What is a model?
In general, any mathematical construct that processes input data and returns output.
model explained in plain English
In general, any mathematical construct that processes input data and returns output. Phrased differently, a model is the set of parameters and structure needed for a system to make predictions. In supervised machine learning, a model takes an example as input and infers a prediction as output. Within supervised machine learning, models differ somewhat. For example: A neural network model consists of: - A set of hidden layers, each containing one or more neurons. - The weights and bias associated with each neuron. A decision tree model consists of: - The shape of the tree; that is, the pattern in which the conditions and leaves are connected. - The conditions and leaves. You can save, restore, or make copies of a model. Unsupervised machine learning also generates models, typically a function that can map an input example to the most appropriate cluster.
An algebraic function such as the following is a model:
The preceding function maps input values (x and y) to output. Similarly, a programming function like the following is also a model:
Example
A caller passes arguments to the preceding Python function, and the Python function generates output (via the return statement). Although a deep neural network has a very different mathematical structure than an algebraic or programming function, a deep neural network still takes input (an example) and returns output (a prediction). A human programmer codes a programming function manually. In contrast, a machine learning model gradually learns the optimal parameters during automated training. ---
People also read
- generative model
Practically speaking, a model that does either of the following: - Creates (generates) new examples from the training dataset.
- activation function
A function that enables neural networks to learn nonlinear (complex) relationships between features and the label.
- Backpropagation
The process that tells a neural network which internal settings caused an error and how to adjust them, working backwards through layers.
- batch
The set of examples used in one training iteration.
- batch normalization
Normalizing the input or output of the activation functions in a hidden layer.
- batch size
The number of examples in a batch.
- Bayesian neural network
A probabilistic neural network that accounts for uncertainty in weights and outputs.
- bias
1.
- bias (math) or bias term
An intercept or offset from an origin.
- co-adaptation
An undesirable behavior in which neurons predict patterns in training data by relying almost exclusively on outputs of specific other neurons instead of relying on the network's behavior as a whole.