Notes on Loss Functions
AI
Loss Functions
A note on different loss functions.
Loss Function or Cost Function or Error Function
Background
Why Loss function
The purpose of loss function is to quantify the error between the output of an algorithm and the given target value.
Let’s say that I have 100 pieces of something and I want the algorithm to predict the number of pieces available. Here, 100 pieces are the ground truth or the target value. Now, if the algorithm predicts that there are only 90 pieces, there is a loss or error of 10 pieces.
Types of Loss Functions
- NCE
- InfoNCE
- NT-Xent
- Contrastive Loss
- Triplet Loss
Thoughts:
Citation
BibTeX citation:
@misc{kumar2024,
author = {Chandan Kumar},
title = {Notes on {Loss} {Functions}},
date = {2024-01-13},
langid = {en-GB}
}
For attribution, please cite this work as:
Chandan Kumar. 2024. “Notes on Loss Functions.”