Dataset Information

Learning to detect and combine the features of an object.

ABSTRACT: To recognize an object, it is widely supposed that we first detect and then combine its features. Familiar objects are recognized effortlessly, but unfamiliar objects--like new faces or foreign-language letters--are hard to distinguish and must be learned through practice. Here, we describe a method that separates detection and combination and reveals how each improves as the observer learns. We dissociate the steps by two independent manipulations: For each step, we do or do not provide a bionic crutch that performs it optimally. Thus, the two steps may be performed solely by the human, solely by the crutches, or cooperatively, when the human takes one step and a crutch takes the other. The crutches reveal a double dissociation between detecting and combining. Relative to the two-step ideal, the human observer's overall efficiency for unconstrained identification equals the product of the efficiencies with which the human performs the steps separately. The two-step strategy is inefficient: Constraining the ideal to take two steps roughly halves its identification efficiency. In contrast, we find that humans constrained to take two steps perform just as well as when unconstrained, which suggests that they normally take two steps. Measuring threshold contrast (the faintness of a barely identifiable letter) as it improves with practice, we find that detection is inefficient and learned slowly. Combining is learned at a rate that is 4× higher and, after 1,000 trials, 7× more efficient. This difference explains much of the diversity of rates reported in perceptual learning studies, including effects of complexity and familiarity.

SUBMITTER: Suchow JW

PROVIDER: S-EPMC3545750 | biostudies-literature | 2013 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Learning to detect and combine the features of an object.

Suchow Jordan W JW Pelli Denis G DG

Proceedings of the National Academy of Sciences of the United States of America 20121224 2

To recognize an object, it is widely supposed that we first detect and then combine its features. Familiar objects are recognized effortlessly, but unfamiliar objects--like new faces or foreign-language letters--are hard to distinguish and must be learned through practice. Here, we describe a method that separates detection and combination and reveals how each improves as the observer learns. We dissociate the steps by two independent manipulations: For each step, we do or do not provide a bioni ...[more]

PMID: 23267067

Similar Datasets

Project description:Successful communication often involves comprehension of both spoken language and observed actions with and without objects. Even very young infants can learn associations between actions and objects as well as between words and objects. However, in daily life, children are usually confronted with both kinds of input simultaneously. Choosing the critical information to attend to in such situations might help children structure the input, and thereby, allow for successful learning. In the current study, we therefore, investigated the developmental time course of children's and adults' word and action learning when given the opportunity to learn both word-object and action-object associations for the same object. All participants went through a learning phase and a test phase. In the learning phase, they were presented with two novel objects which were associated with a distinct novel name (e.g., "Look, a Tanu") and a distinct novel action (e.g., moving up and down while tilting sideways). In the test phase, participants were presented with both objects on screen in a baseline phase, then either heard one of the two labels or saw one of the two actions in a prime phase, and then saw the two objects again on screen in a recognition phase. Throughout the trial, participants' target looking was recorded to investigate whether participants looked at the target object upon hearing its label or seeing its action, and thus, would show learning of the word-object and action-object associations. Growth curve analyses revealed that 12-month-olds showed modest learning of action-object associations, 36-month-olds learned word-object associations, and adults learned word-object and action-object associations. These results highlight how children attend to the different information types from the two modalities through which communication is addressed to them. Over time, with increased exposure to systematic word-object mappings, children attend less to action-object mappings, with the latter potentially being mediated by word-object learning even in adulthood. Thus, choosing between different kinds of input that may be more relevant in their rich environment encompassing different modalities might help learning at different points in development.

Project description:Scene understanding and decomposition is a crucial challenge for intelligent systems, whether it is for object manipulation, navigation, or any other task. Although current machine and deep learning approaches for object detection and classification obtain high accuracy, they typically do not leverage interaction with the world and are limited to a set of objects seen during training. Humans on the other hand learn to recognize and classify different objects by actively engaging with them on first encounter. Moreover, recent theories in neuroscience suggest that cortical columns in the neocortex play an important role in this process, by building predictive models about objects in their reference frame. In this article, we present an enactive embodied agent that implements such a generative model for object interaction. For each object category, our system instantiates a deep neural network, called Cortical Column Network (CCN), that represents the object in its own reference frame by learning a generative model that predicts the expected transform in pixel space, given an action. The model parameters are optimized through the active inference paradigm, i.e., the minimization of variational free energy. When provided with a visual observation, an ensemble of CCNs each vote on their belief of observing that specific object category, yielding a potential object classification. In case the likelihood on the selected category is too low, the object is detected as an unknown category, and the agent has the ability to instantiate a novel CCN for this category. We validate our system in an simulated environment, where it needs to learn to discern multiple objects from the YCB dataset. We show that classification accuracy improves as an embodied agent can gather more evidence, and that it is able to learn about novel, previously unseen objects. Finally, we show that an agent driven through active inference can choose their actions to reach a preferred observation.

Dataset Information

Learning to detect and combine the features of an object.

Publications

Learning to detect and combine the features of an object.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets