🏋️  Squashing Function

Squashing Function#

Any bounded nonlinearity (sigmoid, tanh) that compresses its input range.

Important

✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.

What it is#

A squashing function is any function that compresses an unbounded input — any real number in \((-\infty, \infty)\) — into a bounded range, giving the characteristic S-shape. It “squashes” an infinite domain into a finite interval.

Examples#

The sigmoid squashes to (0, 1) (a probability), tanh to (−1, 1), and softmax squashes a vector of logits into probabilities on (0,1). They are the classic non-linear activations that let a network turn raw scores into interpretable, constrained outputs.

Why it matters#

Squashing is what converts an unbounded linear score (like the log-odds) into something usable — a probability, or a normalized signal — and the non-linearity is what lets stacked layers model complex patterns. Its flat tails are also the source of saturation and vanishing gradients.


Theme: Model Training & Optimization  ·  All terminology



See also

Source article Adapted (context, re-expressed) in our own words from: Squashing Function (insightful-data-lab.com).

Tags: purpose: reference topic: terminology level: intermediate