Syed Abdul Hanan
Author ProfileClaim 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.
🌐 dev.toSource
Deep Learning, Visually #20 Watch the Short: youtube.com/shorts/yYxpjlvW69s Why the...
🌐 dev.toSource
Weight initialization: why a network's dials must start different, and how big the random start should be
🌐 dev.toSource
Vanishing and exploding gradients: why blame fades or blows up on its way back through a deep network, and the fixes that made deep learning work
🌐 dev.toSource
Adam, step by step: why one shared step size fails, and how giving every dial its own fixes it
🌐 dev.toSource
Learning-rate schedules: start big, halve the step size every so often, and settle where one step size can't
🌐 dev.toSource
Loss functions turn every mistake into one number. Here's how squared and absolute loss score the same misses very differently
🌐 dev.toSource
Cross-entropy, the loss behind almost every classifier, as a landscape and as a bet
🌐 dev.toSource
Gradient descent, the walk every neural network takes while it learns, step by step with real numbers
🌐 dev.toSource
The chain rule, the idea that lets a network see through every one of its layers, with real numbers
🌐 dev.toSource
Backpropagation, step by step: how one backward pass hands every weight its share of the blame