Memristive Device Dynamic Behavior Prediction Dataset and Code

Harvard Dataverse hosts a dataset and code for predicting the dynamic behavior of memristive devices using recurrent neural networks. The dataset, created by Somayeh Rezaei, is approximately 755 MB in size and was last updated in March 2026. It contains data and scripts for replicating the computational research.

Use Cases

• Training recurrent neural network models to predict memristive device I-V characteristics.
• Benchmarking machine learning algorithms against physical device simulation data.
• Replicating the computational methodology from the associated research paper.
• Analyzing time-series data of electrical responses in nanoscale memory devices.

Strengths

• Dataset size is substantial at approximately 755 MB, indicating detailed data.
• Includes both dataset and replication code, facilitating reproducibility.
• Cross-platform presence on DataCite and Dataverse signals established sharing.

Limitations

• Exact row count, column names, and specific data schema are not provided.
• License information is not specified across any source.
• Conflicting last update dates exist: one source states 2026-02-24, another 2026-03 12.

Provenance

Source

Somayeh Rezaei via Harvard Dataverse.

Collection Method

Likely generated from simulations or experiments with memristive devices; method not explicitly detailed.

Time Range

null

Freshness

2026-03-12

Geography

null