Discriminative model
A discriminative model predicts labels or other outcomes from inputs by modeling conditional relationships or decision boundaries rather than the full data-generating distribution.
Graph Neural Networks in Action
A discriminative model learns to distinguish among data classes or predict target values without modeling the full data-generating distribution.
- How it is used
- Classifies unseen instances or predicts targets, including node classification with convolutional and attention-based graph neural networks.
- How deep it goes
- Defines conditional prediction and boundary learning, stopping short of model internals or detailed training procedures.
- Examples
- Uses boat-versus-airplane images, telltale visual features, and node-classification tasks as examples.
- What you can do after
- Evaluate when boundary-focused classification is preferable to full-distribution modeling, considering computational cost and outlier robustness.
Read how Graph Neural Networks in Action explains discriminative model →
Data Without Labels
A discriminative model predicts or classifies outcomes by modeling distinctions between data classes or conditional outcomes rather than generating new data.
- How it is used
- Supports supervised prediction and classification by separating classes or estimating conditional outcomes from labeled data.
- How deep it goes
- Defines class boundaries, conditional probability, task types, and representative algorithms, but does not detail training mechanics.
- Examples
- Uses churn, fraud detection, store sales, call volume, logistic regression, decision trees, random forests, support vector machines, and neural networks.
- What you can do after
- Evaluate and understand when classification or numeric prediction requires a discriminative approach rather than data generation.
Read how Data Without Labels explains discriminative model →
Investing for Programmers
A discriminative model predicts labels or quantitative outcomes from input data without generating new content.
- How it is used
- Targets narrow financial research and automated-trading decisions that require measurable predictions rather than creative analysis.
- How deep it goes
- Defines classification and regression outputs but stops short of explaining model reasoning or implementation internals.
- Examples
- Uses industry-outcome assessment, share-price forecasting, buy-sell-hold signals, and automated order triggers.
- What you can do after
- Apply it via traditional machine learning to produce focused financial predictions or trigger rule-based trading actions.
Read how Investing for Programmers explains discriminative model →
Learn Generative AI with PyTorch
A model that learns to predict labels from inputs by estimating conditional probabilities and decision boundaries between classes.
- How it is used
- Classifies pre-existing content by assigning labels from input features.
- How deep it goes
- Defines conditional probabilities and class boundaries through a dog-versus-cat example, without developing implementation internals.
- Examples
- Uses dog-and-cat images, distinguishing facial features, and competing Prob(dog) and Prob(cat) outputs.
- What you can do after
- Evaluate/understand how input features become class probabilities and labels.
Read how Learn Generative AI with PyTorch explains discriminative model →
Related concepts
- generative modelingcontrasts with · Generative modeling is a machine-learning approach that learns patterns or a data distribution to generate new samples resembling the data.
- machine learningequivalent to · Machine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.
- conditional probabilityuses · Conditional probability is the probability of an event or variable value given that specified information, an event, or another variable’s value is known.
- generationcontrasts with · Generation is the computational production of outputs from supplied inputs or context, often by applying a model to produce predictions or new content.
- decision boundaryuses · A decision boundary is the locus in input or feature space that separates regions assigned different classes or decision outcomes by a predictive model.
- supervised learningused by · Supervised learning is a machine-learning approach that learns to map inputs to target outputs from examples paired with known labels or values.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.