Douglas B. Tweed

11 papers A* 1Journal 10
YearRankTypeTitle / Venue / Authors
2023 J jnl
Error bounds and dynamics of bootstrapping in actor-critic reinforcement learning.
Trans. Mach. Learn. Res.
Ahmed Zerouali, Douglas B. Tweed
2021 J jnl
On Bock's Conjecture Regarding the Adam Optimizer.
CoRR
Mohamed Akrout, Douglas B. Tweed
2019 A* conf
Deep Learning without Weight Transport.
NeurIPS
Mohamed Akrout, Collin Wilson, Peter Conway Humphreys, Timothy P. Lillicrap, Douglas B. Tweed
2019 J jnl
Deep Learning without Weight Transport.
CoRR
Mohamed Akrout, Collin Wilson, Peter Conway Humphreys, Timothy P. Lillicrap, Douglas B. Tweed
2017 J jnl
Deep Learning with Dynamic Spiking Neurons and Fixed Feedback Weights.
Neural Comput.
Arash Samadi, Timothy P. Lillicrap, Douglas B. Tweed
2014 J jnl
Random feedback weights support learning in deep neural networks.
CoRR
Timothy P. Lillicrap, Daniel Cownden, Douglas B. Tweed, Colin J. Akerman
2013 J jnl
Optimal Control by Direct Approximation of the Gradient of the Cost-to-Go.
Control. Intell. Syst.
Douglas B. Tweed
2012 J jnl
Adaptive Optimal Control Without Weight Transport.
Neural Comput.
Lakshminarayan V. Chinta, Douglas B. Tweed
2012 J jnl
Computational Advantages of Reverberating Loops for Sensorimotor Learning.
Neural Comput.
Kristen Fortney, Douglas B. Tweed
2008 J jnl
Sensitivity Derivatives for Flexible Sensorimotor Learning.
Neural Comput.
M. N. Abdelghani, Timothy P. Lillicrap, Douglas B. Tweed
1990 J jnl
The superior colliculus and spatiotemporal translation in the saccadic system.
Neural Networks
Douglas B. Tweed, Tutis Vilis