Skip to main content
Home
Browse packagesDocsSign in

@am/neuralnetwork@1.0.0
Built and signed on GitHub Actions

latest
AugustinMauroy/am-neuralnetwork

A simple neural network library for JavaScript and TypeScript.

This package works with Cloudflare Workers, Node.js, Deno, Bun, Browsers
This package works with Cloudflare Workers
This package works with Node.js
This package works with Deno
This package works with Bun
This package works with Browsers
JSR Score
100%
Published
4 weeks ago (1.0.0)
class Model

Represents a neural network model composed of a sequence of layers.

Properties

private
layers: Layer[]
private
lossFunction: Loss
private
metrics: string[]
private
optimizer: Optimizer

Methods

addLayer(layer: Layer): void

Adds a layer to the model.

compile(
optimizer: Optimizer,
lossFunction: Loss,
metrics: string[],
): void

Configures the model for training.

evaluate(
validationData: number[][],
validationLabels: number[][],
): { loss: number; accuracy?: number; }

Evaluates the model on a validation dataset.

fit(
trainingData: number[][],
trainingLabels: number[][],
epochs: number,
batchSize: number,
debugEpochEnabled?: boolean,
): Promise<void>

Trains the model for a fixed number of epochs (iterations on a dataset).

getConfig(): { layers: Array<{ name: string; config: Record<string, unknown>; }>; optimizer: Record<string, unknown>; lossFunction: Record<string, unknown>; metrics: string[]; }

Retrieves the configuration of the model.

getLayers(): Layer[]

Retrieves the layers of the model.

private
isTrainableLayer(layer: Layer): layer is TrainableLayer
predict(inputData: number[][]): number[][]

Generates output predictions for the input samples.

Retrieves the number of layers in the model.

Static Methods

load(modelJson: string): Model

Loads a model from a JSON string.

New Ticket: Report package

Please provide a reason for reporting this package. We will review your report and take appropriate action.

Please review the JSR usage policy before submitting a report.

Add Package

deno add jsr:@am/neuralnetwork

Import symbol

import { Model } from "@am/neuralnetwork";
or

Import directly with a jsr specifier

import { Model } from "jsr:@am/neuralnetwork";

Add Package

pnpm i jsr:@am/neuralnetwork
or (using pnpm 10.8 or older)
pnpm dlx jsr add @am/neuralnetwork

Import symbol

import { Model } from "@am/neuralnetwork";

Add Package

yarn add jsr:@am/neuralnetwork
or (using Yarn 4.8 or older)
yarn dlx jsr add @am/neuralnetwork

Import symbol

import { Model } from "@am/neuralnetwork";

Add Package

vlt install jsr:@am/neuralnetwork

Import symbol

import { Model } from "@am/neuralnetwork";

Add Package

npx jsr add @am/neuralnetwork

Import symbol

import { Model } from "@am/neuralnetwork";

Add Package

bunx jsr add @am/neuralnetwork

Import symbol

import { Model } from "@am/neuralnetwork";