面向材料应用的新型神经形态方法探索
Exploration of Novel Neuromorphic Methodologies for Materials Applications
AI总结:
本文探索储备池计算与超维计算两种神经形态方法,在Materials Project子集上进行带隙分类与回归,发现超维计算能更有效地表示分子图。
摘要:
当今许多最有趣的问题都涉及理解和解释基于图的结构中的复杂关系。例如,在材料科学中,预测材料性质通常依赖于分析原子相互作用的复杂网络。图神经网络(GNNs)已成为处理这些任务的流行方法;然而,它们存在硬件利用效率低和过度平滑等局限性。神经形态计算的最新进展为这些挑战提供了有前景的解决方案。在这项工作中,我们评估了两种此类神经形态策略,即储备池计算和超维计算。我们使用Materials Project数据集的一个子集,比较了两种方法在带隙分类和回归任务上的性能。我们的结果表明,超维计算的最新进展可以有效地应用于更好地表示分子图。
英文摘要:
Many of today's most interesting questions involve understanding and interpreting complex relationships within graph-based structures. For instance, in materials science, predicting material properties often relies on analyzing the intricate network of atomic interactions. Graph neural networks (GNNs) have emerged as a popular approach for these tasks; however, they suffer from limitations such as inefficient hardware utilization and over-smoothing. Recent advancements in neuromorphic computing offer promising solutions to these challenges. In this work, we evaluate two such neuromorphic strategies known as reservoir computing and hyperdimensional computing. We compare the performance of both approaches for bandgap classification and regression using a subset of the Materials Project dataset. Our results indicate recent advances in hyperdimensional computing can be applied effectively to better represent molecular graphs.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。