Fetching the paper…

Reading the bibliography…

2019

Using local plasticity rules to train recurrent neural networks

Marschall, Owen, Cho, Kyunghyun, Savin, Cristina

Original
PDF
Post on X

Understand

To learn useful dynamics on long time scales, neurons must use plasticity rules that account for long-term, circuit-wide effects of synaptic changes.

In other words, neural circuits must solve a credit assignment problem to appropriately assign responsibility for global network behavior to individual circuit components.
Furthermore, biological constraints demand that plasticity rules are spatially and temporally local; that is, synaptic changes can depend only on variables accessible to the pre- and postsynaptic neurons.
While artificial intelligence offers a computational solution for credit assignment, namely backpropagation through time (BPTT), this solution is wildly biologically implausible.

Using local plasticity rules to train recurrent neural networks · Around

Built on

J. T. Dudman, D. Tsay, and S. A. Siegelbaum, “A role for synaptic inputs at distal dendrites: instructive signals for hippocampal long-term plasticity,”
2007
Earlier work this paper cites.
D. Sussillo and L. F. Abbott, “Generating coherent patterns of activity from chaotic neural networks,”
2009
Earlier work this paper cites.
R. Pascanu, T. Mikolov, and Y. Bengio, “On the difficulty of training recurrent neural networks,” in
2013
Earlier work this paper cites.

Similar

P. Somogyi, L. Katona, T. Klausberger, B. Lasztóczi, and T. J. Viney, “Temporal redistribution of inhibition over neuronal subcellular domains underlies state-dependent rhythmic change of excitability in the hippocampus,”
2014
Cited alongside, same era.
S. Pitis, “Recurrent neural networks in tensorflow i.”
2016
Cited alongside, same era.

Then

M. Jaderberg, W. M. Czarnecki, S. Osindero, O. Vinyals, A. Graves, D. Silver, and K. Kavukcuoglu, “Decoupled neural interfaces using synthetic gradients,” in
2017
Later among the works it cites.
J. Guerguiev, T. P. Lillicrap, and B. A. Richards, “Towards deep learning with segregated dendrites,”
Original
2017
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…