Effects of generative and discriminative learning on use of category variability
نویسندگان
چکیده
Rational models of category learning can take two different approaches to representing the relationship between objects and categories. The generative approach solves the categorization problem by building a probabilistic model of each category and using Bayes’ rule to infer category labels. In contrast, the discriminative approach directly learns a mapping between inputs and category labels. With this distinction in mind, we revisit a previously studied categorization experiment that showed people are biased towards categorizing objects into a category with higher variability. Modelling results predict that generative learners should be more greatly affected by category variability than discriminative learners. We show that humans can be prompted to adopt either a generative or discriminative approach to learning the same input, resulting in the predicted effect on use of category variability.
منابع مشابه
Hybrids of Generative and Discriminative Methods for Machine Learning
In machine learning, probabilistic models are described as belonging to one of two categories: generative or discriminative. Generative models are built to understand how samples from a particular category were generated. The category chosen for a new data-point is the category whose model fits the point best. Discriminative models are concerned with defining the boundaries between the categori...
متن کاملDiscriminative Mixture-of-Templates for Viewpoint Classification
Object viewpoint classification aims at predicting an approximate 3D pose of objects in a scene and is receiving increasing attention. State-of-the-art approaches to viewpoint classification use generative models to capture relations between object parts. In this work we propose to use a mixture of holistic templates (e.g. HOG) and discriminative learning for joint viewpoint classification and ...
متن کاملDiscriminative Models for Semi-Supervised Natural Language Learning
An interesting question surrounding semisupervised learning for NLP is: should we use discriminative models or generative models? Despite the fact that generative models have been frequently employed in a semi-supervised setting since the early days of the statistical revolution in NLP, we advocate the use of discriminative models. The ability of discriminative models to handle complex, high-di...
متن کاملLarge Margin GMM for discriminative speaker verification
Gaussian mixture models (GMM), trained using the generative criterion of maximum likelihood estimation, have been the most popular approach in speaker recognition during the last decades. This approach is also widely used in many other classification tasks and applications. Generative learning in not however the optimal way to address classification problems. In this paper we first present a ne...
متن کاملSocratic Learning
Modern machine learning techniques often use discriminative models that require large amounts of labeled data. Since generating labeled training data sets is expensive, an alternative approach is to use a generative model, which leverages a simple heuristic to weakly label data. Domain experts prefer using generative models because they “tell a story” about their data. Unfortunately, generative...
متن کامل