Technology
t-SNE: Reduce Your Dimensions, Keep Your Clusters
2016-01-15
Download
Right click and do "save link as"
Ever tried to visualize a cluster of data points in 40 dimensions? Or even 4, for that matter? We prefer to stick to 2, or maybe 3 if we're feeling well-caffeinated. The t-SNE algorithm is one of the best tools on the market for doing dimensionality reduction when you have clustering in mind.
Relevant links:
https://www.youtube.com/watch?v=RJVL80Gg3lA
view more
More Episodes
Re - Release: How To Lose At Kaggle
2018-08-13
2018-08-13
Compliance Bias
2018-07-22
2018-07-22
AI Winter
2018-07-15
2018-07-15
Rerelease: How to Find New Things to Learn
2018-07-08
2018-07-08
Rerelease: Space Codes
2018-07-02
2018-07-02
Rerelease: Anscombe's Quartet
2018-06-25
2018-06-25
Rerelease: Hurricanes Produced
2018-06-18
2018-06-18
GDPR
2018-06-11
2018-06-11
Git for Data Scientists
2018-06-03
2018-06-03
Analytics Maturity
2018-05-20
2018-05-20
SHAP: Shapley Values in Machine Learning
2018-05-13
2018-05-13
AutoML
2018-04-30
2018-04-30
CPUs, GPUs, TPUs: Hardware for Deep Learning
2018-04-23
2018-04-23
A Technical Introduction to Capsule Networks
2018-04-16
2018-04-16
Convolutional Neural Nets
2018-04-02
2018-04-02
Get this podcast on your
phone, FREE
