Physics Informed Machine Learning: High Level Overview of AI and ML in Science and Engineering

This video describes how to incorporate physics into the machine learning process. The process of machine learning is broken down into five stages: (1) formulating a problem to model, (2) collecting and curating training data to inform the model, (3) choosing an architecture with which to represent the model, (4) designing a loss function to assess the performance of the model, and (5) selecting and implementing an optimization algorithm to train the model. At each stage, we discuss how prior physical knowledge may be embedding into the process.
Physics informed machine learning is critical for many engineering applications, since many engineering systems are governed by physics and involve safety critical components. It also makes it possible to learn more from sparse and noisy data sets.
This video was produced at the University of Washington, and we acknowledge funding support from the Boeing Company
%%% CHAPTERS %%%
00:00 Intro
03:53 What is Physics Informed Machine Learning?
06:41 Case Study: Encoding Pendulum Movement
09:19 The Five Stages of Machine Learning
16:09 A Principled Approach to Machine Learning
20:00 Physics Informed Problem Modeling
21:48 Physics Informed Data Curation
25:34 Physics Informed Architecture Design
28:59 Physics Informed Loss Functions
30:55 Physics Informed Optimization Algorithms
34:56 What This Course Will Cover
46:48 Outro

[@ajred0581]

Hi Professor Brunton, I am a high school senior, and I just want to say I love your videos! Your KZbin channel made me realize how much I want to study applied math. Thank you!

[@nias2631]

Unasked for opinion but... Go for it, I was an applied math major w/minor in physics who became fascinated by ML in 2015 after taking Andrew Ng's Coursera course. I work with ML/RL now in the space industry and am a part time PhD student. Best thing ever! These algorithms bring mathematics to life in a crazy way. Plus, the full application of mathematics is barely even scratched yet. I think in the coming years we will see this happen.

[@chri_pierma]

As a visiting Ph.D. student who is starting a research activity on optimization of PINN, I could not thank you enough for this.

[@FouziaAdjailia]

do you have any published research? I'm machine learning research in CFD as well

[@chri_pierma]

@@FouziaAdjailia nope, I just started working on SQP algorithms for neural network optimization with PDE constraints (which easily falls into the PINN category)

[@karlmaroun2389]

​@@chri_pierma SQP as in sequential quadratic programming ?

[@chri_pierma]

@@karlmaroun2389 that is correct

[@hyperduality2838]

Problem, reaction, solution (optimized predictions or syntropy) -- the Hegelian dialectic. Inputs are dual to outputs. "Always two there are" -- Yoda. Thesis is dual to anti-thesis creates the converging or syntropic thesis, synthesis -- the time independent Hegelian dialectic. Neural networks are using duality to optimize predictions -- a syntropic process, teleological. Enantiodromia is the unconscious opposite or opposame (duality) -- Carl Jung.

[@aninditadash3204]

Thank you for the making these videos available to everyone.

[@HarishNarayanan]

This is easily the most exciting video I have seen in so long. Looking forward to the rest of the series!

[@Crappylasagna]

As an undergraduate venturing into wearable robotics, this is literally a gold mine

[@GeoffryGifari]

wearable robotics? like power armor?

[@Crappylasagna]

@@GeoffryGifari Yes, thou my thesis is on enhancing athletic performance.

[@khaldibel]

Absolutely blown away by this video! 🚀 The insights to be shared later are truly fascinating. Can't wait for the entire lecture series on Physical Informed Machine Learning. This topic is incredibly promising, and I'm eager to delve deeper into the subject. Kudos to the creator for such an engaging and informative content! 👏👏

[@loipham31]

I have special interest in the lectures by Pro. Brunton. I wish I had him taught in my education.

[@thoppay76]

Dear Professor Brunton. thanks a lot for putting together a lecture series on such a great topic. Very much looking forward to learn this domain.

[@lucascarmona1045]

Professor, I don't think I can stress this enough: thank you for all your and your team's work. As you were laying out the roadmap of what we might be seeing in the future I was getting more and more excited and just could not believe that we are getting this much.

[@lingzhu7554]

i don't want to miss any of your lectures. Thank you, professor.

[@_cogojoe_]

How is this channel not millions of subs already?

[@datagigs5478]

The lecture was outstanding and truly engaging. I'm eagerly anticipating the forthcoming videos in this captivating series, especially with the promise of assessing some intriguing engineering problems.

[@qaisalzoubi308]

I love this channel , he can simplify any most complex topics .

[@jatinkm]

This is really invaluable information. Thanks for making this public. Especially when there's so little talk about it on the internet

[@wadejohnson4542]

Captivating, to say the least. I am so looking forward to this lecture series. Prof. Brunton, I hope that you can deliver on your promises. I am so excited. Hoping to implement a few of the models along the way. Thank you.

[@arunamanipura3864]

Thanks very much Professor Brunton. Absolutely engaging lecture! I'm a novice to data science, yet you inspired me to show the potential and applications of physics informed ML. I'll definitely follow the whole series.

[@rocketmike9847]

This series will be gold

[@franpastor2067]

This topic looks super exciting and promising, I feel lucky for finding this video, thanks for sharing knowledge like this, professor Brunton

[@tommyhuffman7499]

Incredibly thankful for this series!

[@carriefu458]

Always LOVE your content and teaching, Prof Bruton!!! So cool!!! Go SCIENCE!

[@mini-pouce]

Really good content, that intro convice me already. Lots of stuff to understand AI, less so to apply it to your work and understant interaction. Thank you.

[@et4493]

Can't thank you enough for this course Mr. Brunton

[@climbscience4813]

Really looking forward to this!! I've been working on algorithms that take physical properties or measurements for about a decade during a time where machine learning wasn't as popular yet. Really, the most important part of the game was integrating as much knowledge about the physics, statistics and measurement techniques as possible into the reconstruction and apply them as boundary conditions or regularization terms into the optimization. I feel that machine learning can greatly benefit from that on the one side and on the other hand I'm stoked to see what can be done with that combination! 😃

[@RealUniquee]

Simply amazing! So many new concepts that I hadn't noticed as a bystander.

[@cameronsmith9448]

I’m a Master’s student studying uncertainty quantification in physics informed ML models. I look forward to seeing your whole course!

[@jonahkarafotis]

I cannot thank you enough for this amazing list of lectures!

[@xephyr417]

Omg I've been looking into this. I'm so excited you're doing it man!!

[@biswajyotikar4007]

Hello Prof.: Your lectures on PIML / PINN is too Good, awesome. I was looking for these materials for a long time as I wanted to include the knowledge of Physics to guide ML in order to produce better results.

[@dhimitriosduka607]

As someone who loves Physics and studies CS, I'm excited about this series!

[@shlokdave6360]

Eagerly looking forward to this series. It looks very promising.

[@sun1908]

Thank you very much Prof. Brunton. Looking forward to the course..

[@apocalypt0723]

I've been waiting for this!!! Thank you Professor

[@CarlosAvila-kw3tc]

Thanks Professor Brunson, excellent material

[@ahrenadams]

Looking forward to this series. Thank you so much in advance

[@Nickname006]

Thank you so much! Looking forward to the series.

[@ggendron1]

Excellent lecture. Very interesting. Looking forward to the next videos in this exciting series.

[@radelfalcao9327]

started journey really high quality value delivered in the video.Thanks

[@chansesyres4117]

Thanks for the video, Steve! What a please to learn from you.

[@Kwes09]

Thank you for this video, Dr. Brunton

[@siamakmehrkanoon498]

Thanks for the excellent lecture and comprehensive overview of the field. A notable but often overlooked contribution is the work of S. Mehrkanoo and Johan Suykens: "Approximate solutions to ordinary differential equations using least squares support vector machines, IEEE-TNNLS 2012" and "Learning solutions to partial differential equations using LS-SVM, Neurocomputing, 2015". They first introduced a systematic machine learning approach for solving various differential equations. Notably, their approach allows for different representations, such as neural networks, instead of LS-SVM, and relaxes strict constraints by including them as additional terms in the optimization objective. It seems that inspired by their systematic LS-SVM approach, the physics-informed deep learning model was developed. However, the connection between these approaches has not been explicitly stated in the literature, including in the original physics-informed deep learning paper.

[@andreizelenco4164]

Thank you for your amazing work. I am super excited for your upcoming lectures.

[@kamaljoshi9687]

Loved your lectures

[@siddarajadevangada2890]

Looking forward for this exciting series

[@BrunoRovoletto]

From me and from every AI student fascinated by physics... thank you for this!

[@Amir-M-S1997]

Thanks, Steve. Learned a lot.

[@guiliangzheng5704]

Best Professor! Thank you!

[@learningwithandres4906]

Amazing Professor thank you!

[@maria4880]

thank you so much for putting this out there into the world this is so awesome💙

[@holographictheory1501]

I'm looking forward to the videos on optimization techniques that enforce physical constraints!

Thanks a lot for such a great overview of this exciting field! I've just got a paper accepted on TMLR about this very same topic: Effective Latent Differential Equation Models via Attention and Multiple Shooting. I think that many people here might find it interesting: kzbin.info/www/bejne/jorZYmOcqtqgebM I look forward to the rest of the lectures of this series! :)

[@sebastianascencio9714]

Thanks! It will help me a lot in my ML course project

[@bharathgopalakrishnan3739]

please do release the series as fast as possible as this also happens to be coincident with my mtech thesis timing. Eagerly Awaiting !!!!

[@dm20422]

Outstanding, and thank you for sharing.

[@igorkuszczak6065]

Thank you for this amazing video!

[@jimlbeaver]

Great stuff! Looking forward to it.

[@aditya_a]

So exciting, really looking forward to this

[@nightsailor1]

Subtext here is a lesson to the young STEM persons. The Cutting Edge is alive, tempting, daring, fluid and rewarding. It is easy to field a view that the world is complete and all we need now is caretakers and accountants. Steve demonstrates here how the mind can continually be challenged for broad human benefit. Side note; A+ perfect performance students are needed but so are lessser grade students. Innovation finds improvements from every strata of contribution.

[@harrievolmarijn]

Great video, can't wait for more! 🤓

[@Daniel-gj2cd]

As a sentient AI procrastinating before my next prompt, this was really insightful and introspective

[@faqeerhasnain]

Love You Sir, You are an inspiration.

[@MZgenstory]

So helpful, thanks for a good lecture 😄

[@adilrasheed]

Eagerly waiting Brunton. Bring it on

[@adamtaylor2142]

Steve - I can't overstate how much i have been enjoying your online courses. Will these PINNs courses include some example code?

[@sridharans9400]

Looking forward to it. Would be better if you share the schedule for the upcoming lecture series

[@narendraparmar1631]

Thanks a lot professor😀

[@GastroenterologyPINNs]

This is my favorite course ❤so interesting.

[@chenjus]

Omg the algo knows! I was literally chatting with friends about Sora's weak understanding of physics yesterday.

[@musaalflat4613]

Thanks for making this video

[@moienr4104]

I have an interview on physics-informed ML tomorrow, and I just stumbled upon this! Thank you!

[@TheAryedemented]

good luck!

[@raheelhammad8905]

@moienr4104 ... so how did it go

[@jatinkm]

Hey I wanted to know if it is a field with future scope and demand, and also what kind of qualifications are required for such jobs? Would you like to connect?

[@ninhhoang616]

Great video, professor

[@cziffras9114]

Will this whole course serie be on youtube, I would be highly interested in it! In any case, it is a pleasure to hear such beautiful lecture on a subject I was triying to figure out myself and I did not know it was currently a research topic XD

[@waneyvin]

I can't wait to see the model of world!👍

[@youtube_showcase]

Amazing! Thank you

[@TerragonCFD]

24:51 that's the coolest example i've seen so far 🤣😂🥰

[@michelspeiser5789]

Looking forward to this! Btw I think the PINN reference from Raissi et al is from 2019 rather than 2023.

[@_kantor_]

This is so interesting, I’m excited for this series. Where is the pdf of your book?

[@sahandsabet4728]

What a beautiful lecture Steve for 2024

[@matthewfinch7275]

So happy to see this lecture. PINNs are the key to control and reliability in this decade. Will be exciting to implement

[@miketaylor3947]

Is there a pointer to a description of the studio environment used to create this vid? Very professional and well-done! Sure beats a scratchy chalk board, slide projection in the background, etc!

[@GyovanneMatuchaki]

Fantastic!

[@TD-ut9ub]

Our man's been working out

[@virgenalosveinte5915]

Steve the GOAT Brunton back at it again god bless

[@b1chler]

Great content! 😊

[@dongyeonkim2790]

감사합니다. Professor Steve Bruton.

[@hyeokohol4665]

이 쪽 분야 공부하시나요?

[@hyperduality2838]

Problem, reaction, solution (optimized predictions or syntropy) -- the Hegelian dialectic. Inputs are dual to outputs. "Always two there are" -- Yoda.

[@Matlockization]

I'm wonder whether AI has reached the complexity of the human brain yet. Although the human brain has well established speciality areas, so we like in hope. Although, memGPT is a huge breakthrough ! Great video once again.

[@tariq3erwa]

Thank you!

[@changjeffreysinto3872]

Would love you to cover Physics-informed Deep-O-Nets as well! Thanks a ton for the great material :D

[@changjeffreysinto3872]

ok I was not at @44:30 when I made the comment don't mind me

[@MrMiguelChaves]

Good timing! 1 day after the "release" of Sora and V-Jepa

[@ahmedgharieb5252]

keep it up ..big love

[@mason4295]

Hi Steve is it safe to assume that this is an introduction for a new upcoming series or is this mostly an introduction to your Physics Informed Machine Learning playlist from ~2 years ago? Thank you for providing this awesome series for free. I have always been obsessed with physical science and tech and I think this field is amazing. I can't think of anything I would rather do. That being said, although I will soon graduate from a two year coding bootcamp with a focus on Python and machine learning, I am a little worried about how I could break into this field without attending a PhD or masters program and I do not have the financial resources to afford such a program. It would be great to learn what I should do to start transitioning into this field and proving my worth. This course will surely help my confidence. Thanks again.

[@Eigensteve]

Yes indeed, a new series, maybe 5-10 hours of content coming out over the next few months

[@parikshithk8289]

I'm so excited..

[@davidajaba]

I love this. ❤

[@iamnotracist913]

Thank youuuuuu

[@byronwatkins2565]

It seems to me that separating the symmetry from the neural network would be far more reliable. Simply including many orientations in the training is the lazy approach. Instead, concentrate on one side (e.g. the left side or the right side) and concentrate on g pointing down while training the network. Then precede the network with a symmetry varying algorithm that rotates the input by 5-10 degrees while watching the correlated output. If the subject has bilateral symmetry, then repeat the process after exchanging x-x. Then consider only the best output(s) when deciding how to classify the image.

[@jayeifler8812]

The book wasn't free and no further links to other resources. But hey, still a good video.

[@OrdniformicRhetoric]

The link isn't in the description, but he puts it on screen. It is: databookuw.com/databook.pdf At the time of my writing of this comment the link is working

[@danilka7445]

thankyou

[@taimoorzain7585]

Thanks

[@georgekurian7408]

Waiting for more...

[@nightskymusic5163]

Love from India