Exploration of Novel Neuromorphic Methodologies for Materials Applications
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929337198968832 |
|---|---|
| author | Gobin, Derek Snyder, Shay Cong, Guojing Kulkarni, Shruti R. Schuman, Catherine Parsa, Maryam |
| author_facet | Gobin, Derek Snyder, Shay Cong, Guojing Kulkarni, Shruti R. Schuman, Catherine Parsa, Maryam |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_04478 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploration of Novel Neuromorphic Methodologies for Materials Applications Gobin, Derek Snyder, Shay Cong, Guojing Kulkarni, Shruti R. Schuman, Catherine Parsa, Maryam Emerging Technologies 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. |
| title | Exploration of Novel Neuromorphic Methodologies for Materials Applications |
| topic | Emerging Technologies |
| url | https://arxiv.org/abs/2405.04478 |