The automated machine learning (AutoML) process can require searching through complex configuration spaces of not only machine learning (ML) components and their hyperparameters but also ways of composing them together, i.e. forming ML pipelines. Optimisation efficiency and the model accuracy attainable for a fixed time budget suffer if this pipeline configuration space is excessively large. A key research question is whether it is both possible and practical to preemptively avoid costly evaluations of poorly performing ML pipelines by leveraging their historical performance for various ML tasks, i.e. meta-knowledge. The previous experience comes in the form of classifier/regressor accuracy rankings derived from either (1) a substantial but non-exhaustive number of pipeline evaluations made during historical AutoML runs, i.e. 'opportunistic' meta-knowledge, or (2) comprehensive cross-validated evaluations of classifiers/regressors with default hyperparameters, i.e. 'systematic' meta-knowledge. Numerous experiments with the AutoWeka4MCPS package suggest that (1) opportunistic/systematic meta-knowledge can improve ML outcomes, typically in line with how relevant that meta-knowledge is, and (2) configuration-space culling is optimal when it is neither too conservative nor too radical. However, the utility and impact of meta-knowledge depend critically on numerous facets of its generation and exploitation, warranting extensive analysis; these are often overlooked/underappreciated within AutoML and meta-learning literature. In particular, we observe strong sensitivity to the `challenge' of a dataset, i.e. whether specificity in choosing a predictor leads to significantly better performance. Ultimately, identifying `difficult' datasets, thus defined, is crucial to both generating informative meta-knowledge bases and understanding optimal search-space reduction strategies.

Advances in machine learning and contactless sensors have enabled the understanding complex human behaviors in a healthcare setting. In particular, several deep learning systems have been introduced to enable comprehensive analysis of neuro-developmental conditions such as Autism Spectrum Disorder (ASD). This condition affects children from their early developmental stages onwards, and diagnosis relies entirely on observing the child's behavior and detecting behavioral cues. However, the diagnosis process is time-consuming as it requires long-term behavior observation, and the scarce availability of specialists. We demonstrate the effect of a region-based computer vision system to help clinicians and parents analyze a child's behavior. For this purpose, we adopt and enhance a dataset for analyzing autism-related actions using videos of children captured in uncontrolled environments (e.g. videos collected with consumer-grade cameras, in varied environments). The data is pre-processed by detecting the target child in the video to reduce the impact of background noise. Motivated by the effectiveness of temporal convolutional models, we propose both light-weight and conventional models capable of extracting action features from video frames and classifying autism-related behaviors by analyzing the relationships between frames in a video. Through extensive evaluations on the feature extraction and learning strategies, we demonstrate that the best performance is achieved with an Inflated 3D Convnet and Multi-Stage Temporal Convolutional Networks, achieving a 0.83 Weighted F1-score for classification of the three autism-related actions, outperforming existing methods. We also propose a light-weight solution by employing the ESNet backbone within the same system, achieving competitive results of 0.71 Weighted F1-score, and enabling potential deployment on embedded systems.

Signal Processing: Image Communication manuscript No. (will be inserted by the editor) Abstract While storing invoice content as metadata comparison of 9 AC per manually processed invoice and to avoid paper document processing may be the future 2 AC per automated processing of one invoice based on trend, almost all of daily issued invoices are still surveys in 2004 and 2003 respectively. A 2016 report by printed on paper or generated in digital formats such the Institute of Finance and Management [2] suggested as PDFs. In this paper, we introduce the OCRMiner that the average cost to process an invoice was $12.90. The system on Scanned Receipt OCR and Information Extraction is designed to process the document in a similar way a (SROIE) at ICDAR 2019 [3] or the Mobile-Captured human reader uses, i.e. to employ different layout and Image Document Recognition for Vietnamese Receipts text attributes in a coordinated decision. Still, annotated benchmark invoice consists of a set of interconnected modules that start datasets are not generally available due to confidential with (possibly erroneous) character-based output from information, and the published papers do not offer a standard OCR system and allow to apply different detailed dataset descriptions and error analyses of the techniques and to expand the extracted knowledge at content. Moreover, although receipts and invoices have each step. Using an open source OCR, the system is some common attributes, their analyses differ vastly able to recover the invoice data in 90% for English and due to complex graphical layouts and richer content in 88% for the Czech set. In 2006, Lewis et al. [6] published the IIT 1 Introduction Complex Document Information Processing Test Collection (IIT-CDIP) based on the Legacy Tobacco Documents Automatic invoice processing systems gain significant Library, containing roughly 40 millions scanned interest of large companies who deal with enormous pages for evaluation of document information processing numbers of invoices each day, due to not only their tasks.

When the historical data are limited, the conditional probabilities associated with the nodes of Bayesian networks are uncertain and can be empirically estimated. Second order estimation methods provide a framework for both estimating the probabilities and quantifying the uncertainty in these estimates. We refer to these cases as uncer tain or second-order Bayesian networks. When such data are complete, i.e., all variable values are observed for each instantiation, the conditional probabilities are known to be Dirichlet-distributed. This paper improves the current state-of-the-art approaches for handling uncertain Bayesian networks by enabling them to learn distributions for their parameters, i.e., conditional probabilities, with incomplete data. We extensively evaluate various methods to learn the posterior of the parameters through the desired and empirically derived strength of confidence bounds for various queries.

In this paper, we propose a new dense retrieval model which learns diverse document representations with deep query interactions. Our model encodes each document with a set of generated pseudo-queries to get query-informed, multi-view document representations. It not only enjoys high inference efficiency like the vanilla dual-encoder models, but also enables deep query-document interactions in document encoding and provides multi-faceted representations to better match different queries. Experiments on several benchmarks demonstrate the effectiveness of the proposed method, out-performing strong dual encoder baselines.The code is available at \url{https://github.com/jordane95/dual-cross-encoder

Total knee arthroplasty (TKA) is a common orthopaedic surgery to replace a damaged knee joint with artificial implants. The inaccuracy of achieving the planned implant position can result in the risk of implant component aseptic loosening, wear out, and even a joint revision, and those failures most of the time occur on the tibial side in the conventional jig-based TKA (CON-TKA). This study aims to precisely evaluate the accuracy of the proximal tibial resection plane intra-operatively in real-time such that the evaluation processing changes very little on the CON-TKA operative procedure. Two X-ray radiographs captured during the proximal tibial resection phase together with a pre-operative patient-specific tibia 3D mesh model segmented from computed tomography (CT) scans and a trocar pin 3D mesh model are used in the proposed simultaneous localisation and mapping (SLAM) system to estimate the proximal tibial resection plane. Validations using both simulation and in-vivo datasets are performed to demonstrate the robustness and the potential clinical value of the proposed algorithm.

In terms of the operation of microgrids, optimal scheduling is a vital issue that must be taken into account. In this regard, this paper proposes an effective framework for optimal scheduling of renewable microgrids considering energy storage devices, wind turbines, micro turbines. Due to the nonlinearity and complexity of operation problems in microgrids, it is vital to use an accurate and robust optimization technique to efficiently solve this problem. To this end, in the proposed framework, the teacher learning-based optimization is utilized to efficiently solve the scheduling problem in the system. Moreover, a deep learning model based on bidirectional long short-term memory is proposed to address the short-term wind power forecasting problem. The feasibility and performance of the proposed framework as well as the effect of wind power forecasting on the operation efficiency are examined using IEEE 33-bus test system. Also, the Australian Wool north wind site data is utilized as a real-world dataset to evaluate the performance of the forecasting model. Results show the effective and efficient performance of the proposed framework in the optimal scheduling of microgrids.

On practical applications, state-of-the-art SAT solvers dominantly use the conflict-driven clause learning (CDCL) paradigm. An alternative for satisfiable instances is local search solvers, which is more successful on random and hard combinatorial instances. Although there have been attempts to combine these methods in one framework, a tight integration which improves the state of the art on a broad set of application instances has been missing. We present a combination of techniques that achieves such an improvement. Our first contribution is to maximize in a local search fashion the assignment trail in CDCL, by sticking to and extending promising assignments via a technique called target phases. Second, we relax the CDCL framework by again extending promising branches to complete assignments while ignoring conflicts. These assignments are then used as starting point of local search which tries to find improved assignments with fewer unsatisfied clauses. Third, these improved assignments are imported back to the CDCL loop where they are used to determine the value assigned to decision variables. Finally, the conflict frequency of variables in local search can be exploited during variable selection in branching heuristics of CDCL. We implemented these techniques to improve three representative CDCL solvers (Glucose, MapleLcm DistChronoBT, and Kissat). Experiments on benchmarks from the main tracks of the last three SAT Competitions from 2019 to 2021 and an additional benchmark set from spectrum allocation show that the techniques bring significant improvements, particularly and not surprisingly, on satisfiable real-world application instances. We claim that these techniques were essential to the large increase in performance witnessed in the SAT Competition 2020 where Kissat and Relaxed LcmdCbDl NewTech were leading the field followed by CryptoMiniSAT-Ccnr, which also incorporated similar ideas.

The neural tangent kernel is a kernel function defined over the parameter distribution of an infinite width neural network. Despite the impracticality of this limit, the neural tangent kernel has allowed for a more direct study of neural networks and a gaze through the veil of their black box. More recently, it has been shown theoretically that the Laplace kernel and neural tangent kernel share the same reproducing kernel Hilbert space in the space of $\mathbb{S}^{d-1}$ alluding to their equivalence. In this work, we analyze the practical equivalence of the two kernels. We first do so by matching the kernels exactly and then by matching posteriors of a Gaussian process. Moreover, we analyze the kernels in $\mathbb{R}^d$ and experiment with them in the task of regression.

For energy-efficient computation in specialized neuromorphic hardware, we present spiking neural coding, an instantiation of a family of artificial neural models grounded in the theory of predictive coding. This model, the first of its kind, works by operating in a never-ending process of "guess-and-check", where neurons predict the activity values of one another and then adjust their own activities to make better future predictions. The interactive, iterative nature of our system fits well into the continuous time formulation of sensory stream prediction and, as we show, the model's structure yields a local synaptic update rule, which can be used to complement or as an alternative to online spike-timing dependent plasticity. In this article, we experiment with an instantiation of our model consisting of leaky integrate-and-fire units. However, the framework within which our system is situated can naturally incorporate more complex neurons such as the Hodgkin-Huxley model. Our experimental results in pattern recognition demonstrate the potential of the model when binary spike trains are the primary paradigm for inter-neuron communication. Notably, spiking neural coding is competitive in terms of classification performance and experiences less forgetting when learning from task sequence, offering a more computationally economical, biologically-plausible alternative to popular artificial neural networks.