TY - GEN
T1 - Exploration of Novel Neuromorphic Methodologies for Materials Applications
AU - Gobin, Derek
AU - Snyder, Shay
AU - Cong, Guojing
AU - Kulkarni, Shruti R.
AU - Schuman, Catherine
AU - Parsa, Maryam
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - graph neural networks
KW - hyperdimensional computing
KW - liquid state machine
KW - materials science
KW - neuromorphic
KW - reservoir computing
KW - spatial semantic pointers
UR - http://www.scopus.com/inward/record.url?scp=85214692110&partnerID=8YFLogxK
U2 - 10.1109/ICONS62911.2024.00049
DO - 10.1109/ICONS62911.2024.00049
M3 - Conference contribution
AN - SCOPUS:85214692110
T3 - Proceedings - 2024 International Conference on Neuromorphic Systems, ICONS 2024
SP - 282
EP - 286
BT - Proceedings - 2024 International Conference on Neuromorphic Systems, ICONS 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 International Conference on Neuromorphic Systems, ICONS 2024
Y2 - 30 July 2024 through 2 August 2024
ER -