相关论文: Holomorphic Equilibrium Propagation Computes Exact…

The backpropagation algorithm has experienced remarkable success in training large-scale artificial neural networks; however, its biological plausibility has been strongly criticized, and it remains an open question whether the brain…

In this work, we extend the Equilibrium Propagation framework to skew-gradient systems and show an equivalence between deep Energy-Based Models and Hamiltonian neural networks. We focus on networks of diffusively coupled Fitzhugh-Nagumo…

Backpropagation, a foundational algorithm for training artificial neural networks, predominates in contemporary deep learning. Although highly successful, it is widely considered biologically implausible, because it relies on precise…

While current deep learning algorithms have been successful for a wide variety of artificial intelligence (AI) tasks, including those involving structured image data, they present deep neurophysiological conceptual issues due to their…

Backpropagation is driving today's artificial neural networks (ANNs). However, despite extensive research, it remains unclear if the brain implements this algorithm. Among neuroscientists, reinforcement learning (RL) algorithms are often…

Back propagation (BP) is the default solution for gradient computation in neural network training. However, implementing BP-based training on various edge devices such as FPGA, microcontrollers (MCUs), and analog computing platforms face…

Training neural networks with reinforcement learning (RL) typically relies on backpropagation (BP), necessitating storage of activations from the forward pass for subsequent backward updates. Furthermore, backpropagating error signals…

While backpropagation (BP) has been applied to spiking neural networks (SNNs) achieving encouraging results, a key challenge involved is to backpropagate a continuous-valued loss over layers of spiking neurons exhibiting discontinuous…

The response time of physical computational elements is finite, and neurons are no exception. In hierarchical models of cortical networks each layer thus introduces a response lag. This inherent property of physical dynamical systems…

Deep learning models have gained great success in many real-world applications. However, most existing networks are typically designed in heuristic manners, thus lack of rigorous mathematical principles and derivations. Several recent…

Neuromorphic computing aims to replicate the brain's capabilities for energy efficient and parallel information processing, promising a solution to the increasing demand for faster and more efficient computational systems. Efficient…

Distinct from closed quantum systems, non-Hermitian system can have exceptional points (EPs) where both eigenvalues and eigenvectors coalesce. Recently, it has been proposed and demonstrated that EPs can enhance the performance of sensors…

Deep State Space Models (SSMs) reignite physics-grounded compute paradigms, as RNNs could natively be embodied into dynamical systems. This calls for dedicated learning algorithms obeying to core physical principles, with efficient…

Spiking neural networks (SNNs) promise orders-of-magnitude efficiency gains by communicating with sparse, event-driven spikes rather than dense numerical activations. However, most training pipelines either rely on surrogate-gradient…

Heterogeneous Graph Neural Networks (HGNNs) are widely used for deep learning on heterogeneous graphs. Typical end-to-end HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs.…

Ongoing studies have identified similarities between neural representations in biological networks and in deep artificial neural networks. This has led to renewed interest in developing analogies between the backpropagation learning…

We consider multi-value expansion planning (MEP), a general bilevel optimization model in which a planner optimizes arbitrary functions of the dispatch outcome in the presence of a partially controllable, competitive electricity market. The…

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Deep neural networks have enabled progress in a wide variety of applications. Growing the size of the neural network typically results in improved accuracy. As model sizes grow, the memory and compute requirements for training these models…

The ubiquitous backpropagation algorithm requires sequential updates through the network introducing a locking problem. In addition, back-propagation relies on the transpose of forward weight matrices to compute updates, introducing a…