Trained Neural Network Structure

A Trained Neural Network Structure is a trained model that instantiates a neural network model.

• Context:
  • It can be the output of a Neural Network Training System (solving a neural network training task).
  • It can range from (typically) being a Trained NNet Classifier to being a Trained NNet Estimator.
  • It can range from being a Trained Deep NNet to being a Trained Shallow NNet.
  • …
• Example(s):
  • an ONNX Format NNet, such as a GPT-2 ONNX Model [1].
  • …
• Counter-Example(s):
  • a Trained Decision Tree.
  • a Trained Logistic Function.
• See: Neural Network File.

---

---

References

2020

• https://github.com/onnx/models
  • QUOTE: ... The ONNX Model Zoo is a collection of pre-trained, state-of-the-art models in the ONNX format contributed by community members like you. Accompanying each model are Jupyter notebooks for model training and running inference with the trained model. The notebooks are written in Python and include links to the training dataset as well as references to the original paper that describes the model architecture. ...

---