How adlerzz/nnts works
This is a small TypeScript neural-network demo with vector and matrix primitives. Its intended workflow is to train a network on a small dataset, then evaluate inputs; that training and evaluation loop is commented out. As currently written, execution only creates and prints a vector. Network behavior and its supporting math are all in src/main.ts, so the graph separates those responsibilities without implying they are separate modules.
Main entry points: main.ts Main entry · models.ts Vector and matrix
Components 8
Other components
- Program runtime
- Main entry
src/main.ts - Training dataset
src/main.ts - Training loop
src/main.ts - Neural network
src/main.ts - Network math
src/main.ts - Vector and matrix
src/models.ts - Console output
Connections 10
- Program runtime → Main entry: runs
- Main entry → Vector and matrix: imports
src/main.ts - Main entry → Training dataset: defines
src/main.ts - Main entry → Training loop: defines
src/main.ts - Training loop → Training dataset: iterates
src/main.ts - Training loop → Neural network: trains
src/main.ts - Neural network → Vector and matrix: uses
src/main.ts - Neural network → Network math: calls
src/main.ts - Main entry → Vector and matrix: creates
src/main.ts - Main entry → Console output: prints
src/main.ts