Unsupervised BCM Network The Usefulness of Distinguishing Features
نویسنده
چکیده
We propose an object recognition scheme based on a method for feature extraction from gray level images that corresponds to recent statistical theory, called pmjection pursuit, and is derived from a biologically motivated feature extracting neuron. To evaluate the performance of this method we use a set of very detailed psychophysical three-dimensional object recognition experiments (Biilthoff and Edelman 1992).
منابع مشابه
Three-Dimensional Object Recognition Using an Unsupervised BCM Network: The Usefulness of Distinguishing Features
We propose an object recognition scheme based on a method for feature extraction from gray level images that corresponds to recent statistical theory, called projection pursuit, and is derived from a biologically motivated feature extracting neuron. To evaluate the performance of this method we use a set of very detailed psychophysical 3D object recognition experiments (B ulthoo and Edelman, 19...
متن کاملFeature Extraction Using an Unsupervised Neural Network
A novel unsupervised neural network for dimensionality reduction that seeks directions emphasizing multimodality is presented, and its connection to exploratory projection pursuit methods is discussed. This leads to a new statistical insight into the synaptic modification equations governing learning in Bienenstock, Cooper, and Munro (BCM) neurons (1982). The importance of a dimensionality redu...
متن کاملExploratory Feature Extraction in Speech Signals
A novel unsupervised neural network for dimensionality reduction which seeks directions emphasizing multimodality is presented, and its connection to exploratory projection pursuit methods is discussed. This leads to a new statistical insight to the synaptic modification equations governing learning in Bienenstock, Cooper, and Munro (BCM) neurons (1982). The importance of a dimensionality reduc...
متن کاملObjective function formulation of the BCM theory of visual cortical plasticity: Statistical connections, stability conditions
In this paper, we present an objective function formulation of the BCM theory of visual cortical plasticity that permits us to demonstrate the connection between the unsupervised BCM learning procedure and various statistical methods, in particular, that of Projection Pursuit. This formulation provides a general method for stability analysis of the xed points of the theory and enables us to ana...
متن کاملThe Usefulness of CD10 in Distinguishing between Cutaneous Basal Cell Carcinoma and Squamous Cell Carcinoma
Background & Objectives: CD10 is a cell surface enzyme with metalloendopeptidase activity, also known as Common Acute Lymphoblastic Leukaemia Antigen, which mainly serves as a marker for acute lymphoblastic leukemia (ALL). To date and to the best of our knowledge, only few comparative immunohistochemical studies have assessed CD10 expression in cutaneous epithelial neoplasms. Our goal was to d...
متن کامل