Fetching the paper…
Reading the bibliography…
We introduce frequency propagation, a learning algorithm for nonlinear physical networks.
W. Millar, “Cxvi. some general theorems for non-linear systems possessing resistance,” The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science
1951
Earlier work this paper cites.
C. Cherry, “Cxvii. some general theorems for non-linear systems possessing reactance,” The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science
1951
Earlier work this paper cites.
P. Baldi and F. Pineda, “Contrastive learning and neural oscillations,” Neural computation
1991
Earlier work this paper cites.
L. Bottou, “Large-scale machine learning with stochastic gradient descent,” in Proceedings of COMPSTAT’2010
2010
Earlier work this paper cites.
A. E. Pereda, “Electrical synapses and their functional interactions with chemical synapses,” Nature Reviews Neuroscience
2014
Earlier work this paper cites.
T. Akam and D. M. Kullmann, “Oscillatory multiplexing of population codes for selective communication in the mammalian brain,” Jan 2014
2014
Earlier work this paper cites.
A. M. Bastos, J. Vezoli, C. A. Bosman, J.-M. Schoffelen, R. Oostenveld, J. R. Dowdall, P. De Weerd, H. Kennedy, and P. Fries, “Visual areas exert feedforward and feedback influences through distinct frequency channels,” Neuron
2015
Earlier work this paper cites.
MIT press, 2016
I. Goodfellow, Y. Bengio, and A. Courville, Deep learning · 2016
Earlier work this paper cites.
B. Scellier and Y. Bengio, “Equilibrium propagation: Bridging the gap between energy-based models and backpropagation,” Frontiers in computational neuroscience
2017
Cited alongside, same era.
R. Naud and H. Sprekeler, “Sparse bursts optimize information transmission in a multiplexed neural code,” Proceedings of the National Academy of Sciences
2018
Cited alongside, same era.
2020
Cited alongside, same era.
M. Stern, C. Arinze, L. Perez, S. E. Palmer, and A. Murugan, “Supervised learning through physical changes in a mechanical system,” Jun 2020
2020
Cited alongside, same era.
M. Stern, D. Hexner, J. W. Rocks, and A. J. Liu, “Supervised learning in physical networks: From machine learning to learning machines,” Physical Review X
A. Payeur, J. Guerguiev, F. Zenke, B. A. Richards, and R. Naud, “Burst-dependent synaptic plasticity can coordinate learning in hierarchical circuits,” Nature neuroscience
2021
Later among the works it cites.
2022
Closest in time.
2022
Closest in time.
M. Stern and A. Murugan, “Learning without neurons in physical systems,” 2022
2022
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
2021
Cited alongside, same era.
2021
Cited alongside, same era.
2021
Cited alongside, same era.
B. Scellier, “A deep learning theory for neural networks grounded in physics,” PhD thesis, Université de Montréal
2021
Cited alongside, same era.
To avoid any confusion, we stress that θ j k \theta_{jk} is a scalar, whereas i ^ j k ( ⋅ ) \hat{i}_{jk}(\cdot) is a real-valued function. Thus, θ j k ( v j − v k ) \theta_{jk}\left(v_{j}-v_{k}\right) denotes the product of θ j k \theta_{jk} and v j − v k v_{j}-v_{k} , whereas i ^ j k ( v j − v k ) \hat{i}_{jk}(v_{j}-v_{k}) denotes the function i ^ j k \hat{i}_{jk} applied to the voltage v j − v k v_{j}-v_{k}
Cited in the paper.
In practical situations such as the squared error prediction, the cost function C C depends only on the state of output nodes ; therefore nudging requires injecting currents at output nodes only
Cited in the paper.
2022
Closest in time.
L. G. Wright, T. Onodera, M. M. Stein, T. Wang, D. T. Schachter, Z. Hu, and P. L. McMahon, “Deep physical neural networks trained with backpropagation,” Nature
2022
Closest in time.
J. D. Semedo, A. I. Jasper, A. Zandvakili, A. Krishna, A. Aschner, C. K. Machens, A. Kohn, and B. M. Yu, “Feedforward and feedback interactions between visual cortical areas use different population activity patterns,” Nature communications
2022
Closest in time.