paper-with-me

Papers

Neuromimetic Linear Systems -- Resilience and Learning

2022-05-10 · Zexin Sun, John Baillieul

Building on our recent work on {\em neuromimetic control theory}, new results on resilience and neuro-inspired quantization are reported. The term neuromimetic refers to the models having features that are characteristic of the neurobiology of biological motor control. As in previous work, the focus is on what we call {\em overcomplete} linear systems that are characterized by larger numbers of input and output channels than the dimensions of the state. The specific contributions of the present paper include a proposed {\em resilient} observer whose operation tolerates output channel intermittency and even complete dropouts. Tying these ideas together with our previous work on resilient stability, a resilient separation principle is established. We also propose a {\em principled quantization} in which control signals are encoded as simple discrete inputs which act collectively through the many channels of input that are the hallmarks of the overcomplete models. Aligned with the neuromimetic paradigm, an {\em emulation} problem is proposed and this in turn defines an optimal quantization problem. Several possible solutions are discussed including direct combinatorial optimization, a Hebbian-like iterative learning algorithm, and a deep Q-learning (DQN) approach. For the problems being considered, machine learning approaches to optimization provide valuable insights regarding comparisons between optimal and nearby suboptimal solutions. These are useful in understanding the kinds of resilience to intermittency and channel dropouts that were earlier demonstrated for continuous systems.

📄 PDF Abstract BibTeX arXiv:2205.05013

Code (0)

등록된 구현이 없습니다.

Tasks

Combinatorial OptimizationQ-LearningQuantization

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

Emulation Learning for Neuromimetic Systems

2023-05-04 · Zexin Sun, John Baillieul

Building on our recent research on neural heuristic quantization systems, results on learning quantized motions and resilience to channel dropouts are reported. We propose a general emulation problem consistent with the …

Model Predictive ControlQuantizationTransfer Learning

Neuromimetic Control -- A Linear Model Paradigm

2021-04-27 · John Baillieul, Zexin Sun

Stylized models of the neurodynamics that underpin sensory motor control in animals are proposed and studied. The voluntary motions of animals are typically initiated by high level intentions created in the primary corte…

model

Model Predictive Control for Neuromimetic Quantized Systems

2022-12-19 · Zexin Sun, John Baillieul

Based on our recent research on neural heuristic quantization systems, we propose an emulation problem consistent with the neuromimetic paradigm. This optimal quantization problem can be solved with model predictive cont…

modelModel Predictive ControlQuantization

Brain in the Dark: Design Principles for Neuromimetic Inference under the Free Energy Principle

2025-02-13 · Mehran H. Bazargani, Szymon Urbas, Karl Friston

Deep learning has revolutionised artificial intelligence (AI) by enabling automatic feature extraction and function approximation from raw data. However, it faces challenges such as a lack of out-of-distribution generali…

Neuromimetic Dynamic Networks with Hebbian Learning

2023-10-03 · Zexin Sun, John Baillieul

Leveraging recent advances in neuroscience and control theory, this paper presents a neuromimetic network model with dynamic symmetric connections governed by Hebbian learning rules. Formal analysis grounded in graph the…