Results 141 to 150 of about 376,950 (319)
Advanced Intelligent Systems, EarlyView.This work harnesses nonidealities in analog in‐memory computing (IMC) by training physical neural networks modeled with ordinary differential equations. A differentiable spike‐time discretization accelerates training by 20× and reduces memory usage by 100×, enabling large IMC‐equivalent models to learn the CIFAR‐10 dataset.
Yusuke Sakemi +5 more
wiley +1 more source
Learning Robust Search Strategies Using a Bandit-Based Approach
, 2018 Effective solving of constraint problems often requires choosing good or specific search heuristics. However, choosing or designing a good search heuristic is non-trivial and is often a manual process.
Xia, Wei, Yap, Roland H. C.
core +1 more source
Worst-case analysis of two travelling salesman heuristics
, 1984 H.L. Ong, Jarrod Moore
openalex +1 more source
Heuristics, LPs, and Trees on Trees: Network Design Analyses [PDF]
, 1996 Anantaram Balakrishnan +2 more
openalex +1 more source
Enhancing Microrobot Swarm Stability and Adaptation by Autonomous Field‐of‐View Planning
Advanced Intelligent Systems, EarlyView.This work presents an adaptive cross‐field‐of‐view navigation strategy for microrobot swarms in large‐scale workspaces by integrating global path planning via A* and local replanning using optimized informed rapidly‐exploring random tree star . The hybrid approach ensures efficient and robust trajectory execution in dynamic environments, enhancing the ...
Zhaowen Su +3 more
wiley +1 more source
The optimal fin profile — a study in heuristics and rigor
, 1987 Arthur David Snider
openalex +1 more source
Advanced Intelligent Systems, EarlyView.This perspective article considers what computations optical computing can and should enable. Focusing upon free‐space optical computing, it argues that a codesign approach whereby materials, devices, architectures, and algorithms are simultaneously optimized is needed.
Prasad P. Iyer +6 more
wiley +1 more source
Sensitivity analysis of the greedy heuristic for binary knapsack problems [PDF]
Greedy heuristics are a popular choice of heuristics when we have to solve a large variety of NP -hard combinatorial problems. In particular for binary knapsack problems, these heuristics generate good results.
Chakravarti, N., Ghosh, D., Sierksma, G.
core +1 more source
Learning Optimal Crowd Evacuation from Scratch Through Self‐Play
Advanced Intelligent Systems, EarlyView.How would a superintelligent crowd behave in emergencies? This study develops an approach using multiagent deep reinforcement learning combined with self‐play to discover optimal evacuation strategies for pressure‐aware agents. The model learns behaviors such as queuing and zipper‐merging that significantly surpass traditional approaches in fatality ...
Mahdi Nasiri +3 more
wiley +1 more source