Hyperparameters

AI fundamentals

Hyperparameters are the settings chosen before training: learning rate, batch size, number of layers. They are not learned by the model but condition the quality of learning; tuning them is a matter of methodical experimentation.

In practice at Gensai

On the usage side, Gensai tunes inference hyperparameters (temperature, maximum length) to control model behaviour.

Same theme

Artificial intelligence (AI)Algorithm Data Dataset Model (AI)Machine learning Deep learning Neural network Supervised learning Unsupervised learning Reinforcement learning Classification Regression Prediction Training Inference Parameters Bias (AI)

Hyperparameters

In practice at Gensai

Go deeper

Same theme