People Good

Ronald Williams — Pionir Backpropagation

Bersama Rumelhart & Hinton, menulis paper backpropagation 1986 yang merevolusi neural network. Kontribusi pada reinforcement learning.

Williams: backpropagation (1986, dengan Rumelhart & Williams), Ronald J. Williams, University of Massachusetts.

June 21, 2026 1 min people
#AI#sejarah#sains
Print

Ronald Williams

Biodata

  • Profesi: Computer scientist

Kontribusi

  • Backpropagation (1986) — paper seminal dengan Rumelhart & Hinton:

    “Learning representations by back-propagating errors”

  • REINFORCE algorithm (1992) — policy gradient untuk reinforcement learning
  • Machine learning di University of Massachusetts

Karier

  • UCSD (1980-an)
  • University of Massachusetts Amherst (1990-)

Legacy

Williams adalah salah satu 3 penulis paper backpropagation (dengan Rumelhart & Hinton). REINFORCE algorithm-nya menjadi fondasi policy gradient methods di RL modern.

Connected to

Not yet written

The following pages are referenced but don't exist yet — they'd make good future additions.

  • /concepts/backpropagation

References

  1. Wikipedia

Type at least 2 characters to search.

Press ↑ ↓ to navigate, ↵ to open, esc to close.