Join our Telegram group for exclusive access to detailed discussions, resources, programming files used in the video, and extra support! It's all free-click the link below to join now. See you there! Telegram Group Link - telegram.me/elastropy_official
Hi @EmmanuelOseiTutu-n7v, thank you very much! I'm glad you found the presentation impressive. If you have any questions or need further clarification on any points, feel free to ask!
Hi @MOTIVAO, Thank you for your kind words! I'm glad to hear the video was easy to follow and helpful. To further reinforce the concepts, I've also created two additional tutorials on Newton's Law of Cooling and a system of ODEs. Feel free to check them out and let me know if you have any questions or feedback!
Hi @blackbuddhaa, thank you for your interest! Currently, we are not offering consultancy services on PINNs. However, we will be sure to inform you when we start. In the meantime, we encourage you to join our Telegram group (check in the pinned comment) for updates and to connect with others who share your interests. Feel free to reach out there as well!
Hi, Great tutorial keep it up, I wonder if we test the Neural network function approximation outside the range of the data it was trained on, what is the output?
Hi @aboudaladdin8604, Thank you for the feedback, glad you enjoyed the tutorial! 😊 Testing outside the training data range can lead to less reliable results since the network is better at interpolation than extrapolation. So, when extrapolating, it may not capture the correct physics accurately, and the results could deviate from the expected behavior. Building a general solution that performs well outside the domain is still a big research challenge in this field. However, techniques like transfer learning can help by adapting the model to new data ranges, although it may not always be perfect depending on the problem.
Hi @maham1976, Thank you so much for the positive feedback! 😊 You can find the instructions to get the source code for the notebook in this tutorial here: www.elastropy.com/more/unlock-free-source-codes. Feel free to check it out and reach out if you have any questions!
Hello. This video was really informative. Thanks for the good job done. Please can you share the link to have access to the Jupyter lab files you used for the presentation?
Hi @SumitKumar-qi2vc, applying PINNs to a system of ODEs or PDEs is super interesting! If you're interested, feel free to join our Telegram group (link in the first pinned comment) so we can discuss this further!
Join our Telegram group for exclusive access to detailed discussions, resources, programming files used in the video, and extra support! It's all free-click the link below to join now. See you there!
Telegram Group Link - telegram.me/elastropy_official
Well done sir.
Pretty impressive presentation
Hi @EmmanuelOseiTutu-n7v, thank you very much! I'm glad you found the presentation impressive. If you have any questions or need further clarification on any points, feel free to ask!
@@elastropy Could you please share the Jupyter Notebook. Thank you.
Great work, this video is complete and very easy to understand.
Hi @MOTIVAO, Thank you for your kind words! I'm glad to hear the video was easy to follow and helpful. To further reinforce the concepts, I've also created two additional tutorials on Newton's Law of Cooling and a system of ODEs. Feel free to check them out and let me know if you have any questions or feedback!
@@elastropy Indeed, keep up the great work
Please more videos, do you also do consulting? I needed some guidance with my research. Doing my PhD
Hi @blackbuddhaa, thank you for your interest! Currently, we are not offering consultancy services on PINNs. However, we will be sure to inform you when we start. In the meantime, we encourage you to join our Telegram group (check in the pinned comment) for updates and to connect with others who share your interests. Feel free to reach out there as well!
"Hi, I’m trying to understand PINNs, how they work, loss function settings, etc. Could you please explain it or point me to some helpful resources?"
awesome thank you
Hi @lysaait1711, you’re welcome! Glad you found the content awesome.
Hi, Great tutorial keep it up, I wonder if we test the Neural network function approximation outside the range of the data it was trained on, what is the output?
Hi @aboudaladdin8604, Thank you for the feedback, glad you enjoyed the tutorial! 😊 Testing outside the training data range can lead to less reliable results since the network is better at interpolation than extrapolation. So, when extrapolating, it may not capture the correct physics accurately, and the results could deviate from the expected behavior. Building a general solution that performs well outside the domain is still a big research challenge in this field. However, techniques like transfer learning can help by adapting the model to new data ranges, although it may not always be perfect depending on the problem.
"Hi, I’m trying to understand PINNs, how they work, loss function settings, etc. Could you please explain it or point me to some helpful resources?"
Hello
The video is really great!
Can you please share with us the link for the notebook you worked with in this tutorial??
Hi @maham1976, Thank you so much for the positive feedback! 😊 You can find the instructions to get the source code for the notebook in this tutorial here: www.elastropy.com/more/unlock-free-source-codes.
Feel free to check it out and reach out if you have any questions!
Hello. This video was really informative. Thanks for the good job done. Please can you share the link to have access to the Jupyter lab files you used for the presentation?
"Hi, I’m trying to understand PINNs, how they work, loss function settings, etc. Could you please explain it or point me to some helpful resources?"
Actually i want to apply this on system of differential equation.. Can u explain
Hi @SumitKumar-qi2vc, applying PINNs to a system of ODEs or PDEs is super interesting! If you're interested, feel free to join our Telegram group (link in the first pinned comment) so we can discuss this further!
Thanku so much @@elastropy
I am also trying to do this
Please leave code here for neural network architecture !