Fetching the paper…
Reading the bibliography…
When training neural networks, the use of Synthetic Gradients (SG) allows layers or modules to be trained without update locking - without waiting for a true error gradient to be backpropagated - resulting in Decoupled Neural Interfaces (DNIs).
Nonlinear programming, computational methods
Zoutendijk, G · 1970
Earlier work this paper cites.
Learning representations by back-propagating errors
Williams, DRGHR and Hinton, GE · 1986
Earlier work this paper cites.
Representational similarity analysis-connecting the branches of systems neuroscience
Kriegeskorte, Nikolaus, Mur, Marieke, and Bandettini, Peter A · 2008
Earlier work this paper cites.
How much gradient noise does a gradient-based linesearch method tolerate
Gratton, Serge, Toint, Philippe L, and Tröltzsch, Anke · 2011
Earlier work this paper cites.
Kickback cuts backprop’s red-tape: Biologically plausible credit assignment in neural networks
Balduzzi, David, Vanchinathan, Hastagiri, and Buhmann, Joachim · 2014
Earlier work this paper cites.
Adam: A method for stochastic optimization
Kingma, Diederik and Ba, Jimmy · 2014
Cited alongside, same era.
Towards biologically plausible deep learning
Bengio, Yoshua, Lee, Dong-Hyun, Bornschein, Jorg, Mesnard, Thomas, and Lin, Zhouhan · 2015
Cited alongside, same era.
Tensorflow: Large-scale machine learning on heterogeneous distributed systems
Abadi, Martín, Agarwal, Ashish, Barham, Paul, Brevdo, Eugene, Chen, Zhifeng, Citro, Craig, Corrado, Greg S, Davis, Andy, Dean, Jeffrey, Devin, Matthieu, et al · 2016
Cited alongside, same era.
Understanding intermediate layers using linear classifier probes
Alain, Guillaume and Bengio, Yoshua · 2016
Cited alongside, same era.
Learning in the machine: Random backpropagation and the learning channel
Decoupled neural interfaces using synthetic gradients
Jaderberg, Max, Czarnecki, Wojciech Marian, Osindero, Simon, Vinyals, Oriol, Graves, Alex, and Kavukcuoglu, Koray · 2016
Later among the works it cites.
Random synaptic feedback weights support error backpropagation for deep learning
Lillicrap, Timothy P, Cownden, Daniel, Tweed, Douglas B, and Akerman, Colin J · 2016
Later among the works it cites.
Toward an integration of deep learning and neuroscience
Marblestone, Adam H, Wayne, Greg, and Kording, Konrad P · 2016
Later among the works it cites.
Direct feedback alignment provides learning in deep neural networks
Nøkland, Arild · 2016
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Baldi, Pierre, Sadowski, Peter, and Lu, Zhiqin · 2016
Cited alongside, same era.