Explore >> Select a destination
|
You are here 
|
jingnanshi.com | ||
| | | | |
iclr-blogposts.github.io
|
|
| | | | | The product between the Hessian of a function and a vector, the Hessian-vector product (HVP), is a fundamental quantity to study the variation of a function. It is ubiquitous in traditional optimization and machine learning. However, the computation of HVPs is often considered prohibitive in the context of deep learning, driving practitioners to use proxy quantities to evaluate the loss geometry. Standard automatic differentiation theory predicts that the computational complexity of an HVP is of the same order of magnitude as the complexity of computing a gradient. The goal of this blog post is to provide a practical counterpart to this theoretical result, showing that modern automatic differentiation frameworks, JAX and PyTorch, allow for efficient computat... | |
| | | | |
robotchinwag.com
|
|
| | | | | Deriving the gradients for the backward pass for matrix multiplication using tensor calculus | |
| | | | |
liorsinai.github.io
|
|
| | | | | A series on automatic differentiation in Julia. Part 1 provides an overview and defines explicit chain rules. | |
| | | | |
www.paepper.com
|
|
| | | [AI summary] This article explains how to train a simple neural network using Numpy in Python without relying on frameworks like TensorFlow or PyTorch, focusing on the implementation of ReLU activation, weight initialization, and gradient descent for optimization. | ||
