Recognition of Manipulated Objects by Motor Learning
نویسندگان
چکیده
We present two neural network controller learning schemes based on feedbackerror-learning and modular architecture for recognition and control of multiple manipulated objects. In the first scheme, a Gating Network is trained to acquire object-specific representations for recognition of a number of objects (or sets of objects). In the second scheme, an Estimation Network is trained to acquire function-specific, rather than object-specific, representations which directly estimate physical parameters. Both recognition networks are trained to identify manipulated objects using somatic and/or visual information. After learning, appropriate motor commands for manipulation of each object are issued by the control networks.
منابع مشابه
Enhanced Multisensory Integration and Motor Reactivation after Active Motor Learning of Audiovisual Associations
Everyday experience affords us many opportunities to learn about objects through multiple senses using physical interaction. Previous work has shown that active motor learning of unisensory items enhances memory and leads to the involvement of motor systems during subsequent perception. However, the impact of active motor learning on subsequent perception and recognition of associations among m...
متن کاملActive Learning of Novel Sound-producing Objects: Motor Reactivation and Enhancement of Visuo-motor Connectivity
Our experience with the world commonly involves physical interaction with objects enabling us to learn associations between multisensory information perceived during an event and our actions that create an event. The interplay among active interactions during learning and multisensory integration of object properties is not well understood. To better understand how action might enhance multisen...
متن کاملLearning and representation of causative motor actions: a neural network model and its use in an embodied theory of language
In this paper we present a neural network model of motor learning structured around circuits which associate motor actions with their sensory effects, as proposed by Hommel et al. (2001). The network implements a novel model of causative actions, which bring about specified distal movements in manipulated target objects (e.g. bending a lever). It also serves as the basis for a novel embodied ac...
متن کاملبهبود مدل تفکیککننده منیفلدهای غیرخطی بهمنظور بازشناسی چهره با یک تصویر از هر فرد
Manifold learning is a dimension reduction method for extracting nonlinear structures of high-dimensional data. Many methods have been introduced for this purpose. Most of these methods usually extract a global manifold for data. However, in many real-world problems, there is not only one global manifold, but also additional information about the objects is shared by a large number of manifolds...
متن کاملTitle: Learning to Recognize Visual Objects with Microstimulation in Inferior Temporal Cortex Authors: It Stimulation during Learning
The malleability of object representations by experience is essential for adaptive behavior. It has been hypothesized that neurons in inferior temporal cortex (IT) in monkeys are pivotal in visual association learning, evidenced by experiments revealing changes in neural selectivity following visual learning, as well as by lesion studies, wherein functional inactivation of IT impairs learning. ...
متن کامل