03/20/2025, 10:15 AM UTC
新型忆阻器对抗人工智能的“灾难性遗忘”问题Novel Memristors to Combat the 'Catastrophic Forgetting' of AI
于利希研究所在《自然通讯》杂志上介绍了新型忆阻组件，相较于之前的版本，这些组件具有显著的优点。这些忆阻器更加坚固，在更宽的电压范围内工作，并且可以用于模拟和数字模式。它们可以解决人工神经网络中的“灾难性遗忘”问题，即学习到的信息突然丢失。
研究人员已将新型忆阻元件应用于人工神经网络模型，在模式识别方面达到了高精度。他们计划寻找可能比当前版本表现更好的忆阻器材料。
Jülich researchers have introduced novel memristive components in Nature Communications, offering significant advantages over previous versions. These memristors are more robust, operate within a wider voltage range, and can be used in both analog and digital modes. They could address the issue of 'catastrophic forgetting' in artificial neural networks, where learned information is abruptly lost.
The researchers have implemented the new memristive element in a model of artificial neural networks, achieving high accuracy in pattern recognition. They plan to seek further materials for memristors that may perform even better than the current version.
---
本文由大语言模型（LLM）生成，旨在为读者提供半导体新闻内容的知识扩展（Beta）。
