Ronald J. Williams | |
|---|---|
| Born | Ronald James Williams 1945 (1945) Los Angeles,California, USA |
| Died | February 16, 2024(2024-02-16) (aged 78–79) |
| Other names | Ron J. Williams |
| Known for | Backpropagation Teacher forcing Policy gradient method |
| Academic background | |
| Education | California Institute of Technology UCSD |
| Doctoral advisor | Donald Werner Anderson |
| Other advisor | David Rumelhart |
| Academic work | |
| Institutions | UCSD Northeastern University |
Ronald James Williams (1945 – February 16, 2024)[1] was an American mathematician andcomputer scientist who spent the majority of his career atNortheastern University. He is considered one of the pioneers ofneural networks. In 1986, he co-authored the seminal paper inNature on thebackpropagation algorithm along withDavid Rumelhart andGeoffrey Hinton, which triggered a boom in neural network research.[2]
Williams was born inSouthern California. He studied atCalifornia Institute of Technology as a undergraduate student and received a B.S. in mathematics there in 1966. He received his M.A. and Ph.D. in mathematics, both atUniversity of California, San Diego (UCSD) in 1972 and 1975, respectively. His Ph.D. thesis was supervised by Donald Werner Anderson. He worked for a defense contractor for some time after graduation. From 1983 to 1986, Williams was a member of theParallel Distributed Processing research group headed byDavid Rumelhart at the Institute for Cognitive Science at UCSD.[3] In 1986, Williams accepted a professorship in computer science atNortheastern University inBoston, where he remained afterwards.[1]
In addition to the backpropagation paper, Williams made fundamental contributions to the fields ofrecurrent neural networks, where he, along with David Zipser, invented theteacher forcing algorithm[4] and made important contributions tobackpropagation through time.[5] Inreinforcement learning, Williams introduced the REINFORCE algorithm in 1992,[6][7] which became the firstpolicy gradient method.
Besides his works on neural networks, Williams, together with Wenxu Tong andMary Jo Ondrechen, developed Partial Order Optimum Likelihood (POOL), a machine learning method used in the prediction of active amino acids in protein structures. POOL is a maximum likelihood method with a monotonicity constraint and is a general predictor of properties that depend monotonically on the input features.[8]
| International | |
|---|---|
| Academics | |
