Circuit realization and hardware linearization of monotone operator equilibrium networks
Not on the map. Why?
Abstract (arXiv)
It is shown that the port behavior of a resistor-diode network corresponds to the solution of a ReLU monotone operator equilibrium network (a neural network in the limit of infinite depth), giving a parsimonious construction of a neural network in analog hardware. We furthermore show that the gradient of such a circuit can be computed directly in hardware, using a procedure we call hardware linearization. This allows the network to be trained in hardware, which we demonstrate with a device-level circuit simulation. We extend the results to cascades of resistor-diode networks, which can be used to implement feedforward and other asymmetric networks. We finally show that different nonlinear elements give rise to different activation functions, and introduce the novel diode ReLU which is induced by a non-ideal diode model.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 65 references that are in the map. First posted on arXiv 17 Sep 2025.
Builds on
28 of 65 references.
References · 28
- 2019Deep Equilibrium Modelscited by 615
- 2016Error bounds for approximations with deep ReLU networkscited by 574
- 2016Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagationcited by 259
- 2015Adding Gradient Noise Improves Learning for Very Deep Networkscited by 145
- 2020Monotone operator equilibrium networkscited by 100
- 2020Training End-to-End Analog Neural Networks with Equilibrium Propagationcited by 63
- 2020Lipschitz Bounded Equilibrium Networkscited by 49
- 2018Training of photonic neural networks through in situ backpropagationcited by 45
- 2021Recurrent Equilibrium Networks: Flexible Dynamic Models with Guaranteed Stability and Robustnesscited by 45
- 2022Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networkscited by 44
- 2021A flexible and fast PyTorch toolkit for simulating training and inference on analog crossbar arrayscited by 39
- 2023Energy-based learning algorithms for analog computing: a comparative studycited by 37
16 more
- 2018Deep Neural Network Structures Solving Variational Inequalitiescited by 26
- 2023Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterialcited by 20
- 2024Quantum Equilibrium Propagation for efficient training of quantum systems based on Onsager reciprocitycited by 9
- 2023Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equationscited by 8
- 2023A universal approximation theorem for nonlinear resistive networkscited by 6
- 2024A Fast Algorithm to Simulate Nonlinear Resistive Networkscited by 6
- 2025Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functionscited by 5
- 2021Monotone one-port circuitscited by 2
- 2022Circuit Analysis using Monotone+Skew Splittingcited by 2
- 2023Non-Euclidean Monotone Operator Theory and Applicationscited by 2
- 2024Learning in memristive electrical circuitscited by 2
- 2024Optimization Algorithm Design via Electric Circuitscited by 2
- 2025Convergence of energy-based learning in linear resistive networkscited by 2
- 2023KirchhoffNet: A Scalable Ultra Fast Analog Neural Networkcited by 1
- 2025Arbitrarily Small Execution-Time Certificate: What was Missed in Analog Optimizationcited by 1
- 2025Operator-Splitting Methods for Neuromorphic Circuit Simulationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.