Machine Learning & Simulation

This channel creates explanatory videos covering topics in machine learning and simulation. The content includes probabilistic machine learning, high-performance computing, continuum mechanics, numerical analysis, computational fluid dynamics, automatic differentiation, and adjoint methods. Many videos feature hands-on coding in Python, Julia, or C++, showcasing modern libraries like JAX, TensorFlow Probability, NumPy, SciPy, FEniCS, and PETSc.

Recent videos demonstrate a focus on differentiable physics and neural emulators for partial differential equations, often using the JAX library. Specific topics covered include neural-hybrid correctors, data assimilation, inverse problems, the Kolmogorov flow, and the Lyapunov spectrum of chaotic systems. The channel states that all material is also available on its associated GitHub repository.