Minimizing Binding Errors Using Learned Conjunctive Features
نویسندگان
چکیده
We have studied some of the design trade-offs governing visual representations based on spatially invariant conjunctive feature detectors, with an emphasis on the susceptibility of such systems to false-positive recognition errors-Malsburg's classical binding problem. We begin by deriving an analytical model that makes explicit how recognition performance is affected by the number of objects that must be distinguished, the number of features included in the representation, the complexity of individual objects, and the clutter load, that is, the amount of visual material in the field of view in which multiple objects must be simultaneously recognized, independent of pose, and without explicit segmentation. Using the domain of text to model object recognition in cluttered scenes, we show that with corrections for the nonuniform probability and nonindependence of text features, the analytical model achieves good fits to measured recognition rates in simulations involving a wide range of clutter loads, word size, and feature counts. We then introduce a greedy algorithm for feature learning, derived from the analytical model, which grows a representation by choosing those conjunctive features that are most likely to distinguish objects from the cluttered backgrounds in which they are embedded. We show that the representations produced by this algorithm are compact, decorrelated, and heavily weighted toward features of low conjunctive order. Our results provide a more quantitative basis for understanding when spatially invariant conjunctive features can support unambiguous perception in multiobject scenes, and lead to several insights regarding the properties of visual representations optimized for specific recognition tasks.
منابع مشابه
The Feasibility of the Conjunctive Use of Surface and Groundwater Resources in Dehloran Plain by Using the MODFLOW Model
Lack of the proper conjunctive use of surface and groundwater resources causes large water stresses in one of these resources. Conjunctive use of surface and groundwater, especially in arid and semi-arid regions, is a scientific and practical solution for sustainable water resources management. The aim of this research was to prepare some mathematical modeling to apply the conjunctive use of su...
متن کاملFactors Affecting Medication Errors from Nurses' Perspective: Lessons Learned
Introduction: Medical errors are among the most threatening faults against patient’s safety in all countries. The most frequent medical errors are medication errors which can lead to serious effects and even death in patients. Therefore, this study aimed to explain factors affecting medication eroors from the viewpoints of nurses in order to present strategies to reduce these errors. Methods:...
متن کاملEmergence of Vocal Developmental Sequences in a Predictive Coding Model of Speech Acquisition
Learning temporal patterns among primitive speech sequences and being able to control the motor apparatus for effective production of the learned patterns are imperative for speech acquisition in infants. In this paper, we develop a predictive coding model whose objective is to minimize the sensory (auditory) and proprioceptive prediction errors. Temporal patterns are learned by minimizing the ...
متن کاملUsing temporal binding for hierarchical recruitment of conjunctive concepts over delayed lines
The temporal correlation hypothesis proposes using distributed synchrony for the binding of different stimulus features. However, synchronized spikes must travel over cortical circuits that have varying-length pathways, leading to mismatched arrival times. This raises the question of how initial stimulus-dependent synchrony might be preserved at a destination binding site. Earlier, we proposed ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Neural computation
دوره 12 2 شماره
صفحات -
تاریخ انتشار 2000