model

Go back to the [[AI Glossary]]

The representation of what a machine learning system has learned from the training data. Within TensorFlow, model is an overloaded term, which can have either of the following two related meanings:

The TensorFlow graph that expresses the structure of how a prediction will be computed.
The particular weights and biases of that TensorFlow graph, which are determined by training.

Metamodels (classifications, patterns)

Cynefin VSM SOFI SD Archetypes

System Dynamics

Causal Loop Diagrams Stock Flow Diagrams Cause/Consequence (Driver) Trees Causal Impact Matrix

Mapping (Representing)

Rich pictures Geographical Information Systems

Simulation (Projection)

Depends whether we are simply aiming to project a behavior pattern or understand causation. The focus here is on causal models.

Spreadsheets Statistical models eg MLR, BJTF System Dynamics

Calibration

Statistics Judgements

Motivations

Improve your comprehension (understanding) Improve your communication Improve your community

Model of the World

• [[pull]] We all carry [[models of the world]] with us at all times. In fact, our models of the world might be the only thing we ever get to interact with; it is with our [[models]] that we [[make sense]] of things and take (or observe) [[decisions]].

model capacity

Go back to the [[AI Glossary]]

The complexity of problems that a model can learn. The more complex the problems that a model can learn, the higher the model’s capacity. A model’s capacity typically increases with the number of model parameters. For a formal definition of classifier capacity, see VC dimension.

model function

Go back to the [[AI Glossary]]

#TensorFlow

The function within an Estimator that implements machine learning training, evaluation, and inference. For example, the training portion of a model function might handle tasks such as defining the topology of a deep neural network and identifying its optimizer function. When using premade Estimators, someone has already written the model function for you. When using custom Estimators, you must write the model function yourself.

For details about writing a model function, see the Creating Custom Estimators chapter in the TensorFlow Programmers Guide.

model training

Go back to the [[AI Glossary]]

The process of determining the best model.

modeless markup