Hello, Autoencoder / Fil

Fil

Vocateur.

Workspace

Published

Edited

Aug 2, 2020

5 stars

Hello

Hello, A5 Hello, PGLite INSEE Parquet Hello, apcach DruidJS worker Hello, Orbit Word Tour: 40k words and their friends Hello, spectral.js Hello, petite-vue Hello, @thi.ng/grid-iterators Hello, thumbhash Hello, SwissGL Hello, QOI (and glitches)Hello, orb Hello, cosmograph Hello, Tabulator Using d3.blur with Plot Math.cbrt Hello debounce Colorcet Hello, glii Hello, Open Meteo Hello, PyWavelets Hello, typesense Hello, libgif Hello, kmeans-engine Happy anniversary, Project Gutenberg!Hello, fflate Hello, ArchieML!Hello, d3-bboxCollide Hello, jsgeoda!Hello, EDTF!Hello, protovis!Hello, placekey Hello, fuse.js Hello, Reorder.js Hello, shadow DOM jszip Hello, procedural-gl Hello, qhull Hello, genetic-js DruidJS Hello, Tippy.js Hello, paintWorklet Big π

Hello, Autoencoder

Hello, Shakespearean UUIDs Hello, ccwt.js Hello, constrainautor Hello, talisman Hello, polygon-offset Hello p-queue Hello async-pool Hello rollup-plugin-ascii Hello, algebra.js Hello, pixi.js Hello, d3-render Hello zip/unzip Cumulative Wikipedia Donations HTML <details>regl texture Hello, npyjs Hello protobuf Hello, pencil touch Hello, LOESS Hello html2canvas legra maps color2css Hello, ecsy 2D point distributions Hello, delatin The gpu.js loop Dijkstra’s shortest-path tree Hello nojacko/Dijkstras-js Hello, tcort/dijkstrajs Hello, lambdabaa/dijkstra Hello, gpu.js v2 Hello jsqr Hello qrcode Hello SharedArrayBuffer Hello GamePad API Hello vtk.js Hello nd4js Hello Biofabric Travelling with a self-organizing map Hello glitch Hello UMAP-js Hello pandemonium Hello iocane Hello JSON-editor Hello d3-gridding Hello mljs/knn Worker Hello lalolib Image to GPU.js Image to blink.js Tissot's indicatrix Vega projections Hello WebCLGL Using d3-inertia with observable Video contouring 3 ngraph: pagerank, louvain…Union-Find Perceptron (simple statistics)mljs Hello h3-js Emoji Flags Hello, poisson-disk-sampling

Also listed in…

Clustering

Algorithms

Autoencoder = require('https://bundle.run/autoencoder@0.0.2')

data = require("@observablehq/iris").then(l =>

l.map(d =>

Object.assign([d.sepalLength, d.sepalWidth, d.petalLength, d.petalWidth], {

color: classify(d.species)

})

)

classify = d3.scaleOrdinal(d3.schemeAccent)

ae = {

replay;

const ae = new Autoencoder({

nInputs: data[0].length,

nHidden: 4,

scale: true,

activation

});

ae.fit(data, {

batchSize: 50,

iterations: 2000,

method,

stepSize: 0.05

});

return ae;

}

Y = ae.encode(data)

ae.decode(Y)

ae.predict(data) // same as decode(encode(data))

distances = ae

.predict(data)

.map((predicted, i) => Math.hypot(...predicted.map((d, j) => d - data[i][j])))

score = d3.quantile(distances, .9)

d3 = require("d3@6.0.0-rc.2")

import { select } from "@jashkenas/inputs"

Purpose-built for displays of data

Observable is your go-to platform for exploring data and creating expressive data visualizations. Use reactive JavaScript notebooks for prototyping and a collaborative canvas for visual data exploration and dashboard creation.

Learn more