Types Of Prior Knowledge Research Articles

Constraining acyclicity of differentiable Bayesian structure learning with topological ordering

Distributional estimates in Bayesian approaches in structure learning have advantages compared to the ones performing point estimates when handling epistemic uncertainty. Differentiable methods for Bayesian structure learning have been developed to enhance the scalability of the inference process and are achieving optimistic outcomes. However, in the differentiable continuous setting, constraining the acyclicity of learned graphs emerges as another challenge. Various works utilize post-hoc penalization scores to impose this constraint which cannot assure acyclicity. The topological ordering of the variables is one type of prior knowledge that contains valuable information about the acyclicity of a directed graph. In this work, we propose a framework to guarantee the acyclicity of inferred graphs by integrating the information from the topological ordering into the inference process. Our integration framework does not interfere with the differentiable inference process while being able to strictly assure the acyclicity of learned graphs and reduce the inference complexity. Our extensive empirical experiments on both synthetic and real data have demonstrated the effectiveness of our approach with preferable results compared to related Bayesian approaches.

A multimodal breast cancer diagnosis method based on Knowledge-Augmented Deep Learning

Breast cancer is a worldwide medical challenge that requires Early diagnosis. While there are numerous diagnostic methods for breast cancer, many primarily focus on network structure, neglecting the guidance of professional medical knowledge. Moreover, these methods limit their analysis to 2-dimensional B-mode ultrasound images and rarely consider the potential insights provided by Contrast-Enhanced Ultrasound (CEUS) videos, which offer more detailed dynamic pathological information. Therefore, how to effectively utilize prior medical knowledge to achieve a precise diagnosis of breast cancer based on CEUS videos has emerged as a pressing issue. To address this challenge, we propose a multimodal breast cancer diagnostic method based on Knowledge-Augmented Deep Learning named KAMnet. This method integrates three types of prior knowledge into deep neural networks through different integration strategies. First, we devise a temporal segment selection strategy guided by Gaussian sampling through data-level integration, guiding the model to focus on keyframes. Second, we construct a feature fusion network for architecture-level integration and achieve collaborative inference through decision-level integration, facilitating multimodal information exchange. Finally, a spatial attention-guided loss function through training-level integration helps the model target lesion regions. We validate our model on our breast cancer video dataset consisting of 332 cases. The result shows that our model can achieve a sensitivity of 90.91% and an accuracy of 88.238%. Extensive ablation experiments demonstrate the effectiveness of our knowledge enhancement modules. The code is released at https://github.com/tobenan/BCCAD_torch.

How to identify pollen like a palynologist: A prior knowledge-guided deep feature learning for real-world pollen classification

Airborne pollen identification is crucial to help patients prevent pollinosis symptoms. Existing data-driven methods rely on large-scale pollen images with simple backgrounds. In real scenarios, the background is complex and the data scale is small. Therefore, these methods suffer from two challenges: (1) Irrelevant information interference; (2) Incomplete feature attention. To overcome these challenges, we propose a prior knowledge-guided deep feature learning (PK-DFL) for real-world optical microscope image classification. Its main steps are as follows: Pollen location is designed to locate pollen grains based on color features, aiming to boost the accuracy of shape and texture prior feature extraction. Shape-texture awareness helps to extract the shape and texture of pollen grains via predefined feature extractors (i.e., a set of shape descriptors and an improved SFTA). These features are used to construct two types of prior knowledge, namely shape-texture attention maps (STA maps) and shape-texture feature vectors (STF vectors). Pollen classification uses a deep network (CNN) to classify pollen via imitating the pollen identification procedure of palynologists. It uses STA maps to weight pollen images and convolutional feature maps for instructing the CNN to focus on critical areas of pollen images (for the first challenge). STF vectors are employed to obtain the inter-class similarity of pollen via template matching. This information is further converted to soft targets that are used to supervise the CNN attending to comprehensive key features (for the second challenge). Extensive experiments on real-world datasets demonstrate the effectiveness of our PK-DFL (with accuracy and F1-score over 88%).

Wooden spoon crack detection by prior knowledge-enriched deep convolutional network

Since the outbreak of COVID-19, in order to reduce people’s contact, the takeaway business has been developed rapidly, bringing a large demand for disposable and degradable tableware (e.g., wooden spoon). However, in the production process of wooden spoon, the selection of crack spoons still relies on manual labour. Therefore, in order to detect cracked wooden spoons more effectively and reduce production costs, we propose a wooden spoon crack detection method by using machine vision techniques and apply it in real-world industrial factory. In the production system, the captured color of crack regions is black while the good region shows normal log color. The positions of crack regions are located frequently in the central or marginal areas of spoons and their directions of cracks are often same due to the extrusion of the mold in the production process. Based on these two types of prior knowledge (i.e., color and spatial prior information), three modules are designed to explore these priors by jointly integrating with the current mainstream detection network of YOLO-v5, which satisfies the speed and accuracy for detecting cracks. The color fusion module is designed to explore the color difference between good regions and crack regions. The attention and orientation modules are then combined and embedded into the backbone of deep architecture. Reported experiments on our collected database show that our proposed detection method can locate the spoon cracks very well and significantly outperforms the model of YOLO-v5 with the protocols of Recall, Precision and meanAveragePrecision(mAP).

Knowledge-informed generative adversarial network for functional calibration of computer models

Functional model calibration considers the input dependency of model parameters by explicitly considering them as functional calibration parameters. In this study, a novel knowledge-informed generative adversarial network (KI-GAN) is proposed for the functional calibration of computer models under uncertainty. The proposed KI-GAN leverages the superior distribution learning ability of generative models for uncertainty quantification of model parameters and uses prior knowledge to inform generative model training by formulating a knowledge-based loss function that can easily incorporate different types of physical and expert knowledge of the computer model and its parameters. Two experiments are presented to demonstrate the effectiveness of the proposed KI-GAN for calibrating the functional model parameters under various scenarios. The results indicate that the proposed KI-GAN can effectively encode various types of prior knowledge on the computer model and its parameters, such as partial differential equation constraints and derivative constraints, which can significantly improve the parameter estimation accuracy and reduce estimation uncertainty. Furthermore, with appropriate constraints applied, the proposed KI-GAN can estimate model parameters with reasonable accuracy even under sparse and noisy observations and quantify the underlying uncertainties. Finally, the trained generators can accurately infer the probabilistic distributions of unobserved model outputs without running the computer model.

Prior Knowledge Guided Ultra-high Dimensional Variable Screening with Application to Neuroimaging Data.

Variable screening is a powerful and efficient tool for dimension reduction under ultrahigh dimensional settings. However, most existing methods overlook useful prior knowledge in specific applications. In this work, from a Bayesian modeling perspective, we develop a unified variable screening procedure for the linear regression model. We discuss different constructions of posterior mean screening (PMS) statistics to incorporate different types of prior knowledge according to specific applications. With non-informative prior specifications, PMS is equivalent to high-dimensional ordinary least-square projections (HOLP). We establish the screening consistency property for PMS with different types of prior knowledge. We show that PMS is robust to prior misspecifications; and when the prior knowledge provides correct information on summarizing the true parameter settings, PMS can substantially improve the selection accuracy compared to HOLP and other existing methods. We illustrate our method with extensive simulation studies and an analysis of neuroimaging data.

Reimagining American education: Possible futures: A curriculum that promotes civic ends and meets developmental needs

If schools are to prepare students to participate more productively in civic life, schools will need to ensure that they have opportunities to practice the skills of civic reasoning, argues Carol Lee. Yet schools are challenged by the limits in the curriculum and the difficulty of addressing the different types of prior knowledge that students bring to the classroom. Lee suggests that when schools build their content and pedagogy on current understandings of human learning, they will be better able to enable students from all backgrounds to practice building the understandings they need, now and in the future.

Weakly supervised instance segmentation using multi-prior fusion

Instance segmentation usually requires mask annotation, which has a much higher labeling cost than bounding box annotation. In recent years, weakly supervised instance segmentation (WSIS) has drawn great attention with only bounding box annotation needed during training. However, bounding box annotation can only provide limited information for the segmentation task. Without pixel-wise fine-grained supervision, predicted segmentation masks usually have blurred boundaries with poor performance. To address the issue caused by weak bounding box annotation, in this paper, two types of prior knowledge, i.e., bounding box tightness prior and contour prior, are employed to guide the mask prediction. For the bounding box tightness prior, we assume that the objects are annotated tightly with bounding boxes. A multi-instance learning (MIL) approach is adopted with the tightness constraint. For the contour prior, we assume that the mask boundaries should align with strong image gradients. We maximize the inner product of the gradients between the mask proposal and the corresponding image region, which is treated as the contour prior constraint. Finally, both prior constraints are combined for separating targets and background. The experiment results on the PASCAL VOC dataset and the augmented dataset demonstrate that our method outperforms most state-of-the-art WSIS methods.

Recognition of Basketball Player’s Shooting Action Based on the Convolutional Neural Network

In the field of basketball, the formulation of the existing training plan mainly relies on the coaches’ artificial observation and personal experience, which is inevitably subjective. The application of body domain network technology in athletes’ training and recognition of athletes’ postures can help coaches to assist decision-making and greatly improve athletes’ competitive ability. The human movements reflected in basketball are more complex which need deep understanding. The accuracy of basketball players’ shooting movements recognition plays a positive and important role in basketball games and training practice. Based on the prior knowledge of the convolutional neural network study, environment light conditions change the dynamic characteristics of basketball image analysis, capture images of the basketball goal algorithm of minimum circumscribed rectangle of the object, and based on the convolutional neural network, introduce two types of prior knowledge, one kind is based on the feature matching method that defined a priori knowledge, while another kind is based on training the convolution neural network model. The test results of the network model are taken as the prior knowledge, and then, a convolutional neural network dynamic target recognition model is constructed based on the prior knowledge. The construction process of the model is organized as the basketball target image is collected under any illumination conditions, the convolutional neural network model is trained with the convolutional neural network as the input data, and the standard illumination conditions are determined according to the test results of the network model. Then, put it into the trained network model to test and get the recognition results of basketball players’ shooting movements. The research is validated with performing experiments and the results revealed the success of the study.

Improving image quality in fast, time-resolved micro-CT by weighted back projection

Time-resolved micro-CT is an increasingly powerful technique for studying dynamic processes in materials and structures. However, it is still difficult to study very fast processes with this technique, since fast scanning is typically associated with high image noise levels. We present weighted back projection, a technique applicable in iterative reconstruction methods using two types of prior knowledge: (1) a virtual starting volume resembling the sample, for example obtained from a scan before the dynamic process was initiated, and (2) knowledge on which regions in the sample are more likely to undergo the dynamic process. Therefore, processes on which this technique is applicable are preferably occurring within a static grid. Weighted back projection has the ability to handle small errors in the prior knowledge, while similar 4D micro-CT techniques require the prior knowledge to be exactly correct. It incorporates the prior knowledge within the reconstruction by using a weight volume, representing for each voxel its probability of undergoing the dynamic process. Qualitative analysis on a sparse subset of projection data from a real micro-CT experiment indicates that this method requires significantly fewer projection angles to converge to a correct volume. This can lead to an improved temporal resolution.

How types of prior knowledge and task properties impact the category-based induction: diverging evidence from the P2, N400, and LPC effects

Category-based induction task was combined with ERP to unravel whether prior knowledge and property interact when inferring on genes or diseases. Larger P2 amplitudes for near taxonomic/causal distances relative to far ones, as well as larger LPC for taxonomic relation relative to thematic relation, are found in both gene and disease tasks. However, smaller N400 is found for taxonomic relation in gene task and thematic relation in disease task, respectively, and larger LPC at 700-850 ms for near taxonomic distance in the gene task and near causal distance in the disease task. These results suggested that the category-based inductive reasoning is context-sensitive, and there may be four stages of category-based inductive reasoning: the early automatic comparison of features/relations (P2), features/relations generalization process (N400), the extraction of common relationship/rule (LPC at 550-700 ms), the inference generation (LPC at 700-850 ms).

BENIN: Biologically enhanced network inference.

Gene regulatory network inference is one of the central problems in computational biology. We need models that integrate the variety of data available in order to use their complementarity information to overcome the issues of noisy and limited data. BENIN: Biologically Enhanced Network INference is our proposal to integrate data and infer more accurate networks. BENIN is a general framework that jointly considers different types of prior knowledge with expression datasets to improve the network inference. The method states the network inference as a feature selection problem and uses a popular penalized regression method, the Elastic net, combined with bootstrap resampling to solve it. BENIN significantly outperforms the state-of-the-art methods on the simulated data from the DREAM 4 challenge when combining genome-wide location data, knockout gene expression data, and time series expression data.

View and Clothing Invariant Gait Recognition via 3D Human Semantic Folding

A novel 3-dimensional (3D) human semantic folding is introduced to provide a robust and efficient gait recognition method which is invariant to camera view and clothing style. The proposed gait recognition method comprises three modules: (1) 3D body pose, shape and viewing data estimation network (3D-BPSVeNet); (2) gait semantic parameter folding model; and (3) gait semantic feature refining network. First, 3D-BPSVeNet is constructed based on a convolution gated recurrent unit (ConvGRU) to extract 2-dimensional (2D) to 3D body pose and shape semantic descriptors (2D-3D-BPSDs) from a sequence of gait parsed RGB images. A 3D gait model with virtual dressing is then constructed by morphing the template of 3D body model using the estimated 2D-3D-BPSDs and the recognized clothing styles. The more accurate 2D-3D-BPSDs without clothes are then obtained by using the silhouette similarity function when updating the 3D body model to fit the 2D gait. Second, the intrinsic 2D-3D-BPSDs without interference from clothes are encoded by sparse distributed representation (SDR) to gain the binary gait semantic image (SD-BGSI) in a topographical semantic space. By averaging the SD-BGSIs in a gait cycle, a gait semantic folding image (GSFI) is obtained to give a high-level representation of gait. Third, a gait semantic feature refining network is trained to refine the semantic feature extracted directly from GSFI using three types of prior knowledge, i.e., viewing angles, clothing styles and carrying condition. Experimental analyses on CMU MoBo, CASIA B, KY4D, OU-MVLP and OU-ISIR datasets show a significant performance gain in gait recognition in terms of accuracy and robustness.

A unified treatment of multiple testing with prior knowledge using the p-filter

There is a significant literature on methods for incorporating knowledge into multiple testing procedures so as to improve their power and precision. Some common forms of prior knowledge include (a) beliefs about which hypotheses are null, modeled by nonuniform prior weights; (b) differing importances of hypotheses, modeled by differing penalties for false discoveries; (c) multiple arbitrary partitions of the hypotheses into (possibly overlapping) groups and (d) knowledge of independence, positive or arbitrary dependence between hypotheses or groups, suggesting the use of more aggressive or conservative procedures. We present a unified algorithmic framework called p-filter for global null testing and false discovery rate (FDR) control that allows the scientist to incorporate all four types of prior knowledge (a)–(d) simultaneously, recovering a variety of known algorithms as special cases.

Preserved capacity for learning statistical regularities and directing selective attention after hippocampal lesions

Prior knowledge about the probabilistic structure of visual environments is necessary to resolve ambiguous information about objects in the world. Expectations based on stimulus regularities exert a powerful influence on human perception and decision making by improving the efficiency of information processing. Another type of prior knowledge, termed top-down attention, can also improve perceptual performance by facilitating the selective processing of relevant over irrelevant information. While much is known about attention, the mechanisms that support expectations about statistical regularities are not well-understood. The hippocampus has been implicated as a key structure involved in or perhaps necessary for the learning of statistical regularities, consistent with its role in various kinds of learning and memory. Here, we tested this hypothesis using a motion discrimination task in which we manipulated the most likely direction of motion, the degree of attention afforded to the relevant stimulus, and the amount of available sensory evidence. We tested memory-impaired patients with bilateral damage to the hippocampus and compared their performance with controls. Despite a modest slowing in response initiation across all task conditions, patients performed similar to controls. Like controls, patients exhibited a tendency to respond faster and more accurately when the motion direction was more probable, the stimulus was better attended, and more sensory evidence was available. Together, these findings demonstrate a robust, hippocampus-independent capacity for learning statistical regularities in the sensory environment in order to improve information processing.

Performance Research on Iterative Methods for Image Deblurring

This paper introduces the iterative image restoration algorithms for the elimination of linearly varying blurs from the images degraded by motion blur and additive noise. Iterative algorithms are very operative for this applications since they include different types of prior knowledge about the class of reasonable solutions. These algorithms are robust in nature to the errors in estimating the blurring operators and can be used to remove the non-stationary blurs. Performance analysis and limitations of traditional approaches such as Inverse, Wiener and Constrained Least Square filters (CLS) are discussed with respect to the iterations. Role and choice of imposing a constraint on the solutions of the algorithms which gives better restoration results are discussed. Regularization methods are debated to Minimis extreme noise amplifications due to ill-posed conditions in the inverse deblurring problems and it is shown that the reduction of noise effects can be achieved by terminating the algorithm after finite number of iterations. It is shown that restoration algorithms with constraints and spatially adaptability reduces the effects of ringing artifacts significantly. The rate of convergence of the algorithms based on the variations in the number of iterations are discussed and performance analysis, limitations and Comparison with the experimental results are presented.

Integration of prior knowledge during haptic exploration depends on information type.

When haptically exploring softness, humans use higher peak forces when indenting harder versus softer objects. Here, we investigated the influence of different channels and types of prior knowledge on initial peak forces. Participants explored two stimuli (hard vs. soft) and judged which was softer. In Experiment 1 participants received either semantic (the words "hard" and "soft"), visual (video of indentation), or prior information from recurring presentation (blocks of harder or softer pairs only). In a control condition no prior information was given (randomized presentation). In the recurring condition participants used higher initial forces when exploring harder stimuli. No effects were found in control and semantic conditions. With visual prior information, participants used less force for harder objects. We speculate that these findings reflect differences between implicit knowledge induced by recurring presentation and explicit knowledge induced by visual and semantic information. To test this hypothesis, we investigated whether explicit prior information interferes with implicit information in Experiment 2. Two groups of participants discriminated softness of harder or softer stimuli in two conditions (blocked and randomized). The interference group received additional explicit information during the blocked condition; the implicit-only group did not. Implicit prior information was only used for force adaptation when no additional explicit information was given, whereas explicit interfered with movement adaptation. The integration of prior knowledge only seems possible when implicit prior knowledge is induced-not with explicit knowledge.

Prior Knowledge-Based Probabilistic Collaborative Representation for Visual Recognition.

Collaborative representation is an effective way to design classifiers for many practical applications. In this paper, we propose a novel classifier, called the prior knowledge-based probabilistic collaborative representation-based classifier (PKPCRC), for visual recognition. Compared with existing classifiers which use the collaborative representation strategy, the proposed PKPCRC further includes characteristics of training samples of each class as prior knowledge. Four types of prior knowledge are developed from the perspectives of image distance and representation capacity. They adaptively accommodate the contribution of each class and result in an accurate representation to classify a query sample. Experiments and comparisons on four challenging databases demonstrate that PKPCRC outperforms several state-of-the-art classifiers.

Statistical evaluation of spectral interferences in laser-induced breakdown spectroscopy

Line broadening due to plasma processes or the instrument degrade spectral resolution leading to uncertainty in the elemental profile obtained by optical emission spectroscopy. A novel approach to quantify spectral interferences in laser-induced breakdown spectroscopy (LIBS) is introduced. This algorithm establishes a statistical interference factor (SIF) to quantify spectral interferences for individual line assignment in LIBS while using the full information provided by a spectrum. This factor combines fundamentals of plasma emission with a Bayesian analysis of the experimental spectrum using eventual prior knowledge about the sample and/or the conditions of analysis. Two types of prior knowledge were used to interpret spectra from a pure silicon sample as well as a NIST SRM 610 glass sample and alumina with a controlled Ni contamination at different concentrations. Knowledge of the elemental composition confirmed the existence of spectral lines with high sensitivity to interference while other lines are more appropriate for analysis due to their consistent SIFs despite having knowledge of the composition.

How Students Combine Resources to Make Conceptual Breakthroughs

We use the framework of cognitive resources to investigate how students construct understanding of a complex physics topic, namely, a photovoltaic cell. By observing students as they learn about how a solar cell functions, we identified over 60 distinct resources that learners may activate while thinking about photovoltaic cells. We classify these resources into three main types: phenomenological primitives, conceptual resources, and epistemological resources. Furthermore, we found a pattern that suggests that when students make conceptual breakthroughs they may be more likely to activate combinations of resources of different types in concert, especially if a resource from each of the three categories is used. This pattern suggests that physics instructors should encourage students to activate multiple types of prior knowledge during the learning process. This can result from instructors deliberately and explicitly connecting new knowledge to students’ prior experience both in and outside the formal physics classroom, as well as allowing students to reflect metacognitively on how the new knowledge fits into their existing understanding of the natural world.