相关论文: Differentiable Weightless Controllers: Learning Lo…

Contributions to AI: This paper proposes a neuro-symbolic search architecture integrating discrete rule-based logic with lightweight Neural Network Feedback Control (NNFC). Utilizing cascade filtering to isolate neural mispredictions while…

In this paper, a novel model-free wide-area damping control (WADC) method is proposed, which can achieve full decoupling of modes and damp multiple critical inter-area oscillations simultaneously using grid-connected voltage source…

Fully parallel neural network accelerators on field-programmable gate arrays (FPGAs) offer high throughput for latency-critical applications but face hardware resource constraints. Weightless neural networks (WNNs) efficiently replace…

Many autonomous robots aimed at source-seeking are studied, and their controls designed, using unicycle modeling and formulation. This is true not only for model-based controllers, but also for model-free, real-time control methods such as…

Augmenting algorithms with learned predictions is a promising approach for going beyond worst-case bounds. Dinitz, Im, Lavastida, Moseley, and Vassilvitskii~(2021) have demonstrated that a warm start with learned dual solutions can improve…

In this paper, we present the combined learning-and-control (CLC) approach, which is a new way to solve optimal control problems with unknown dynamics by unifying model-based control and data-driven learning. The key idea is simple: we…

Deterministic model predictive control (MPC), while powerful, is often insufficient for effectively controlling autonomous systems in the real-world. Factors such as environmental noise and model error can cause deviations from the expected…

Complex neural networks require substantial memory to store a large number of synaptic weights. This work introduces WINGs (Automatic Weight Generator for Secure and Storage-Efficient Deep Learning Models), a novel framework that…

Nonlinear systems, such as switching DC-DC boost or buck converters, have rich dynamics. A simple one-dimensional discrete-time model is used to analyze the boost or buck converter in discontinuous conduction mode. Seven different control…

We address the problem of computing a Minimum Weighted Vertex Cover (MWVC) in a decentralized network. MWVC, a classical NP-hard problem, is foundational in applications such as network monitoring and resource placement. We propose a fully…

Deep Reinforcement Learning (DRL) techniques have received significant attention in control and decision-making algorithms. Most applications involve complex decision-making systems, justified by the algorithms' computational power and…

We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most classic and simple classifiers. Current deep models learn…

We study the continuous-time structure of the difference-of-convex algorithm (DCA) for smooth DC decompositions with a strongly convex component. In dual coordinates, classical DCA is exactly the full-step explicit Euler discretization of a…

In this paper we investigate data-driven predictive control of discrete-time linear descriptor systems. Specifically, we give a tailored variant of Willems' fundamental lemma, which shows that for descriptor systems the non-parametric…

Our results reveal that a well-regularized shallow architecture can serve as a highly competitive baseline across heterogeneous domains - from smart-city surveillance to agricultural variety classification - without requiring large GPUs or…

Deep reinforcement learning offers a model-free alternative to supervised deep learning and classical optimization for solving the transmit power control problem in wireless networks. The multi-agent deep reinforcement learning approach…

This paper deals with differentiable dynamical models congruent with neural process theories that cast brain function as the hierarchical refinement of an internal generative model explaining observations. Our work extends existing…

Combining neural networks with continuous logic and multicriteria decision making tools can reduce the black box nature of neural models. In this study, we show that nilpotent logical systems offer an appropriate mathematical framework for…

Differential graphical models are designed to represent the difference between the conditional dependence structures of two groups, thus are of particular interest for scientific investigation. Motivated by modern applications, this…

Learning dynamical systems through purely data-driven methods is challenging as they do not learn the underlying conservation laws that enable them to correctly generalize. Existing port-Hamiltonian neural network methods have recently been…