Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization

Arthur N. Montanari; Francesco Bullo; Dmitry Krotov; Adilson E. Motter

cs.LGApr 6, 2026

Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization

Authors: Arthur N. Montanari, Francesco Bullo, Dmitry Krotov, Adilson E. Motter

Organizations: Center for Network Dynamics and the Department of Physics & Astronomy, Northwestern University, Evanston, IL 60208, USA · Center for Control, Dynamical Systems, and Computation and the Department of Mechanical Engineering, University of California at Santa Barbara, Santa Barbara, CA 93106, USA · Independent Researcher, Cambridge, MA 02141, USA · Center for Network Dynamics, the Department of Physics & Astronomy, the Northwestern Institute on Complex Systems, and the Department of Engineering Sciences & Applied Mathematics, Northwestern University, Evanston, IL 60208, USA

Abstract

Recent advances at the intersection of control theory, neuroscience, and machine learning have revealed novel mechanisms by which dynamical systems perform computation. These advances encompass a wide range of conceptual, mathematical, and computational ideas, with applications for model learning and training, memory retrieval, data-driven control, and optimization. This tutorial focuses on neuro-inspired approaches to computation that aim to improve scalability, robustness, and energy efficiency across such tasks, bridging the gap between artificial and biological systems. Particular emphasis is placed on energy-based dynamical models that encode information through gradient flows and energy landscapes. We begin by reviewing classical formulations, such as continuous-time Hopfield networks and Boltzmann machines, and then extend the framework to modern developments. These include dense associative memory models for high-capacity storage, oscillator-based networks for large-scale optimization, and proximal-descent dynamics for composite and constrained reconstruction. The tutorial demonstrates how control-theoretic principles can guide the design of next-generation neurocomputing systems, steering the discussion beyond conventional feedforward and backpropagation-based approaches to artificial intelligence.

Figures & tables

Fig. 1: Dynamical systems used in neurocomputation, machine learning, and unconventional computing that admit EDM formulations (the acronyms are defined throughout the text). In biological neural systems, computation is most commonly interpreted as emerging from spiking activity and complex recurrent circuitry. In contrast, machine learning models simplify this representation to layered neural architectures with feedforward signal propagation and static nonlinear activations, which facilitate training and inference. Unconventional computing, on the other hand, exploits the intrinsic physical dynamics of analog hardware to perform computation; many such systems, including electronic oscillators, photonic devices, resistor networks, and spintronics, exhibit oscillatory or nonlinear dynamical behavior. The EDM formalism presented in this tutorial provides a unifying framework to study and design neurocomputational models across these three domains.

Fig. 2: Continuous-time Hopfield neural network for associative memory. (a) Neural network, where nodes represent individual neurons $x_{i}$ and edges represent pairwise interactions $W_{ij}$ . The activity of each neuron encodes the pixel intensity of a grayscale image, forming a memory pattern $\bm{\xi}^{(\mu)}$ corresponding to the letter N. (b) Schematic of the energy landscape of a high-dimensional Hopfield network. Stored memory patterns $\bm{\xi}^{(\mu)}$ are encoded as local minima of $\mathcal{E}(\bm{x})$ , and inference occurs as the network state $\bm{x}(t)$ relaxes from an initial condition $\bm{x}(0)$ toward a nearby minimum through gradient descent. The energy landscape may contain undesired local minima, known as spurious attractors. (c) Energy landscape $\mathcal{E}(\bm{x})$ of a Hopfield network with $N=2$ neurons and $K=2$ patterns. The contour levels are shown in the $(x_{1},x_{2})$ plane. (d) Hebbian learning adjusts the synaptic weights $W_{ij}$ so that the energy landscape can encode (store) the desired memory patterns as local minima. In this example, the energy landscape is initialized with random weights, yielding a monostable system. As the weights evolve according to Oja’s rule, the energy function encodes the desired patterns.

Fig. 3: Boltzmann machines for generative modeling and sampling-based inference. (a) Gibbs-Boltzmann distribution, plotted for increasing temperatures. States with higher energy are exponentially less likely to be sampled by the Boltzmann machine. (b) Evolution of the energy landscape via contrastive Hebbian learning. Blue and orange nodes represent states $\bm{x}$ sampled from the data distribution $\pi_{\rm data}$ and from the model distribution $\pi_{\theta}$ , respectively. Through this contrastive learning, the model reshapes the landscape so that configurations consistent with the data occupy low-energy regions, while inconsistent configurations are pushed to higher energy. Thus, the learned model samples data-like states with higher probability.

Fig. 4: Oscillatory associative memory models. (a) Binary memory patterns are encoded as phase-locked configurations, which form stable equilibria due to the second-harmonic coupling in OAMs. (b) Capacity scaling for small-error (left) and error-free (right) retrieval. The curves are shown for Hopfield networks (assuming binary random, orthogonal, and sparse patterns), DAMs (with different functions $F$ ), and OAMs (with different coupling strengths $\kappa$ ). (c) Stability diagram of the OAM, showing the distribution of $\lambda_{\rm max}(J(\bm{\xi}^{(\mu)}))$ for stored binary memory patterns, single-bit perturbations of those patterns, and random binary configurations. For a suitable choice of $\kappa$ , the desired memory patterns can be made stable while all other (undesired) configurations become unstable, thereby eliminating spurious attractors.

Fig. 5: Positive competitive network implementing sparse signal reconstruction via the proximal gradient dynamics. Each excitatory neuron $i$ receives feedforward drive $\Theta_{i}^{\top}\bm{u}$ proportional to its dictionary match, and is laterally inhibited by neuron $j$ with strength ${-}\Theta_{i}^{\top}\Theta_{j}\leq 0$ (for nonnegative dictionaries). A global bias $\lambda$ controls the sparsity level of the steady-state representation.

Fig. 6: E k -I network implementing winner-take-all competition. A set of

k

excitatory neurons project to a shared inhibitory interneuron, which in turn inhibits all excitatory neurons. Under the monostability condition

w_{\mathrm{EE}}<1

and the functionality condition

w_{\mathrm{IE}}\geq 1+w_{\mathrm{II}}

, the network selects the neuron receiving the strongest input while suppressing all others.

Explore similar work

The Forward-Backward Disconnect: State Dynamics, Credit Assignment, and Biological Grounding in Neural Computation
Aug 20, 2026Hadi Al Mubasher, Mariette AwadCredit Assignment Neural Network Training Dynamics
Department of Electrical and Computer Engineering, Maroun Semaan Faculty of Engineering and Architecture, American University of Beirut, Lebanon
minAction.net: Energy-First Neural Architecture Design -- From Biological Principles to Systematic Validation
Apr 27, 2026Martin G. FraschEnergy-Efficient ML Neural Network Optimization
Institute on Human Development and Disability, University of Washington, Seattle, WA 98195, USA · Health Stream Analytics, LLC, Seattle, WA, USA
Bio-inspired Learning and Decision-Making with Probabilistic In-Memory Computing Hardware: Part 1
Sep 10, 2026Thomas Dalgaty, Eiji Kawasaki, Miguel de Prado +2Compute-in-Memory Bayesian Inference
CEA-List, Grenoble, France

Aug 20, 2026J/K move · Enter open · S save

The Forward-Backward Disconnect: State Dynamics, Credit Assignment, and Biological Grounding in Neural Computation

Hadi Al Mubasher, Mariette Awad

Department of Electrical and Computer Engineering, Maroun Semaan Faculty of Engineering and Architecture, American University of Beirut, Lebanon

Credit Assignment Neural Network Training Dynamics Backpropagation Biologically Plausible Learning

Open paper AskPDF arXiv

A recurring pattern in neural computation is the reintroduction of dynamical and biological structure into models originally simplified for scalable optimization. Early feedforward networks reduced biological neurons to threshold or rate-like summation units, an abstraction compatible with global-gradient training at scale. Since then, forward computation has diversified: modern architectures carry recurrent state, retrieve from long contexts through attention and associative memory, compress histories through structured state-space dynamics, evolve in continuous time, settle to implicit equilibria, and communicate through sparse spikes. Training has diversified less. Scalable learning remains concentrated around backpropagation, backpropagation through time, adjoint methods, implicit differentiation, and surrogate-gradient variants. We call this asymmetry the forward-backward disconnect and develop a taxonomy spanning neural model families along three coupled axes: state-dynamics structure, credit-assignment mechanism, and biological grounding. Forward and learning grounding are treated separately, and the unit of analysis is the architecture-learning configuration rather than the architecture name alone. Across static, recurrent, attention-based, state-space, continuous-time, implicit, spiking, biologically plausible, and neuromorphic families, forward dynamics have diversified while the highest demonstrated scales remain concentrated in global or closely gradient-derived error-propagation mechanisms. Closing this disconnect requires better alignment among state dynamics, credit assignment, and computational substrate.

Abstract

Explore similar work

The Forward-Backward Disconnect: State Dynamics, Credit Assignment, and Biological Grounding in Neural Computation

minAction.net: Energy-First Neural Architecture Design -- From Biological Principles to Systematic Validation

Bio-inspired Learning and Decision-Making with Probabilistic In-Memory Computing Hardware: Part 1