Open in the console1 link · 1 kind
Export
forward-mode differentiation
/wiki/forward-mode-differentiation
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in Claude
Sending this to someone?
MarkdownPlain text for notes apps and AI chats
WordA document to edit and annotate
PDFA4, for printing and sharing
ZIPEverything: the documents, the data, and instructions for AI assistants
With its linksA pack for Claude, ChatGPT, Gemini or NotebookLM, or STIX and CSV, from the console
Share the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
stub ·
1 feed
forward-mode differentiation
Automatic differentiation approach that propagates derivatives forward from inputs to outputs, requiring one sweep per input
Intelligence coverage
Automatic differentiation approach that propagates derivatives forward from inputs to outputs, requiring one sweep per input.
Drawn from 1 news source; the facts and relationships below show where each detail comes from.
Detection 1
Requires one sweep per input parameter
Superseded by 1
Sources 1
- What loss.backward() actually does · Hacker News (YC)