An adaptive learning rate for RBFNN using time-domain feedback analysis.
Ontology highlight
ABSTRACT:
SUBMITTER: Ali SS
PROVIDER: S-EPMC3980919 | biostudies-other | 2014
REPOSITORIES: biostudies-other
Similar Datasets
Project description:This research has presented an optimum model for surface roughness prediction in a shop floor machining operation. The proposed solution is premised on difference analysis enhanced with a feedback control model capable of generating transient adaptive weights until a converging set point is attained. The surface roughness results utilized herein were adopted from two prior experiments in the literature. The design of experiment herein is premised on three cutting parameters in both experimental scenarios viz: feed rate, cutting speed and depth of cut for experimental dataset one and cutting speed, feed rate and flow rate for experimental dataset two. Three experimental levels were considered in both scenarios resulting in twenty-seven outcomes each. The simulation trial anchored on Matlab software was divided into two sub-categories viz: prediction of surface roughness for cutting combinations with vector points off the edges of the mesh referred to as off-edge cutting combinations (Off-ECC) and recovery of cutting combinations with positions on the edges of the mesh referred to as on-edge cutting combinations (On-ECC). The proposed hybrid scheme of difference analysis with feedback control premised on the use of dynamic weights produced an accurate output in comparison with the abductive, regression analysis and artificial neural network techniques as earlier utilized in the literature. The novelty of the proposed hybrid model lies in its high degree of prediction and recovery of existing datasets with an error margin approximately zero. This predictive efficacy is premised on the use of set points and transient dynamic weights for feedback iterations. The proposed solution technique in this research is quite consistent with its outputs and capable of working with very small to complex datasets.
| S-EPMC8035492 | biostudies-literature
Project description:School physical education (PE) has the potential to contribute to public-health promotion and well-being, but oftentimes students' lack of motivation toward PE or physical activity in general, especially during adolescence, diminishes, or eradicates the positive effects associated with PE. Therefore, practical approaches are required that help teachers to increase or awake students intrinsic motivation toward PE, for which self-determination theory may provide the conceptual framework. In that regard, the purpose of the present study was to examine whether the use of real-time, heart rate feedback (as a method to support students' need for autonomy and competence) during regular PE lessons has the potential to increase students' autonomous motivation and physical effort. To achieve this, we had forty healthy adolescents between 16 and 17 years of age run for 30 min either with (experimental group, EG) or without (control group, CG) real-time, individualized heart rate feedback during a regular PE class and compared physical and perceived exertion as well as joy of running between the two groups. Participants were randomly assigned to the groups. Our data revealed that participants in the EG enjoyed running more than participants in the CG (joy of running was 3.20 in the EG vs. 2.63 in the CG, p = 0.03) despite a higher physical (163 to 178 in EG vs. 141 to 156 beats per minute in the CG, p < 0.001) and perceived exertion (rating of perceived exertion of 13.22 in the EG vs. 10.59 in the CG, p = 0.02). That means, running with real-time, individualized heart rate feedback apparently increased participants' motivation to run and to enjoy running at higher levels of exertion. In that regard, real-time, individualized activity feedback should be implemented in regular PE classes systematically and repeatedly to create a controllable and attainable situation that allows students to actively adjust their own behavior to achieve appealing and realistic goals.
| S-EPMC8009282 | biostudies-literature
Project description:In any non-deterministic environment, unexpected events can indicate true changes in the world (and require behavioural adaptation) or reflect chance occurrence (and must be discounted). Adaptive behaviour requires distinguishing these possibilities. We investigated how humans achieve this by integrating high-level information from instruction and experience. In a series of EEG experiments, instructions modulated the perceived informativeness of feedback: Participants performed a novel probabilistic reinforcement learning task, receiving instructions about reliability of feedback or volatility of the environment. Importantly, our designs de-confound informativeness from surprise, which typically co-vary. Behavioural results indicate that participants used instructions to adapt their behaviour faster to changes in the environment when instructions indicated that negative feedback was more informative, even if it was simultaneously less surprising. This study is the first to show that neural markers of feedback anticipation (stimulus-preceding negativity) and of feedback processing (feedback-related negativity; FRN) reflect informativeness of unexpected feedback. Meanwhile, changes in P3 amplitude indicated imminent adjustments in behaviour. Collectively, our findings provide new evidence that high-level information interacts with experience-driven learning in a flexible manner, enabling human learners to make informed decisions about whether to persevere or explore new options, a pivotal ability in our complex environment.
| S-EPMC5312784 | biostudies-literature
Project description:Empathy allows us to respond to the emotional state of another person. Considering that an empathic interaction may last beyond the initial response, learning mechanisms may be involved in dynamic adaptation of the reaction to the changing emotional state of the other person. However, traditionally, empathy is assessed through sets of isolated reactions to another's distress. Here we address this gap by focusing on adaptive empathy, defined as the ability to learn and adjust one's empathic responses based on feedback. For this purpose, we designed a novel paradigm of associative learning in which participants chose one of two empathic strategies (reappraisal or distraction) to attenuate the distress of a target person, where one strategy had a higher probability of relieving distress. After each choice, participants received feedback about the success of their chosen strategy in relieving the target person's distress, which they could use to inform their future decisions. The results show that the participants made more accurate choices in the adaptive empathy condition than in a non-social control condition, pointing to an advantage for learning from social feedback. We found a correlation between adaptive empathy and a trait measure of cognitive empathy. These findings indicate that the ability to learn about the effectiveness of empathic responses may benefit from incorporating mentalizing abilities. Our findings provide a lab-based model for studying adaptive empathy and point to the potential contribution of learning theory to enhancing our understanding of the dynamic nature of empathy.
| S-EPMC8339423 | biostudies-literature
Project description:Closed-loop neurotechnologies often need to adaptively learn an encoding model that relates the neural activity to the brain state, and is used for brain state decoding. The speed and accuracy of adaptive learning algorithms are critically affected by the learning rate, which dictates how fast model parameters are updated based on new observations. Despite the importance of the learning rate, currently an analytical approach for its selection is largely lacking and existing signal processing methods vastly tune it empirically or heuristically. Here, we develop a novel analytical calibration algorithm for optimal selection of the learning rate in adaptive Bayesian filters. We formulate the problem through a fundamental trade-off that learning rate introduces between the steady-state error and the convergence time of the estimated model parameters. We derive explicit functions that predict the effect of learning rate on error and convergence time. Using these functions, our calibration algorithm can keep the steady-state parameter error covariance smaller than a desired upper-bound while minimizing the convergence time, or keep the convergence time faster than a desired value while minimizing the error. We derive the algorithm both for discrete-valued spikes modeled as point processes nonlinearly dependent on the brain state, and for continuous-valued neural recordings modeled as Gaussian processes linearly dependent on the brain state. Using extensive closed-loop simulations, we show that the analytical solution of the calibration algorithm accurately predicts the effect of learning rate on parameter error and convergence time. Moreover, the calibration algorithm allows for fast and accurate learning of the encoding model and for fast convergence of decoding to accurate performance. Finally, larger learning rates result in inaccurate encoding models and decoders, and smaller learning rates delay their convergence. The calibration algorithm provides a novel analytical approach to predictably achieve a desired level of error and convergence time in adaptive learning, with application to closed-loop neurotechnologies and other signal processing domains.
| S-EPMC5993334 | biostudies-literature
Project description:Fine-tuning is an important technique in transfer learning that has achieved significant success in tasks that lack training data. However, as it is difficult to extract effective features for single-source domain fine-tuning when the data distribution difference between the source and the target domain is large, we propose a transfer learning framework based on multi-source domain called adaptive multi-source domain collaborative fine-tuning (AMCF) to address this issue. AMCF utilizes multiple source domain models for collaborative fine-tuning, thereby improving the feature extraction capability of model in the target task. Specifically, AMCF employs an adaptive multi-source domain layer selection strategy to customize appropriate layer fine-tuning schemes for the target task among multiple source domain models, aiming to extract more efficient features. Furthermore, a novel multi-source domain collaborative loss function is designed to facilitate the precise extraction of target data features by each source domain model. Simultaneously, it works towards minimizing the output difference among various source domain models, thereby enhancing the adaptability of the source domain model to the target data. In order to validate the effectiveness of AMCF, it is applied to seven public visual classification datasets commonly used in transfer learning, and compared with the most widely used single-source domain fine-tuning methods. Experimental results demonstrate that, in comparison with the existing fine-tuning methods, our method not only enhances the accuracy of feature extraction in the model but also provides precise layer fine-tuning schemes for the target task, thereby significantly improving the fine-tuning performance.
| S-EPMC11232598 | biostudies-literature
Project description:A multiple-echo MR spectroscopic imaging (MRSI) method is presented that enables improved metabolite imaging in the presence of local field inhomogeneities and measurement of transverse relaxation parameters. Short echo spacing is used to maximize signal energy from inhomogeneously line-broadened resonances, and time domain parametric spectral analysis of the entire echo train is used to obtain sufficient spectral resolution from the shortened sampling periods. Optimal sequence parameters for 1H MRSI are determined by computer simulation, and performance is compared with conventional single-echo acquisition using phantom studies at a field strength of 4.7 T. A preliminary example for use at 1.5 T is also presented using phantom and human brain MRSI studies. This technique is shown to offer improved performance relative to single-echo MRSI for imaging of metabolites with shortened T2* values due to the presence of local field inhomogeneities. Additional advantages are the intrinsic measurement of metabolite T2 values and determination of metabolite integrals without T2 weighting, thereby facilitating quantitative metabolite imaging.
| S-EPMC2780031 | biostudies-other
Project description:Computer vision approaches have made significant inroads into offline tracking of behavior and estimating animal poses. In particular, because of their versatility, deep-learning approaches have been gaining attention in behavioral tracking without any markers. Here, we developed an approach using DeepLabCut for real-time estimation of movement. We trained a deep-neural network (DNN) offline with high-speed video data of a mouse whisking, then transferred the trained network to work with the same mouse, whisking in real-time. With this approach, we tracked the tips of three whiskers in an arc and converted positions into a TTL output within behavioral time scales, i.e., 10.5 ms. With this approach, it is possible to trigger output based on movement of individual whiskers, or on the distance between adjacent whiskers. Flexible closed-loop systems like the one we have deployed here can complement optogenetic approaches and can be used to directly manipulate the relationship between movement and neural activity.
| S-EPMC8174057 | biostudies-literature
Project description:Multi-exposure laser speckle contrast imaging (MELSCI) estimates microcirculatory blood perfusion more accurately than single-exposure LSCI. However, the technique has been hampered by technical limitations due to massive data throughput requirements and nonlinear inverse search algorithms, limiting it to an offline technique where data must be postprocessed. To present an MELSCI system capable of continuous acquisition and processing of MELSCI data, enabling real-time video-rate perfusion imaging with high accuracy. The MELSCI algorithm was implemented in programmable hardware (field programmable gate array) closely interfaced to a high-speed CMOS sensor for real-time calculation. Perfusion images were estimated in real-time from the MELSCI data using an artificial neural network trained on simulated data. The MELSCI perfusion was compared to two existing single-exposure metrics both quantitatively in a controlled phantom experiment and qualitatively in vivo. The MELSCI perfusion shows higher signal dynamics compared to both single-exposure metrics, both spatially and temporally where heartbeat-related variations are resolved in much greater detail. The MELSCI perfusion is less susceptible to measurement noise and is more linear with respect to laser Doppler perfusion in the phantom experiment (R2 = 0.992). The presented MELSCI system allows for real-time acquisition and calculation of high-quality perfusion at 15.6 frames per second.
| S-EPMC7666876 | biostudies-literature
Project description:Machine learning techniques that rely on textual features or sentiment lexicons can lead to erroneous sentiment analysis. These techniques are especially vulnerable to domain-related difficulties, especially when dealing in Big data. In addition, labeling is time-consuming and supervised machine learning algorithms often lack labeled data. Transfer learning can help save time and obtain high performance with fewer datasets in this field. To cope this, we used a transfer learning-based Multi-Domain Sentiment Classification (MDSC) technique. We are able to identify the sentiment polarity of text in a target domain that is unlabeled by looking at reviews in a labelled source domain. This research aims to evaluate the impact of domain adaptation and measure the extent to which transfer learning enhances sentiment analysis outcomes. We employed transfer learning models BERT, RoBERTa, ELECTRA, and ULMFiT to improve the performance in sentiment analysis. We analyzed sentiment through various transformer models and compared the performance of LSTM and CNN. The experiments are carried on five publicly available sentiment analysis datasets, namely Hotel Reviews (HR), Movie Reviews (MR), Sentiment140 Tweets (ST), Citation Sentiment Corpus (CSC), and Bioinformatics Citation Corpus (BCC), to adapt multi-target domains. The performance of numerous models employing transfer learning from diverse datasets demonstrating how various factors influence the outputs.
| S-EPMC10984522 | biostudies-literature