What is a graph?
In TensorFlow, a computation specification.
graph explained in plain English
In TensorFlow, a computation specification. Nodes in the graph represent operations. Edges are directed and represent passing the result of an operation (a Tensor) as an operand to another operation. Use TensorBoard to visualize a graph.
Example
Practitioners refer to graph when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- act
A stage in the agentic loop in which the agent executes the action chosen during the reason stage.
- Backpropagation
The process that tells a neural network which internal settings caused an error and how to adjust them, working backwards through layers.
- broadcasting
Expanding the shape of an operand in a matrix math operation to dimensions compatible for that operation.
- Einsum notation
An efficient notation for describing how two tensors are to be combined.
- feature engineering
A process that involves the following steps: 1.
- feedback
A stage in an agentic loop in which the agent evaluates the action taken during the act stage.
- function transformation
A function that takes a function as input and returns a transformed function as output.
- layer
A set of neurons in a neural network.
- MCP
An open protocol that lets AI models connect to external tools, data sources, and services.
- Mean Squared Error
The average loss per example when L2 loss is used.