Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures

• URL: http://arxiv.org/abs/2305.18701v3
• Date: Wed, 30 Oct 2024 22:38:06 GMT
• Title: Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures
• Authors: Devdhar Patel, Terrence Sejnowski, Hava Siegelmann,
• Abstract summary: biological control achieves remarkable performance while also optimizing computational energy expenditure and decision frequency. We propose a Decision Bounded Markov Decision Process (DB-MDP), that constrains the number of decisions and computational energy available to agents in reinforcement learning environments. We introduce a biologically-inspired, Temporally Layered Architecture (TLA), enabling agents to manage computational costs through two layers with distinct time scales and energy requirements.
• Score: 0.9831489366502302
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The current reinforcement learning framework focuses exclusively on performance, often at the expense of efficiency. In contrast, biological control achieves remarkable performance while also optimizing computational energy expenditure and decision frequency. We propose a Decision Bounded Markov Decision Process (DB-MDP), that constrains the number of decisions and computational energy available to agents in reinforcement learning environments. Our experiments demonstrate that existing reinforcement learning algorithms struggle within this framework, leading to either failure or suboptimal performance. To address this, we introduce a biologically-inspired, Temporally Layered Architecture (TLA), enabling agents to manage computational costs through two layers with distinct time scales and energy requirements. TLA achieves optimal performance in decision-bounded environments and in continuous control environments, it matches state-of-the-art performance while utilizing a fraction of the compute cost. Compared to current reinforcement learning algorithms that solely prioritize performance, our approach significantly lowers computational energy expenditure while maintaining performance. These findings establish a benchmark and pave the way for future research on energy and time-aware control.

Related papers

• Energy Considerations of Large Language Model Inference and Efficiency Optimizations [28.55549828393871]
  As large language models (LLMs) scale in size and adoption, their computational and environmental costs continue to rise. We systematically analyze the energy implications of common inference efficiency optimizations across diverse NLP and AI workloads. Our findings reveal that the proper application of relevant inference efficiency optimizations can reduce total energy use by up to 73% from unoptimized baselines.
  arXiv  Detail & Related papers  (2025-04-24T15:45:05Z)
• A Non-Invasive Load Monitoring Method for Edge Computing Based on MobileNetV3 and Dynamic Time Regulation [2.405805395043031]
  Methods based on machine learning and deep learning have achieved remarkable results in load decomposition accuracy. These methods generally suffer from high computational costs and huge memory requirements. This study proposes an innovative Dynamic Time Warping (DTW) algorithm in the time-frequency domain.
  arXiv  Detail & Related papers  (2025-04-22T06:43:33Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [70.91804882618243]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks. We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge. Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• Reinforcement Learning for Adaptive Resource Scheduling in Complex System Environments [8.315191578007857]
  This study presents a novel computer system performance optimization and adaptive workload management scheduling algorithm based on Q-learning. By contrast, Q-learning, a reinforcement learning algorithm, continuously learns from system state changes, enabling dynamic scheduling and resource optimization. This research provides a foundation for the integration of AI-driven adaptive scheduling in future large-scale systems, offering a scalable, intelligent solution to enhance system performance, reduce operating costs, and support sustainable energy consumption.
  arXiv  Detail & Related papers  (2024-11-08T05:58:09Z)
• Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management [8.08366903467967]
  We adapt the reinforcement learning framework to intensity control using choice-based network revenue management. We show that by utilizing the inherent discretization of the sample paths created by the jump points, one does not need to discretize the time horizon in advance.
  arXiv  Detail & Related papers  (2024-06-08T05:27:01Z)
• Energy-Efficient Federated Edge Learning with Streaming Data: A Lyapunov Optimization Approach [34.00679567444125]
  We develop a dynamic scheduling and resource allocation algorithm to address the inherent randomness in data arrivals and resource availability under long-term energy constraints. Our proposed algorithm makes adaptive decisions on device scheduling, computational capacity adjustment, and allocation of bandwidth and transmit power in every round. The effectiveness of our scheme is verified through simulation results, demonstrating improved learning performance and energy efficiency as compared to baseline schemes.
  arXiv  Detail & Related papers  (2024-05-20T14:13:22Z)
• Switchable Decision: Dynamic Neural Generation Networks [98.61113699324429]
  We propose a switchable decision to accelerate inference by dynamically assigning resources for each data instance. Our method benefits from less cost during inference while keeping the same accuracy.
  arXiv  Detail & Related papers  (2024-05-07T17:44:54Z)
• Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution [51.83951489847344]
  In robotics applications, smooth control signals are commonly preferred to reduce system wear and energy efficiency. In this work, we aim to bridge this performance gap by growing discrete action spaces from coarse to fine control resolution. Our work indicates that an adaptive control resolution in combination with value decomposition yields simple critic-only algorithms that yield surprisingly strong performance on continuous control tasks.
  arXiv  Detail & Related papers  (2024-04-05T17:58:37Z)
• Computation-efficient Deep Learning for Computer Vision: A Survey [121.84121397440337]
  Deep learning models have reached or even exceeded human-level performance in a range of visual perception tasks. Deep learning models usually demand significant computational resources, leading to impractical power consumption, latency, or carbon emissions in real-world scenarios. New research focus is computationally efficient deep learning, which strives to achieve satisfactory performance while minimizing the computational cost during inference.
  arXiv  Detail & Related papers  (2023-08-27T03:55:28Z)
• A Comparative Study of Machine Learning Algorithms for Anomaly Detection in Industrial Environments: Performance and Environmental Impact [62.997667081978825]
  This study seeks to address the demands of high-performance machine learning models with environmental sustainability. Traditional machine learning algorithms, such as Decision Trees and Random Forests, demonstrate robust efficiency and performance. However, superior outcomes were obtained with optimised configurations, albeit with a commensurate increase in resource consumption.
  arXiv  Detail & Related papers  (2023-07-01T15:18:00Z)
• Sustainable AIGC Workload Scheduling of Geo-Distributed Data Centers: A Multi-Agent Reinforcement Learning Approach [48.18355658448509]
  Recent breakthroughs in generative artificial intelligence have triggered a surge in demand for machine learning training, which poses significant cost burdens and environmental challenges due to its substantial energy consumption. Scheduling training jobs among geographically distributed cloud data centers unveils the opportunity to optimize the usage of computing capacity powered by inexpensive and low-carbon energy. We propose an algorithm based on multi-agent reinforcement learning and actor-critic methods to learn the optimal collaborative scheduling strategy through interacting with a cloud system built with real-life workload patterns, energy prices, and carbon intensities.
  arXiv  Detail & Related papers  (2023-04-17T02:12:30Z)
• Coverage and Capacity Optimization in STAR-RISs Assisted Networks: A Machine Learning Approach [102.00221938474344]
  A novel model is proposed for the coverage and capacity optimization of simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) assisted networks. A loss function-based update strategy is the core point, which is able to calculate weights for both loss functions of coverage and capacity by a min-norm solver at each update. The numerical results demonstrate that the investigated update strategy outperforms the fixed weight-based MO algorithms.
  arXiv  Detail & Related papers  (2022-04-13T13:52:22Z)
• Reinforcement Learning-Based Coverage Path Planning with Implicit Cellular Decomposition [5.2424255020469595]
  This paper provides a systematic analysis of the coverage problem and formulates it as an optimal stopping time problem. We show that reinforcement learning-based algorithms efficiently cover realistic unknown indoor environments.
  arXiv  Detail & Related papers  (2021-10-18T05:18:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.