Optimal Hyperparameters for Transfer Learning and Fine-Tuning Across Five Folds

Optimal hyperparameters identified for transfer learning and fine-tuning across all five folds. The dataset lists learning rate, weight decay, dropout rate, dense layer units, batch size, and optimizer. Christopher Mai published this 5.5 KB XLS file on figshare in May 2026 under a CC-BY-4.0 license.

Use Cases

• Benchmarking model performance based on the listed optimal hyperparameter sets.
• Reproducing transfer learning experiments based on the documented learning rates and optimizers.
• Analyzing the relationship between hyperparameters like weight decay and dropout rate for model tuning.

Strengths

• Specific hyperparameters are listed, including learning rate, weight decay, and dropout rate.
• Results are provided across five folds, suggesting a cross-validation methodology.
• The dataset is small (5.5 KB), ensuring quick download and inspection.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare

Collection Method

Likely derived from a hyperparameter optimization experiment.

Freshness

Last updated 2026-05-29 17:30:04; freshness should be verified.