Implementation:Tensorflow Tfjs Exports Regularizers

Knowledge Sources	Tensorflow_Tfjs TensorFlow.js API
Domains	Deep_Learning, Layers_API, Regularization
Last Updated	2026-02-10 06:00 GMT

Overview

This module provides the public API factory functions for creating weight regularizer instances in TensorFlow.js Layers. Regularizers add penalty terms to the loss function during training to prevent overfitting. The three factory functions correspond to L1 regularization, L2 regularization, and combined L1+L2 regularization, exposed under the tf.regularizers namespace.

Code Reference

Source Location

tfjs-layers/src/exports_regularizers.ts (GitHub)

Imports

import * as regularizers from './regularizers';
import {L1Args, L1L2, L1L2Args, L2Args, Regularizer} from './regularizers';

Factory Functions

l1l2

Creates a regularizer applying both L1 and L2 penalties: loss += sum(l1 * abs(x)) + sum(l2 * x^2).

export function l1l2(config?: L1L2Args): Regularizer

l1

Creates a regularizer applying L1 penalty only: loss += sum(l1 * abs(x)).

export function l1(config?: L1Args): Regularizer

l2

Creates a regularizer applying L2 penalty only: loss += sum(l2 * x^2).

export function l2(config?: L2Args): Regularizer

I/O Contract

Function	Input	Output
l1l2	L1L2Args ({l1?, l2?})	Regularizer
l1	L1Args ({l1})	Regularizer
l2	L2Args ({l2})	Regularizer

Usage Example

import * as tf from '@tensorflow/tfjs';

const model = tf.sequential();
model.add(tf.layers.dense({
  units: 64,
  kernelRegularizer: tf.regularizers.l1l2({l1: 0.01, l2: 0.01}),
  inputShape: [128]
}));

Related Pages

• Tensorflow_Tfjs_Regularizers - Underlying regularizer class implementations (L1L2, l1, l2)
• Tensorflow_Tfjs_Exports_Constraints - Factory functions for weight constraints
• Tensorflow_Tfjs_Exports_Initializers - Factory functions for weight initializers