Lu, Yukuan

TL;DR: - For categorical outcomes (e.g., classification), the negative log-likelihood corresponds to the cross-entropy loss. - For continuous outcomes (e.g., regression), assuming a Gaussian distribution, the negative log-likelihood corresponds to the Mean Squared Error (MSE) loss.

Sources:

1. Linux Services from Linux command line for you and me

This post elaborates the boot process of a Linux system. For details, read the bootup man page or Click here to read it online.

Sources:

1. Bernard Kolman, Robert C. Busby & Sharon Cutler Ros. (2014). Functions. Discrete Mathematical Structures (6th ed., pp. 206-246). Pearson.
2. John Hubbard; Barbara Burke Hubbard. (2015). Vector calculus, linear algebra, and differential forms: A unified approach (5th ed., pp. 9-11). Matrix Editions.

In this section we define the notion of a function, a special type of relation.

In 3-D Euclidean space, a sphere can be locally approximated as a plane. The proof is as follows.

Sources:

1. Deconvolution 2013 paper
2. Guided Backpropagation 2015 paperhttps://arxiv.org/abs/1412.6806)

Code: Jax Feature Attribution Methods

Sources:

1. Grad CAM (and Guided Grad CAM) 2015 paper
2. CAM 2015 paper (Bolei Zhou)
3. Guided Backpropagation

Code: Jax Feature Attribution Methods

Sources:

1. Logical Volume Manager (LVM) versus standard partitioning in Linux

->Image source

Sources:

1. Logical Volume Manager (LVM) versus standard partitioning in Linux

Source:

1. Yubei Chen's talk on unsupervised learning.
2. Nonlinear Dimensionality Reduction by Locally Linear Embedding 2000 paper.

Most of the figures in this article are sourced from Yubei Chen's course, EEC289A, at UC Davis.