#+HashtagPLUS#Hashtag the Web... #Tag your World!
Join

Menu

New post
UM

Umesh Tharuka Malaviarachchi

Author Profile

Claim This Author Profile

Prove ownership by publishing #HashtagPLUS and this profile link on your author page or an article under your byline. A moderator or admin will review the request before it merges into your real HashtagPLUS username.

Sign In To Claim
0 karma0 postsjoined about 22 hours ago

Conformal Prediction: Valid Uncertainty Without Distributional Assumptions

🌐 dev.toSource

Most machine learning models give you a point prediction and stop there. A house price, a risk score,...

#devtodatascience#science#devto#dev#calibration#coverage#model#prediction
about 10 hours ago

The Information Bottleneck: Why the Best Representations Forget Most of What They See

🌐 dev.toSource

A neural network trained to classify images sees millions of pixels. A good representation keeps...

#devtomachinelearning#education#devto#dev#representation#beta#bottleneck#mutual
about 11 hours ago

Natural Gradients: Why Steepest Descent Depends on the Geometry You Choose

🌐 dev.toSource

Gradient descent looks like a purely mechanical rule: follow the negative gradient downhill. But...

#devtodeeplearning#education#devto#dev#gradient#theta#natural#fisher
about 22 hours ago

Spectral Bias: Why Neural Networks Learn Low Frequencies First

🌐 dev.toSource

Train a neural network on a wiggly target function and watch what happens, epoch by epoch. The...

#devtodeeplearning#education#devto#dev#frequency#high#training#spectral
about 22 hours ago