A feedback control structure for on-line learning tasks

Learning when limited to modification of some parameters has a limited scope; capability to modify the system structure is also needed to get a wider range of the learnable. In the case of artificial neural networks, learning by iterative adjustment of synaptic weights can only succeed if the network designer predefines an appropriate network structure, i.e. the number of hidden layers, units, and the size and shape of their receptive and projective fields. This paper advocates the view that the network structure should not, as is usually done, be determined by trial-and-error but should be computed by the learning algorithm. Incremental learning algorithms can modify the network structure by addition and/or removal of units and/or links. A survey of current connectionist literature is given on this line of thought. “Grow and Learn” (GAL) is a new algorithm that learns an association at one shot due to its being incremental and using a local representation. During the so-called “sleep” phase, units that were previously stored but which are no longer necessary due to recent modifications are removed to minimize network complexity. The incrementally constructed network can later be finetuned off-line to improve performance. Another method proposed that greatly increases recognition accuracy is to train a number of networks and vote over their responses. The algorithm and its variants were tested on recognition of handwritten numerals and seem promising especially in terms of learning speed. This makes the algorithm attractive for on-line learning tasks, e.g. in robotics. The biological plausibility of incremental learning is also discussed briefly.

Download Full-text

Adaptive Nonlinear PD Learning Control for Robot Manipulators

Volume 2: 28th Biennial Mechanisms and Robotics Conference, Parts A and B ◽

10.1115/detc2004-57131 ◽

2004 ◽

Cited By ~ 2

Author(s):

P. R. Ouyang ◽

W. J. Zhang ◽

M. M. Gupta

Keyword(s):

Control Structure ◽

Control Method ◽

Robot Manipulator ◽

Robot Manipulators ◽

Learning Control ◽

Asymptotic Convergence ◽

Simulation Studies ◽

Pd Control ◽

On Line ◽

On Line Learning

A new control method, called adaptive nonlinear PD learning control (NPD-LC), is proposed for robot manipulator applications in this paper. The proposed control structure is a combination of a nonlinear PD control structure and a directly learning structure. Consequently, this new control method possesses both adaptive and on-line learning properties. One of the unique features of the NPD-LC algorithm is that the learning is based on the previous torque profile of the repetitive task. It is proved that the NPD-LC enjoys the asymptotic convergence for both tracking positions and tracking velocities. Simulation studies were conducted by comparing the proposed method with many other existing methods. As a result, it was demonstrated that the NPD-LC method can achieve a faster convergence speed. The proposed NPD-LC is robust and can be implemented for the control of robot manipulators.

Download Full-text

Patterns of Implicit Learning Below the Level of Conscious Knowledge

Journal of Psychophysiology ◽

10.1027/0269-8803/a000018 ◽

2010 ◽

Vol 24 (2) ◽

pp. 91-101 ◽

Cited By ~ 1

Author(s):

Juliana Yordanova ◽

Rolf Verleger ◽

Ullrich Wagner ◽

Vasil Kolev

Keyword(s):

Implicit Learning ◽

Explicit Knowledge ◽

Implicit Knowledge ◽

Knowledge Generation ◽

Sleep Stages ◽

Implicit Processing ◽

Implicit Processes ◽

Late Night ◽

On Line ◽

On Line Learning

The objective of the present study was to evaluate patterns of implicit processing in a task where the acquisition of explicit and implicit knowledge occurs simultaneously. The number reduction task (NRT) was used as having two levels of organization, overt and covert, where the covert level of processing is associated with implicit associative and implicit procedural learning. One aim was to compare these two types of implicit processes in the NRT when sleep was or was not introduced between initial formation of task representations and subsequent NRT processing. To assess the effects of different sleep stages, two sleep groups (early- and late-night groups) were used where initial training of the task was separated from subsequent retest by 3 h full of predominantly slow wave sleep (SWS) or rapid eye movement (REM) sleep. In two no-sleep groups, no interval was introduced between initial and subsequent NRT performance. A second aim was to evaluate the interaction between procedural and associative implicit learning in the NRT. Implicit associative learning was measured by the difference between the speed of responses that could or could not be predicted by the covert abstract regularity of the task. Implicit procedural on-line learning was measured by the practice-based increased speed of performance with time on task. Major results indicated that late-night sleep produced a substantial facilitation of implicit associations without modifying individual ability for explicit knowledge generation or for procedural on-line learning. This was evidenced by the higher rate of subjects who gained implicit knowledge of abstract task structure in the late-night group relative to the early-night and no-sleep groups. Independently of sleep, gain of implicit associative knowledge was accompanied by a relative slowing of responses to unpredictable items suggesting reciprocal interactions between associative and motor procedural processes within the implicit system. These observations provide evidence for the separability and interactions of different patterns of processing within implicit memory.

Download Full-text