them faster.Sign upDocumented ActivitiesFeaturedNewView moreContentReal-world applications of symbolic regression | by LucianoSphere | Towards Data Sciencetowardsdatascience.comThe main idea of symbolic regression, which is finding equations that relate variables, has existed for a long time. But only in the last decade has it begun to make an impact on actual research in physics, chemistry, biology, and engineering. Find there the key novel methods, some of the modern programs you can use, and several example applications.Add this content to a path or other contentMark this as completed to improve your recommendationsBookmark this to save it in your library for laterMark this as helpful to improve your recommendationsLearning PathImplement Semantic SearchAfter building and deploying a semantic search engine myself, I would say that this learning path might be a valuable guide to do this. It starts by developing a basic understanding of linear algebra, neural networks and the transformer model. It then covers AWS, Django and React basics. Finally, the path provides tutorials on systems that can be integrated to build a semantic search.Bookmark this to save it in your library for laterMark this as helpful to improve your recommendationsContentStable Fluids implemented in Python/NumPywww.youtube.comIn his 1999 SIGGRAPH Paper Jos Stam introduced a famous algorithm that is still ubiquitous in Computer Graphics and Video Game Physics. It solves the Navier-Stokes equations unconditionally stable and simulates fluid dynamics. Here is the code: https://github.com/Ceyron/machine-learning-and-simulation/blob/main/english/simulationscripts/stablefluidspythonsimple.py
Unconditionally stable means that the time steps can be chosen arbitrarily large, and the kinematic viscosity can also be selected freely. This is extremely advantageous for computer graphics applications. Surely, this algorithm is unable to compete with state-of-the-art CFD codes in terms of accuracy and modelling capabilities. However, I think it is beautiful and encourages one to dig deeper.
You can find Jos' original paper here: https://d2f99xq7vri1nk.cloudfront.net/legacyappfiles/pdf/ns.pdf
His modified solver which is suitable to run in real-time is described here: http://graphics.cs.cmu.edu/nsp/course/15-464/Fall09/papers/StamFluidforGames.pdf
📝 : Check out the GitHub Repository of the channel, where I upload all the handwritten notes and source-code files (contributions are very welcome): https://github.com/Ceyron/machine-learning-and-simulation
📢 : Follow me on LinkedIn or Twitter for updates on the channel and other cool Machine Learning & Simulation stuff: https://www.linkedin.com/in/felix-koehler and https://twitter.com/felixmkoehler
💸 : If you want to support my work on the ch