Hacker News with Generative AI: Gradient Descent

How linear regression works intuitively and how it leads to gradient descent (briefer.cloud)
Learning, to a computer, is just turning bad guesses into better ones. In this post, we’ll see how that starts with a straight line: how linear regression makes the first guess, and gradient descent keeps improving it.
Machine Learning, Linear Regression, Gradient Descent
321 points by lucasfcosta 4 days ago | 100 comments
Finding paths of least action with gradient descent (2023) (greydanus.github.io)
The purpose of this simple post is to bring to attention a view of physics which isn’t often communicated in introductory courses: the view of physics as optimization.
Physics, Optimization, Gradient Descent
73 points by E-Reverance 13 days ago | 14 comments
State-space models can learn in-context by gradient descent (arxiv.org)
Deep state-space models (Deep SSMs) have shown capabilities for in-context learning on autoregressive tasks, similar to transformers. However, the architectural requirements and mechanisms enabling this in recurrent networks remain unclear.
Machine Learning, Deep Learning, Artificial Intelligence, Gradient Descent
86 points by dsalaj 195 days ago | 58 comments
Enterprise-add: Number addition in C using gradient descent (github.com/TruncatedDinoSour)
Machine Learning, Programming, C, Optimization, Gradient Descent
11 points by EveryPizza 327 days ago | 0 comments