The discussion centers on the intersection of machine learning and physics, specifically how data-driven models can replicate or replace traditional mathematical formulas in physics. Participants highlight a program developed at Cornell that successfully extracted equations of motion for a mechanical pendulum using data alone, demonstrating the potential of machine learning in scientific discovery. However, concerns are raised about the inability to explain results derived from machine learning, emphasizing the need for theoretical backing in scientific research. The conversation also touches on the practical applications of such technologies in fields like agriculture.
PREREQUISITESResearchers, physicists, data scientists, and anyone interested in the implications of machine learning in scientific discovery and its applications across various fields.
Are you investigating the question, whether the current physics (mathematical formulas) will be once replaced by neutral networks, which predict the outcome of experiments?Pring said:Nowadays, the machine learning of computer science is hot. It is based on data, and drove by data. Thus, a question is naturally coming out: the data in physics, and the models of data. I think it is a really empirical way to know how physicists do the same thing as the computer scientists.
That's a horror idea! I just think of the key idea 'from data to model' in physics instead of investigating it.A.T. said:Are you investigating the question, whether the current physics (mathematical formulas) will be once replaced by neutral networks, which predict the outcome of experiments?
jedishrfu said: