Discriminative model

As explained in Learn Generative AI with PyTorch

A model that learns to predict labels from inputs by estimating conditional probabilities and decision boundaries between classes.

A discriminative model recognizes and categorizes existing content by learning how input features distinguish among classes. It estimates conditional probabilities such as P(Y|X), then assigns the label with the highest predicted probability. section 1.1 section 1.1.1

Unlike a generative model, which learns a joint distribution to create new instances, a discriminative model focuses on the boundary between labels rather than synthesizing content. section 1.1.1

A typical classification task proceeds as follows:

• Provide an input, such as an image containing a dog or cat. section 1.1.1
• Use distinguishing features, such as small noses or pointy ears, to estimate Prob(dog) and Prob(cat). section 1.1.1
• Choose the label with the highest predicted probability. section 1.1.1

Figure 1.1 A comparison of generative models versus discriminative models. A discriminative model (top half of the figure) takes data as inputs and produces probabilities of different labels, which we denote by Prob(dog) and Prob(cat). In contrast, a generative model (bottom half) acquires an in-depth understanding of the defining characteristics of these images to synthesize new images representing dogs and cats.

Compare the input-to-label workflow of discriminative models with the content-generation workflow of generative models. section 1.1.1

How Learn Generative AI with PyTorch covers it

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.

How it connects

Contrasts discriminative models with generative models and connects them to classification, conditional probability, and joint probability distributions.

liveBookmanning.com

Read Learn Generative AI with PyTorch on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Graph Neural Networks in ActionA discriminative model learns to distinguish among data classes or predict target values without modeling the full data-generating distribution.
• 

  liveBookmanning.com
  Data Without LabelsA discriminative model predicts or classifies outcomes by modeling distinctions between data classes or conditional outcomes rather than generating new data.
• 

  liveBookmanning.com
  Investing for ProgrammersA discriminative model predicts labels or quantitative outcomes from input data without generating new content.

Compare how 4 books explain 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.

This explainer was generated by Manning's knowledge graph from the text of Learn Generative AI with PyTorch. The section links point to the parts of the book it draws on.