Lectures related to Gradient | EPFL Graph Search

Covers tensors, loss functions, autograd, and convolutional layers in deep learning.

Explores gradient in scalar fields, directional derivatives, and level sets.

Covers a review of vector calculus and the Maxwell equations in electromagnetism.

Introduces differential operators, gradient, and divergence in vector fields.

Covers the analysis of scalar fields, including divergence, gradient, and Laplacian.

Explains necessary conditions for convergence in optimization problems.

Covers vector fields, gradient, divergence, heat flux, and stress tensors.

Covers methods of demonstrations and the Taylor formula for functions of several variables.

Covers derivability, linear applications, composition of functions, and the gradient vector.

Introduces the concept of fluid kinematics and explores properties, descriptions, and derivatives in fluid mechanics.

Covers the differentiability of functions of multiple variables and the significance of directional derivatives and gradients.

Covers optimization basics, including unconstrained optimization and gradient descent methods for finding optimal solutions.

Explores continuity equations and internal entropy production in various coordinate systems, emphasizing scalar functions and vector quantities.

Explores curl in 2D vector fields, demonstrating its rotation concept through examples and its application in physics.

Explores gradient, divergence, and integral theorems in vector calculus.

Explores the use of momentum in gradient descent to enhance speed and stability.

Covers the concepts of vector differentiation and convex functions.

Introduces gradient, Laplacian, Taylor formula, polynomial approximations, extrema, and Taylor series expansions in multiple variables.

Explores the connection between Riemannian and Euclidean gradients and Hessians at critical points.

Explores generalisations of functions and the concept of gradients in advanced analysis.