Rapid reconfiguration is an important capability of flexible production system supporting personalized customization. When the product requirement change and the existing capacity configuration of the production syste...
详细信息
Evolutionary algorithms are increasingly recognised as a viable computational approach for the automated optimisation of deep neural networks (DNNs) within artificial intelligence. this method extends to the training ...
详细信息
ISBN:
(纸本)9783031779404;9783031779411
Evolutionary algorithms are increasingly recognised as a viable computational approach for the automated optimisation of deep neural networks (DNNs) within artificial intelligence. this method extends to the training of DNNs, an approach known as neuroevolution. However, neuroevolution is an inherently resource-intensive process, with certain studies reporting the consumption of thousands of GPU days for refining and training a single DNN network. To address the computational challenges associated with neuroevolution while still attaining good DNN accuracy, surrogate models emerge as a pragmatic solution. Despite their potential, the integration of surrogate models into neuroevolution is still in its early stages, hindered by factors such as the effective use of high-dimensional data and the representation employed in neuroevolution. In this context, we address these challenges by employing a suitable representation based on Linear Genetic programming, denoted as NeuroLGP, and leveraging Kriging Partial Least Squares. the amalgamation of these two techniques culminates in our proposed methodology known as the NeuroLGP-Surrogate Model (NeuroLGP-SM). For comparison purposes, we also code and use a baseline approach incorporating a repair mechanism, a common practice in neuroevolution. Notably, the baseline approach surpasses the renowned VGG-16 model in accuracy. Given the computational intensity inherent in DNN operations, a singular run is typically the norm. To evaluate the efficacy of our proposed approach, we conducted 96 independent runs spanning a duration of 4weeks. Significantly, our methodologies consistently outperform the baseline, withthe SM model demonstrating superior accuracy or comparable results to the NeuroLGP approach. Noteworthy is the additional advantage that the SM approach exhibits a 25% reduction in computational requirements, further emphasising its efficiency for neuroevolution.
the proceedings contain 29 papers. the special focus in this conference is on NASA Formal Methods. the topics include: reasoning with Metric Temporal logic and Resettable Skewed Clocks;centralized Multi-agen...
ISBN:
(纸本)9783031331695
the proceedings contain 29 papers. the special focus in this conference is on NASA Formal Methods. the topics include: reasoning with Metric Temporal logic and Resettable Skewed Clocks;centralized Multi-agent Synthesis with Spatial Constraints via Mixed-Integer Quadratic programming;a Framework for Policy Based Negotiation;rewrite-Based Decomposition of Signal Temporal logic Specifications;Quantitative Verification and Strategy Synthesis for BDI Agents;Multi-objective Task Assignment and Multiagent Planning with Hybrid GPU-CPU Acceleration;reasoning over Test Specifications Using Assume-Guarantee Contracts;from the Standards to Silicon: Formally Proved Memory Controllers;Formalising Liveness Properties in Event-B withthe Reflexive EB4EB Framework;open- and Closed-Loop Neural Network Verification Using Polynomial Zonotopes;formalized High Level Synthesis with Applications to Cryptographic Hardware;From Natural Language Requirements to the Verification of Programmable logic Controllers: Integrating FRET into PLCverif;automata-Based Software Model Checking of Hyperproperties;condition Synthesis Realizability via Constrained Horn Clauses;a Toolkit for automated Testing of Dafny;Verified ALL(*) Parsing with Semantic Actions and Dynamic Input Validation;Subtropical Satisfiability for SMT Solving;a Linear Weight Transfer Rule for Local Search;adiar 1.1: Zero-Suppressed Decision Diagrams in External Memory;satisfiability of Non-linear Transcendental Arithmetic as a Certificate Search Problem;verifying Attention Robustness of Deep Neural Networks Against Semantic Perturbations;formalizing Piecewise Affine Activation Functions of Neural Networks in Coq;verifying an Aircraft Collision Avoidance Neural Network with Marabou;strategy Synthesis in Markov Decision Processes Under Limited Sampling Access;learning Symbolic Timed Models from Concrete Timed Data;reward Shaping from Hybrid Systems Models in Reinforcement Learning;conservative Safety Monitors of Stochastic Dynamical Sys
作者:
Chistikov, Dmitry
Department of Computer Science University of Warwick United Kingdom
Presburger arithmetic, or linear integer arithmetic (LIA), is a logicthat allows one to express linear constraints on integers: equalities, inequalities, and divisibility by nonzero n ∈ . More formally, it is the fi...
详细信息
the development of appropriate control strategies for building energy systems has been a challenging issue for the traditional planning process of building automation, especially facing the increasing complexity of bu...
详细信息
the use of assurance cases is gaining popularity, particularly in the safety-critical system industry, as an organized approach to submitting documentation for the safety and security certification of systems. However...
详细信息
the use of assurance cases is gaining popularity, particularly in the safety-critical system industry, as an organized approach to submitting documentation for the safety and security certification of systems. However, these arguments can become overwhelming and complicated, even for moderately complex systems. therefore, there is a compelling requirement to develop new automation strategies that can aid in creating and assessing assurance cases. Existing assurance-case tools primarily automate syntactic analysis, focusing on structural completeness, while providing limited or no support for semantically evaluating the logical aspects of the assurance case. In prior work, we introduced a framework called Assurance 2.0, which aims to enhance the rigor of assurance cases by emphasizing the reasoning process, evidence utilized, and explicit identification of counter-claims (defeaters) and counter-evidence. In this paper, we present a new approach to enhancing Assurance 2.0 by incorporating semantic rule-based analysis capabilities. Firstly, we systematically convert the assurance case into Prolog predicates and constraints. then, leveraging the analysis capabilities of the s(CASP), a goal-directed top-down solver for Constraints Answer Set Programs, we evaluate the semantic properties of assurance cases, including logical consistency, completeness, and indefeasibility. the application of these analyses provides both authors and evaluators with higher confidence when assessing the assurance case. 2023 Copyright for this paper by its authors.
We present an asymptotic improvement in the number of variables (n + m⌊log2(k − 1)⌋) required for state-of-the-art formulation of (max-)k-SAT problems when encoded as a quadratic unconstrained binary optimization (QUB...
详细信息
In the field of automated planning, an action is called reversible when other actions can be applied in order to revert the effects of this action and return to the original state. In recent years, there has been rene...
详细信息
this paper presents a software module for working with fuzzy logic inference systems in the context of fuzzy case-based reasoning. Fuzzy logic, providing tools for describing and handling uncertainty, is an important ...
详细信息
ISBN:
(数字)9798350371369
ISBN:
(纸本)9798350371376
this paper presents a software module for working with fuzzy logic inference systems in the context of fuzzy case-based reasoning. Fuzzy logic, providing tools for describing and handling uncertainty, is an important component of engineering practice. the considered free software is used in the National Research University "Moscow Power Engineering Institute" and is implemented in the process of teaching master's degree students of "Applied Mathematics and Computer Science" in the discipline "Actual Problems of Applied Mathematics and Computer Science".
this paper investigates the application of Vision Transformers (ViTs), specifically DETR (DEtection TRans-former), for the detection and classification of digital logic gates in hand-sketched digital logic circuits (D...
详细信息
暂无评论