Google的AlphaChip，用强化学习把Macro Placement——芯片布局中最难的部分——从几周压到了几小时。 几周变成几小时。 而且这件事登上了Nature封面。 你想一下这有多离谱。 AlphaChip是Google自研的AI加速器芯片，它的设计过程本身就是用AI来设计的——用深度强化学习 ...

Abstract: Modern global routers employ various routing methods to improve routing speed and quality. Maze routing is the most time-consuming process for existing global routing algorithms. This paper ...

These include such learning paradigms as Q-Learning and the Deep Q-Networks setups. Reinforcement Learning paradigms essentially aim at teaching robots to undertake certain actions that will be used ...

Abstract: Exact route matching is an important constraint for analog and mixed signal designs with nonuniform metal stacks. In this paper, we propose a constrained-path-based maze routing algorithm ...

Evolution has led to natural algorithms that regulate collective behavior in many biological systems. Here, we investigate natural algorithms that solve the shortest path problem, a basic optimization ...

It seems that every other day I have a work conversation about lacking documentation for complex processes, people getting caught up in incidents not knowing what they're supposed to do - other than ...