Steve Brunton Courses

Physics Informed Neural Networks (PINNs) - Introduction and Applications

3 ratings

Introduction to Physics Informed Neural Networks (PINNs): combining neural networks with physical laws to solve complex problems in fluid dynamics and beyond. Explores advantages, applications, and extensions of this innovative approach.

• YouTube
• 35 minutes
• Self-Paced
• Free Video

Singular Value Decomposition

2 ratings

Explore singular value decomposition for matrix approximation, data processing, image compression, regression, PCA, and randomized algorithms.

• YouTube
• 7 hours
• Self-Paced
• Free Video

Quality Control and Non-Destructive Inspection Using the Multinomial Distribution

2 ratings

Explore quality control principles through multinomial distribution, learning to assess batch reliability using non-destructive inspection methods and statistical sampling techniques.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

Taylor Series and Power Series Made Easy - Review of Calculus

2 ratings

Review Taylor and power series through sine and cosine expansions, with Python and MATLAB plots showing how higher-order terms improve approximations.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

Fluid Dynamics

1 rating

Learn how machine learning models turbulence, extracts flow patterns, and enables control of complex fluid dynamics.

• YouTube
• 6 hours
• Self-Paced
• Free Video

Data-Driven Science and Engineering

1 rating

Apply singular value decomposition and Fourier methods to analyze data, model dynamical systems, and develop machine-learning and control approaches.

• YouTube
• 20 hours
• Self-Paced
• Free Video

Data-Driven Control with Machine Learning

1 rating

Explores data-driven control through system identification, model reduction, optimization, and reinforcement learning.

• YouTube
• 11 hours
• Self-Paced
• Free Video

Control Bootcamp - Kalman Filter Example in Matlab

1 rating

Use a Kalman filter in MATLAB to estimate an inverted pendulum’s full state from a single noisy cart-position measurement.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

Probability and Statistics: An Introductory Overview

1 rating

Explore probability and statistics fundamentals, from basic concepts to advanced topics, covering applications, history, and key principles in data science and machine learning.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Conjugate Priors Example - Normal Distribution and the Exponential Family of Distributions

1 rating

Explore conjugate priors through Normal distributions and the Exponential Family, demonstrating how Normal likelihoods pair with Normal priors for Bayesian inference.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Linear Systems - Control Bootcamp

1 rating

Analyze linear systems of ordinary differential equations with eigenvalues and eigenvectors as the mathematical foundation for linear control theory.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

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

1 rating

Explore how to integrate physics into machine learning, enhancing model accuracy and efficiency in engineering applications. Learn to leverage prior physical knowledge across all stages of the ML process.

• YouTube
• 47 minutes
• Self-Paced
• Free Video

Fourier Analysis

Builds Fourier analysis from first principles into practical MATLAB and Python methods for transforms, FFT-based denoising, PDEs, spectrograms, wavelets, and image compression.

• YouTube
• 8 hours
• Self-Paced
• Free Video

Linear Algebra

Explores singular value decomposition, Fourier analysis, and compressed sensing through mathematical explanations and MATLAB/Python examples for compression, denoising, and reconstruction.

• YouTube
• 19 hours
• Self-Paced
• Free Video

Koopman Analysis

Analyze nonlinear dynamics through Koopman operator representations, HAVOK models, spectral analysis, compressed sensing, and control.

• YouTube
• 3 hours 30 minutes
• Self-Paced
• Free Video