📚 node [[parameter|parameter]]
Welcome! Nobody has contributed anything to 'parameter|parameter' yet. You can:
  • Write something in the document below!
    • There is at least one public document in every node in the Agora. Whatever you write in it will be integrated and made available for the next visitor to read and edit.
  • Write to the Agora from social media.
    • If you follow Agora bot on a supported platform and include the wikilink [[parameter|parameter]] in a post, the Agora will link it here and optionally integrate your writing.
  • Sign up as a full Agora user.
    • As a full user you will be able to contribute your personal notes and resources directly to this knowledge commons. Some setup required :)
⥅ related node [[hyperparameter]]
⥅ related node [[parameter]]
⥅ related node [[parameter_server_(ps)]]
⥅ related node [[parameter_update]]
⥅ node [[parameter]] pulled by Agora

parameter

Go back to the [[AI Glossary]]

A variable of a model that the machine learning system trains on its own. For example, weights are parameters whose values the machine learning system gradually learns through successive training iterations. Contrast with hyperparameter.

⥅ node [[parameter_server_(ps)]] pulled by Agora

Parameter Server (PS)

Go back to the [[AI Glossary]]

#TensorFlow

A job that keeps track of a model's parameters in a distributed setting.

See the TensorFlow Architecture chapter in the TensorFlow Programmers Guide for details.

⥅ node [[parameter_update]] pulled by Agora

parameter update

Go back to the [[AI Glossary]]

The operation of adjusting a model's parameters during training, typically within a single iteration of gradient descent.

📖 stoas
⥱ context