liveBook · Manning

Parameter

As explained in Build AI Drug Discovery Pipelines

A model parameter is a numerical value that governs a model's mapping from inputs to outputs and is typically learned from data.

A model parameter is a learned numerical value that controls how input features contribute to a prediction. Weights express feature importance, while a bias provides an adjustable offset. section 4.2.1 section 3.3.1

Parameters begin with initial values and are tuned from training data. A loss measures prediction error, a cost aggregates it, and an optimization routine adjusts parameters to reduce that error. section 8.2.3 section 3.3.1

A parameter follows a different lifecycle during training and inference:

  • Training repeatedly updates parameters using predictions, targets, loss, backpropagation, and an optimizer. section 8.2.3
  • Validation loss helps reveal when further updates stop improving generalization and informs choices such as early stopping. section 8.2.3
  • Inference uses previously learned parameters without updating them on new data. section 3.3.1

Linear solubility model

For a molecule represented by 11 RDKit descriptors, the model multiplies each feature by its corresponding weight and sums the results with a bias. Learning adjusts these values so predicted solubility better matches measured solubility. section 4.2.1

Neural-network training

An EGFR activity model receives 2,048-bit Morgan fingerprints and predicts pIC50. PyTorch computes the loss, backpropagates gradients, and calls the optimizer to nudge the network's weights and biases. section 8.2

y^=∑jnwjxj=w0x0+w1x1+w2x2+…+wnxn

Expand the equation to see how each feature-specific parameter and the bias contributes to a linear prediction. section 4.2.1

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains weights, bias, loss-driven updates, validation monitoring, and frozen inference while deferring formal distribution theory.
Examples
Demonstrates parameters with RDKit descriptors for solubility and Morgan fingerprints for EGFR activity prediction.
What it assumes
Assumes feature vectors, targets, and prediction error; defines parameter roles and training mechanics through molecular-property examples.
What you can do after
Build it from scratch by configuring a training loop that computes loss, propagates gradients, updates parameters, and evaluates validation performance.
How it connects
Connects parameters to linear models, neural networks, loss functions, optimization, backpropagation, inference, and parametric models.

Also explained in

Compare how 41 books explain parameter →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.