PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “GENERALIZATION LEARNING”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 541 records · Page 30Linked to original sources
PubMed2006

An e-learning portal for nurses in Singapore General Hospital.

Singapore General Hospital (SGH) pioneered e-learning systems in Singapore as a knowledge management initiative for nurses. This paradigm shift in nursing education is a proactive step taken to address the increasing sophistication of healthcare systems, expanding demand and perennial shortage of nursing talent. E-learning has been a success at SGH, through providing systematic sharing of knowledge and capture of experience, through both formal and informal online channels. It also made training more effective and less costly. Formal methods of knowledge sharing comprise online learning through interactive training modules and slides presentation with narration, while informal learning comprises of peer group discussion and journal review. Both elements have been essential in making e-learning a success and in creating a lifelong learning culture in SGH.

Education, Distance↗
PubMed1993

What do students with learning disabilities think when their general education teachers make adaptations?

The purpose of this study was to investigate the perceptions of mainstreamed students with learning disabilities (LD) regarding adaptations (e.g., altering tests, homework, assignments, instruction) made by general education teachers. Furthermore, their responses were compared with those of low achieving (LA) and average/high achieving (A/HA) classmates. One hundred seventy-nine students participated in this study: 60 mainstreamed students with LD, 59 low achieving students, and 60 average/high achieving students. Students were selected from 60 teachers' classrooms (20 elementary, 20 middle school, and 20 high school). Results from the elementary level indicate that students with LD differ from their LA and A/HA classmates in that the former indicate a stronger preference for opportunities to work in groups with different students, and prefer the teacher to make adaptations when they have difficulty learning. High school and middle school students from both the LA and A/HA groups, but not the LD group, preferred the teacher who made no adaptations in homework and textbooks. Discussion focuses on the role of students' perceptions in teacher decision making.

Adolescent↗
PubMed1996

Assessing general practitioners' care of adult patients with learning disability: case-control study.

OBJECTIVE: To compare general practitioners' care of adult patients with learning disability with that of control patients in the same practice. DESIGN: Case-control study of patients and controls by a structured interview study of general practitioners. SETTING: Avon. PATIENTS: 78 adult patients with learning disability and 78 age and sex matched controls--cared for by 62 general practitioners. MAIN MEASURES: Number and content of consultations and opinions of the general practitioners. RESULTS: There were more consultations for diseases of the central nervous system and of the skin among the patients than the controls (15 v 3 for central nervous system disease and 15 v 4 skin disease). There were also significantly fewer recordings of blood pressure and cervical cytology tests (34 v 51 for blood pressure and 2 v 18 for cytology). Although more patients were taking drugs affecting the central nervous system (33 v 6), more controls were taking drugs for musculoskeletal complaints (17 v 7). CONCLUSION: Although adult patients with learning disability consult with their general practitioners at equivalent rates to other patients, they get less preventive care and consult for different types of problems than do other patients. The reasons for these differences in preventive care are not clear. Carers and general practitioners should be informed of these differences to ensure that appropriate care is given.

Adult↗
PubMed2001

The contextual interference effect in acquisition of dart-throwing skill tested on a transfer test with extended trials.

Previous studies of contextual interference have shown that practicing several motor skills randomly (high contextual interference) facilitates retention and transfer in comparison to practicing the same tasks in a blocked order (low contextual interference). However, many studies have not supported this phenomenon in motor learning, and some researchers have questioned whether the effect can be tested by using only a few trials on the transfer test. The present study used a different methodological approach in which the number of test trials was increased to assess whether the contextual interference effect is sustained over an extended number of trials in the transfer phase. Undergraduate students (N=32) were randomly allocated to either a blocked or random group. The participants practiced 80 acquisition trials in the dart-throwing task from distances of 300 cm and 420 cm, using two different grips. The transfer test after a 10-min. interval consisted of 40 trials with a new grip at a distance of 360 cm. The results did not support the contextual interference effect since there were no significant differences between groups on transfer. These findings suggest that the contextual interference effect may not be a global learning phenomenon which can be generalized to all learning situations.

Adult↗
PubMed2005

Case-based object recognition for airborne fungi recognition.

OBJECTIVE: Model-based object recognition is a well-known task in Computer Vision. Usually, one object that can be generalized by a model should be detected in an image based on this model. Biomedical applications have the special quality that one object can have a great variation in appearance. Therefore the appearance of this object cannot be generalized by one model. A set of cases of the appearance of this object (sometimes 50 cases or more) is necessary to detect this object in an image. The recognition method is rather case-based object recognition than model-based object recognition. Case-based object recognition is a challenging task. METHODS AND MATERIAL: It puts special requirements to the similarity measure and needs a matching algorithm that can work fast in a large number of cases. It also needs a case acquisition procedure that can capture the great variation in appearance of an object and generalize these data into a case description. In this paper we describe the chosen case representation, the similarity measure and the matching as well as the case acquisition procedure. We evaluate our method based on a large enough set of digital images containing biological objects such as fungi spores. RESULTS: We can show that the similarity measure is superior to detect the objects in the images. The developed method for case acquisition and learning of generalized cases allows us to learn interactively a sufficient number of cases that are further stored into our case base. Finally, we give results on the performance of the system by calculating the recognition rate. CONCLUSION: These result show that we have developed a novel similarity measure for object detection in digital grey-level images and a novel procedure for case acquisition and learning that allows us to learn a sufficiently large enough case base and to generalize over a group of cases.

Algorithms↗
PubMed2004

Improving generalization performance of natural gradient learning using optimized regularization by NIC.

Natural gradient learning is known to be efficient in escaping plateau, which is a main cause of the slow learning speed of neural networks. The adaptive natural gradient learning method for practical implementation also has been developed, and its advantage in real-world problems has been confirmed. In this letter, we deal with the generalization performances of the natural gradient method. Since natural gradient learning makes parameters fit to training data quickly,the overfitting phenomenon may easily occur, which results in poor generalization performance. To solve the problem, we introduce the regularization term in natural gradient learning and propose an efficient optimizing method for the scale of regularization by using a generalized Akaike information criterion (network information criterion). We discuss the properties of the optimized regularization strength by NIC through theoretical analysis as well as computer simulations. We confirm the computational efficiency and generalization performance of the proposed method in real-world applications through computational experiments on benchmark problems.

Algorithms↗
PubMed2000

Infant artificial language learning and language acquisition.

The rapidity with which children acquire language is one of the mysteries of human cognition. A view held widely for the past 30 years is that children master language by means of a language-specific learning device. An earlier proposal, which has generated renewed interest, is that children make use of domain-general, associative learning mechanisms. However, our current lack of knowledge of the actual learning mechanisms involved during infancy makes it difficult to determine the relative contributions of innate and acquired knowledge. A recent approach to studying this problem exposes infants to artificial languages and assesses the resulting learning. In this article, we review studies using this paradigm that have led to a number of exciting discoveries regarding the learning mechanisms available during infancy. These studies raise important issues with respect to whether such mechanisms are general or specific to language, the extent to which they reflect statistical learning versus symbol manipulation, and the extent to which such mechanisms change with development. The fine-grained characterizations of infant learning mechanisms that this approach permits should result in a better understanding of the relative contributions of, and the dynamic between, innate and learned factors in language acquisition.

Journal Article↗
PubMed1999

What are the computations of the cerebellum, the basal ganglia and the cerebral cortex?

The classical notion that the cerebellum and the basal ganglia are dedicated to motor control is under dispute given increasing evidence of their involvement in non-motor functions. Is it then impossible to characterize the functions of the cerebellum, the basal ganglia and the cerebral cortex in a simplistic manner? This paper presents a novel view that their computational roles can be characterized not by asking what are the "goals" of their computation, such as motor or sensory, but by asking what are the "methods" of their computation, specifically, their learning algorithms. There is currently enough anatomical, physiological, and theoretical evidence to support the hypotheses that the cerebellum is a specialized organism for supervised learning, the basal ganglia are for reinforcement learning, and the cerebral cortex is for unsupervised learning.This paper investigates how the learning modules specialized for these three kinds of learning can be assembled into goal-oriented behaving systems. In general, supervised learning modules in the cerebellum can be utilized as "internal models" of the environment. Reinforcement learning modules in the basal ganglia enable action selection by an "evaluation" of environmental states. Unsupervised learning modules in the cerebral cortex can provide statistically efficient representation of the states of the environment and the behaving system. Two basic action selection architectures are shown, namely, reactive action selection and predictive action selection. They can be implemented within the anatomical constraint of the network linking these structures. Furthermore, the use of the cerebellar supervised learning modules for state estimation, behavioral simulation, and encapsulation of learned skill is considered. Finally, the usefulness of such theoretical frameworks in interpreting brain imaging data is demonstrated in the paradigm of procedural learning.

Journal Article↗
PubMed1998

Learning people's names following severe closed-head injury.

Although problems remembering people's names rank highly among the subjective complaints of patients with closed-head injuries, very few studies have examined their memory for people's names by objective measurements. An experiment is reported in which patients with severe closed-head injuries and normal controls learned the same set of words, either as names or as possessions, for unfamiliar faces. Name learning proved to be impaired in the patients. Patient recall of meaningless names and possessions which were described by nonwords was equally poor. The patients, but not the controls, recalled significantly fewer names than possessions if these items were described by concrete nouns. This last finding suggests that the patients' problems with learning people's names can not be fully explained by a general verbal learning impairment.

Adult↗
PubMed1994

Reducing Knowledge of Results About Relative Versus Absolute Timing: Differential Effects on Learning.

The purpose of the present experiment was to examine further earlier suggestions that a reduced relative frequency of knowledge of results (KR) can enhance the learning of generalized motor programs (GMPs) but at the same time degrade parameter learning, compared with giving KR after every trial (Wulf & Schmidt, 1989; Wulf, Schmidt, & Deubel, 1993). In contrast to these earlier studies, here KR was given separately for relative timing and absolute timing. Subjects practiced three movement patterns that required the same relative timing but different absolute movement times. KR was provided on 100% or 50% of the practice trials for relative timing or absolute timing, respectively. In retention and transfer tests, the groups that had had 50% KR about relative timing demonstrated more effective learning of the relative-timing structure, that is, GMP learning, than the groups that had had 100% KR about relative timing. The KR frequency had no effect on parameterization during retention; yet, when transfer to a task with a novel overall duration was required, the groups given 100% KR about absolute timing were more accurate in parameterization than the groups provided with 50% KR about absolute timing. Thus, the reduced relative KR frequency enhanced GMP learning but had no beneficial effect, or even a degrading effect, on parameter learning. The differential effects of a reduced KR frequency on the learning of relative timing and absolute timing also provide additional support for the dissociation of GMP and parameterization processes.

Journal Article↗
PubMed1999

Sequential RAM-based neural networks: learnability, generalisation, knowledge extraction, and grammatical inference.

A fundamental question in the field of artificial neural networks is what set of problems a given class of networks can perform (computability). Such a problem can be made less general, but no less important, by asking what these networks could learn by using a given training procedure (learnability). The basic purpose of this paper is to address the learnability problem. Specifically, it analyses the learnability of sequential RAM-based neural networks. The analytical tools used are those of Automata Theory. In this context, this paper establishes which class of problems and under what conditions such networks, together with their existing learning rules, can learn and generalize. This analysis also yields techniques for both extracting knowledge from and inserting knowledge into the networks. The results presented here, besides helping in a better understanding of the temporal behaviour of sequential RAM-based networks, could also provide useful insights for the integration of the symbolic/connectionist paradigms.

Algorithms↗
PubMed1993

Hippocampal mediation of stimulus representation: a computational theory.

The authors propose a computational theory of the hippocampal region's function in mediating stimulus representations. The theory assumes that the hippocampal region develops new stimulus representations that enhance the discriminability of differentially predictive cues while compressing the representation of redundant cues. Other brain regions, including cerebral and cerebellar cortices, are presumed to use these hippocampal representations to recode their own stimulus representations. In the absence of an intact hippocampal region, the theory implies that other brain regions will attempt to learn associations using previously established fixed representations. Instantiated as a connectionist network model, the theory provides a simple and unified interpretation of the functional role of the hippocampal region in a wide range of conditioning paradigms, including stimulus discrimination, reversal learning, stimulus generalization, latent inhibition, sensory preconditioning, and contextual sensitivity. The theory makes novel predictions regarding the effects of hippocampal lesions on easy-hard transfer and compound preexposure. Several prior qualitative characterizations of hippocampal function--including stimulus selection, chunking, cue configuration, and contextual coding--are identified as task-specific special cases derivable from this more general theory. The theory suggests that a profitable direction for future empirical and theoretical research will be the study of learning tasks in which both intact and lesioned animals exhibit similar initial learning behaviors but differ on subsequent transfer and generalization tasks.

Animals↗
PubMed2005

A Generalization Error for Q-Learning.

Planning problems that involve learning a policy from a single training set of finite horizon trajectories arise in both social science and medical fields. We consider Q-learning with function approximation for this setting and derive an upper bound on the generalization error. This upper bound is in terms of quantities minimized by a Q-learning algorithm, the complexity of the approximation space and an approximation term due to the mismatch between Q-learning and the goal of learning a policy that maximizes the value function.

Journal Article↗
PubMed1999

Bound-morpheme generalization by children with SLI: is there a functional relationship with accuracy of response to training targets?

We investigated whether limited bound-morpheme generalization (BMG) by preschool children with SLI is functionally related to limited learning of training targets (words, affixed forms). Thirty children with SLI and 30 age-/gender-matched controls participated in the study. Production probes revealed a dissociation between learning and generalization performance. In addition, the number of children who achieved criterion-level BMG increased abruptly during an additional instructional experience with new training targets. These findings suggest that positive evidence of a bound morpheme's generalizability to different vocabulary stems benefits BMG. Furthermore, they suggest that limited BMG reflects problems not with the storage or access of specific trained facts but with the extraction and extension of the linguistic pattern (e.g., regularity, "rule") instantiated in the learning targets.

Child, Preschool↗
PubMed1996

Generalization of form in visual pattern classification.

Human observers were trained to criterion in classifying compound Gabor signals with symmetry relationships, and were then tested with each of 18 blob-only versions of the learning set. Generalization to dark-only and light-only blob versions of the learning signals, as well as to dark-and-light blob versions was found to be excellent, thus implying virtually perfect generalization of the ability to classify mirror-image signals. The hypothesis that the learning signals are internally represented in terms of a 'blob code' with explicit labelling of contrast polarities was tested by predicting observed generalization behaviour in terms of various types of signal representations (pixelwise, Laplacian pyramid, curvature pyramid, ON/OFF, local maxima of Laplacian and curvature operators) and a minimum-distance rule. Most representations could explain generalization for dark-only and light-only blob patterns but not for the high-thresholded versions thereof. This led to the proposal of a structure-oriented blob-code. Whether such a code could be used in conjunction with simple classifiers or should be transformed into a propositional scheme of representation operated upon by a rule-based classification process remains an open question.

Adult↗
PubMed1963

PREDICTION OF DISCRIMINATION FROM GENERALIZATION AFTER VARIATIONS IN SCHEDULE OF REINFORCEMENT.

The relationship between generalization and discrimination is explored in the present study by utilizing the results of systematic changes in the generalization gradient to predict changes in discrimination behavior. In the first of two experiments, differing groups of pigeons were trained to respond to a wavelength of 550 mmicro under conditions of varying schedules of reinforcement. Generalization gradients were then obtained and the ratios of the responses to selected discriminative stimuli calculated. These were used to predict discrimination behavior in a second experiment using the same stimuli. Both the number of trials to a discrimination criterion and the ratio of response indicate the plausibilty of an inverse hypothesis, and the applicability of the generalization model to related behavior such as discrimination.

Animals↗