Forward models: Supervised learning with a distal teacher

Jordan, Michelle E.

doi:10.1016/0364-0213(92)90036-t

Cited by 318 publications

(109 citation statements)

References 14 publications

Supporting

Mentioning

108

Contrasting

Order By: Relevance

“…Every predictive schema has an associated incoherence schema that acts as a prediction error detector. Corbacho (1997) presented predictive schemas as a generalization of forward models (Jordan and Rumelhart 1992). Other researchers have also included predictive internal models as central components of their systems dynamics.…”

Section: Schema-based Learningmentioning

confidence: 99%

Schema-based learning of adaptable and flexible prey- catching in anurans II. Learning after lesioning

et al. 2005

View full text Add to dashboard Cite

The previous companion paper describes the initial (seed) schema architecture that gives rise to the observed prey-catching behavior. In this second paper in the series we describe the fundamental adaptive processes required during learning after lesioning. Following bilateral transections of the hypoglossal nerve, anurans lunge toward mealworms with no accompanying tongue or jaw movement. Nevertheless anurans with permanent hypoglossal transections eventually learn to catch their prey by first learning to open their mouth again and then lunging their body further and increasing their head angle. In this paper we present a new learning framework, called schema-based learning (SBL). SBL emphasizes the importance of the current existent structure (schemas), that defines a functioning system, for the incremental and autonomous construction of ever more complex structure to achieve ever more complex levels of functioning. We may rephrase this statement into the language of Schema Theory (Arbib 1992, for a comprehensive review) as the learning of new schemas based on the stock of current schemas. SBL emphasizes a fundamental principle of organization called coherence maximization, that deals with the maximization of congruence between the results of an interaction (external or internal) and the expectations generated for that interaction. A central hypothesis consists of the existence of a hierarchy of predictive internal models (predictive schemas) all over the control center-brain-of the agent. Hence, we will include predictive models in the perceptual, sensorimotor, and motor components of the autonomous agent architecture. We will then show that predictive models are fundamental for structural learning. In particular we will show how a system can learn a new structural component (augment the overall network topology) after being lesioned in order to recover (or even improve) its original functionality. Learning after lesioning is a special case of structural learning but clearly shows that solutions cannot be known/hardwired a priori since it cannot be known, in advance, which substructure is going to break down.

show abstract

Section: Schema-based Learningmentioning

confidence: 99%

Schema-based learning of adaptable and flexible prey- catching in anurans II. Learning after lesioning

et al. 2005

View full text Add to dashboard Cite

show abstract

“…These solutions are called "direct inverse modeling" (Kuperstein 1988), "feedback-error learning" (Kawato et al 1987;Kawato 1990), and "distal supervised learning" (Jordan and Rumelhart 1992).…”

Section: Saccade Controller Compared To Literaturementioning

confidence: 99%

“…The disadvantage of this type of learning is that it is not goal-directed, which means that the random search in motor space ignores the goal. Thus, taskrelevant sensory values may be underrepresented (Jordan and Rumelhart 1992).…”

Section: Saccade Controller Compared To Literaturementioning

confidence: 99%

Learning visuomotor transformations for gaze-control and grasping

2005

View full text Add to dashboard Cite

For reaching to and grasping of an object, visual information about the object must be transformed into motor or postural commands for the arm and hand. In this paper, we present a robot model for visually guided reaching and grasping. The model mimics two alternative processing pathways for grasping, which are also likely to coexist in the human brain. The first pathway directly uses the retinal activation to encode the target position. In the second pathway, a saccade controller makes the eyes (cameras) focus on the target, and the gaze direction is used instead as positional input. For both pathways, an arm controller transforms information on the target's position and orientation into an arm posture suitable for grasping. For the training of the saccade controller, we suggest a novel staged learning method which does not require a teacher that provides the necessary motor commands. The arm controller uses unsupervised learning: it is based on a density model of the sensor and the motor data. Using this density, a mapping is achieved by completing a partially given sensorimotor pattern. The controller can cope with the ambiguity in having a set of redundant arm postures for a given target. The combined model of saccade and arm controller was able to fixate and grasp an elongated object with arbitrary orientation and at arbitrary position on a table in 94% of trials.

show abstract

“…This is accomplished with another device -a so-called forward model. 11 Within motor control, forward models are used to predict sensory consequences from efference copies of issued motor commands. 12 In the model described in this paper, we use forward models for the selection actions in the following way: the outcome of all possible actions in the present context is predicted with the forward model and then the action which produces the most desired effect is chosen.…”

Section: Action Selectionmentioning

confidence: 99%

Understanding Communicative Intentions Using Simulated Role-Reversal

Klein

2009

Connectionist Models of Behaviour and Cognition II

View full text Add to dashboard Cite

Understanding the communicative intention of a speaker is the ultimate goal of language comprehension. Yet, there is very little computational work on this topic. In this chapter a general cognitive plausible model of how an addressee can understand communicative intentions is presented in mathematical detail. The key mechanism of the model is simulated role-reversal of the addressee with the speaker, i.e., the addressee puts himself in the state of the speaker andusing his own experience about plausible intentions -computes the most likely intention in the given context. To show the model's computational effectiveness, it was implemented in a multi-agent system. In this system agents learn about which states of the world are desirable using a neural network trained with reinforcement learning. The power of simulated role-reversal in understanding communicative intention was demonstrated by depriving the utterances of speakers of all content. Employing the outlined model, the agents nevertheless accomplished a remarkable understanding of intentions using context information alone.

show abstract

Forward models: Supervised learning with a distal teacher

Cited by 318 publications

References 14 publications

Schema-based learning of adaptable and flexible prey- catching in anurans II. Learning after lesioning

Schema-based learning of adaptable and flexible prey- catching in anurans II. Learning after lesioning

Learning visuomotor transformations for gaze-control and grasping

Understanding Communicative Intentions Using Simulated Role-Reversal

Contact Info

Product

Resources

About