Differentiable programming

Related lectures (12)

Explores the connection between limit existence and function continuity, emphasizing derivative properties and function graphs.

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

Explores the definition and derivability of functions in differential calculus, emphasizing differentiability at specific points.

Explores convolutional neural networks, backpropagation, and stochastic gradient descent in deep learning.

Covers linear applications, rank, and ciphers, emphasizing the importance of understanding the rank of linear transformations.

Explores backward and central differences for numerical differentiation, analyzing their properties and error analysis.

Introduces Quasi-Newton methods for optimization, explaining their advantages over traditional approaches like Gradient Descent and Newton's Method.

Explores numerical differentiation using finite differences and addresses the impact of errors in computer computations.

Explores differentiability in two variables and the chain rule for compositions.

Introduces numerical optimization with Scipy, covering zero finding, problem dimensionality, derivatives, and advanced visualization techniques.

Introduces numerical root finding, differentiation, integration, and ODE solving using Scipy.

Explores numerical differentiation and integration methods, emphasizing the accuracy of finite differences in computing derivatives and integrals.

Page 1 of 1