Baseline Model Hyperparameters with Defaults Noted

Final training setups for baseline models compiled by Nadine Francis and uploaded to figshare on 2026-04-09. The 5.5 KB Excel file retains hyperparameters from original papers and marks common defaults. Missing values for optimizer, learning rate, schedule, momentum, or weight decay are indicated.

Use Cases

• Reproducing baseline model experiments based on reported hyperparameters.
• Comparing training setups across different models based on optimizer, learning rate, and schedule details.
• Setting default hyperparameter values for missing configurations based on the marked common defaults.
• Analyzing the use of specific loss functions like cross-entropy or Dice loss in baseline models.

Strengths

• Hyperparameters are sourced from original papers, providing a traceable reference.
• Missing values are explicitly marked, clarifying where defaults were applied.
• File size is 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.

Provenance

Source

Nadine Francis via figshare

Collection Method

Compilation from original research papers, with defaults applied where values were missing.

Time Range

null

Freshness

Last updated 2026-04-09 17:38:25; freshness should be verified.

Geography

null