Visualizing Data Using t-SNE

Name: Visualizing Data Using t-SNE
Uploaded: 2013-11-07T06:44:04Z
Duration: 55 min 10 s
Channel: Google TechTalks
Description: A Google Tech Talk by Laurens van der Maaten, co-creator of t-SNE, on visualizing high-dimensional data by mapping it to two dimensions. It explains how the technique works and how it compares with other visualization approaches.

Google TechTalks1 HN recommender · recommended in 1 month, 2013-2019

YouTube

204K views · 13 years ago · talk · evergreen

A Google Tech Talk by Laurens van der Maaten, co-creator of t-SNE, on visualizing high-dimensional data by mapping it to two dimensions. It explains how the technique works and how it compares with other visualization approaches.

HN people point to it as the canonical explanation from the method's author whenever t-SNE comes up.

Data visualization & information design Machine learning & deep learning #t-sne #datavisualization #machinelearning #high-dimensionaldata #embeddings

3 comments from Hacker News

@vankessel2019 · in “The Human Brain Can Create Structures in Up to 11 Dimensions”

Use non spatial dimensions as well, like color, size, and shape. You can also use clever projections like t-sne to reduce the number of dimensions while retaining some of the structure of the data ( ▶ this video )

CitesView on HN

@zoren2016 · in “A.I. Experiments”

Thanks for the offer. I've seen this ▶ this video and I think I understand how it works but still think the results are amazing.

CitesView on HN

@a1k0n2013 · in “Show HN: 3d Word Vectors with Neural Networks, T-SNE, and WebGL”

Barnes-Hut uses a quadtree, doesn't it? I don't know whether the code was adapted to use an octree in 3D instead; maybe it was? FWIW there's a really interesting Google techtalk on how it works: ▶ this video

Visualizing Data Using t-SNE

3 comments from Hacker News

Deep Visualization Toolbox

Transformers, the tech behind LLMs | Deep Learning Chapter 5

Bret Victor - Drawing Dynamic Visualizations

Attention in transformers, step-by-step | Deep Learning Chapter 6

Thinking outside the 10-dimensional box

Google Developers Day US - Theorizing from Data

Recent Developments in Deep Learning

H3: Tiling the Earth with Hexagons

I Solved Klotski

An Observation on Generalization

REcon 2013 - The Future of RE : Dynamic Binary Visualization (Christopher Domas)

Large Language Models from scratch

Neural Network Learns The Physics of Fluids and Smoke | Two Minute Papers #118

Neural Networks Demystified [Part 1: Data and Architecture]

15 Sorting Algorithms in 6 Minutes

Backpropagation, intuitively | Deep Learning Chapter 3

Visualization of Quantum Physics (Quantum Mechanics)

CS231n Winter 2016: Lecture1: Introduction and Historical Context

A Better Default Colormap for Matplotlib | SciPy 2015 | Nathaniel Smith and Stéfan van der Walt

Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition

Visualizing Data Using t-SNE

3 comments from Hacker News

Deep Visualization Toolbox

Transformers, the tech behind LLMs | Deep Learning Chapter 5

Bret Victor - Drawing Dynamic Visualizations

Attention in transformers, step-by-step | Deep Learning Chapter 6

Thinking outside the 10-dimensional box

Google Developers Day US - Theorizing from Data

Recent Developments in Deep Learning

H3: Tiling the Earth with Hexagons

I Solved Klotski

An Observation on Generalization

REcon 2013 - The Future of RE : Dynamic Binary Visualization (Christopher Domas)

Large Language Models from scratch

Neural Network Learns The Physics of Fluids and Smoke | Two Minute Papers #118

Neural Networks Demystified [Part 1: Data and Architecture]

15 Sorting Algorithms in 6 Minutes

Backpropagation, intuitively | Deep Learning Chapter 3

Visualization of Quantum Physics (Quantum Mechanics)

CS231n Winter 2016: Lecture1: Introduction and Historical Context

A Better Default Colormap for Matplotlib | SciPy 2015 | Nathaniel Smith and Stéfan van der Walt

Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition