Visual Tracking With Convolutional Random Vector Functional Link Network

Robust Incremental Broad Learning System for Data Streams of Uncertain Scale

Due to its marvelous performance and remarkable scalability, a broad learning system (BLS) has aroused a wide range of attention. However, its incremental learning suffers from low accuracy and long training time, especially when dealing with unstable data streams, making it difficult to apply in real-world scenarios. To overcome these issues and enrich its relevant research, a robust incremental BLS (RI-BLS) is proposed. In this method, the proposed weight update strategy introduces two memory matrices to store the learned information, thus the computational procedure of ridge regression is decomposed, resulting in precomputed ridge regression. During incremental learning, RI-BLS updates two memory matrices and renews weights via precomputed ridge regression efficiently. In addition, this update strategy is theoretically analyzed in error, time complexity, and space complexity compared with existing incremental BLSs. Different from Greville's method used in the original incremental BLS, its results are closer to the solution of one-shot calculation. Compared with the existing incremental BLSs, the proposed method exhibits more stable time complexity and superior space complexity. The experiments prove that RI-BLS outperforms other incremental BLSs when handling both stable and unstable data streams. Furthermore, experiments demonstrate that the proposed weight update strategy applies to other random neural networks as well.

An ensemble multi-dimensional randomization network for intelligent recognition of tobacco baking stage

In recent years, image processing technology has been increasingly studied on intelligent unmanned platforms, and the differences in the shooting environment during tobacco baking pose challenges to image processing algorithms. To address this problem, an ensemble multi-dimensional randomization network (EMRNet) for intelligent recognition of tobacco baking stage is proposed. The first is to obtain the tobacco leaf area during the baking process. Then, a multi-dimensional randomization network (MRNet) is designed to recognize tobacco baking stage. The effectiveness of MRNet lies in multi-scale hidden layer feature extraction, which can effectively enhance the expression ability of features to overcome the impact of differences between different environments on the tobacco baking stage. Finally, MRNet is used as component learner for constructing an ensemble randomization network structure to distinguish the tobacco baking stage. On the constructed tobacco baking stage dataset, EMRNet achieves 89.14% accuracy with 642.96MFLOPs. Compared with SVM, MLP, BP, ELM, CRVFL and other algorithms, EMRNet shows excellent performance in accuracy and model complexity. The proposed method explores the application of image processing technology in crop baking and drying, providing theoretical support for intelligent baking technology.

Multimodal Alzheimer's disease classification through ensemble deep random vector functional link neural network

Alzheimer's disease (AD) is a condition with a complex pathogenesis, sometimes hereditary, characterized by the loss of neurons and synapses, along with the presence of senile plaques and neurofibrillary tangles. Early detection, particularly among individuals at high risk, is critical for effective treatment or prevention, yet remains challenging due to data variability and incompleteness. Most current research relies on single data modalities, potentially limiting comprehensive staging of AD. This study addresses this gap by integrating multimodal data-including clinical and genetic information-using deep learning (DL) models, with a specific focus on random vector functional link (RVFL) networks, to enhance early detection of AD and mild cognitive impairment (MCI). Our findings demonstrate that ensemble deep RVFL (edRVFL) models, when combined with effective data imputation techniques such as Winsorized-mean (Wmean), achieve superior performance in detecting early stages of AD. Notably, the edRVFL model achieved an accuracy of 98.8%, precision of 98.3%, recall of 98.4%, and F1-score of 98.2%, outperforming traditional machine learning models like support vector machines, random forests, and decision trees. This underscores the importance of integrating advanced imputation strategies and deep learning techniques in AD diagnosis.

Coupled Multimodal Emotional Feature Analysis Based on Broad-Deep Fusion Networks in Human-Robot Interaction

A coupled multimodal emotional feature analysis (CMEFA) method based on broad-deep fusion networks, which divide multimodal emotion recognition into two layers, is proposed. First, facial emotional features and gesture emotional features are extracted using the broad and deep learning fusion network (BDFN). Considering that the bi-modal emotion is not completely independent of each other, canonical correlation analysis (CCA) is used to analyze and extract the correlation between the emotion features, and a coupling network is established for emotion recognition of the extracted bi-modal features. Both simulation and application experiments are completed. According to the simulation experiments completed on the bimodal face and body gesture database (FABO), the recognition rate of the proposed method has increased by 1.15% compared to that of the support vector machine recursive feature elimination (SVMRFE) (without considering the unbalanced contribution of features). Moreover, by using the proposed method, the multimodal recognition rate is 21.22%, 2.65%, 1.61%, 1.54%, and 0.20% higher than those of the fuzzy deep neural network with sparse autoencoder (FDNNSA), ResNet-101 + GFK, C3D + MCB + DBN, the hierarchical classification fusion strategy (HCFS), and cross-channel convolutional neural network (CCCNN), respectively. In addition, preliminary application experiments are carried out on our developed emotional social robot system, where emotional robot recognizes the emotions of eight volunteers based on their facial expressions and body gestures.

Ensemble Deep Random Vector Functional Link Network Using Privileged Information for Alzheimer's Disease Diagnosis

Alzheimer's disease (AD) is a progressive brain disorder. Machine learning models have been proposed for the diagnosis of AD at early stage. Recently, deep learning architectures have received quite a lot attention. Most of the deep learning architectures suffer from the issues of local minima, slow convergence and sensitivity to learning rate. To overcome these issues, non-iterative learning based deep randomized models especially random vector functional link network (RVFL) with direct links have proven to be successful. However, deep RVFL and its ensemble models are trained only on normal samples. In this paper, deep RVFL and its ensembles are enabled to incorporate privileged information, as the standard RVFL model and its deep models are unable to use privileged information. To fill this gap, we have incorporated learning using privileged information (LUPI) in deep RVFL model, and propose deep RVFL with LUPI framework (dRVFL+). Privileged information is available while training the models. As RVFL is an unstable classifier, we propose ensemble deep RVFL+ with LUPI framework (edRVFL+) which exploits the LUPI as well as the diversity among the base leaners for better classification. Unlike traditional ensemble approach wherein multiple base learners are trained, the proposed edRVFL+ model optimises a single network and generates an ensemble via optimization at different levels of random projections of the data. Both dRVFL+ and edRVFL+ efficiently utilise the privileged information which results in better generalization performance. In LUPI framework, half of the available features are used as normal features and rest as the privileged features. However, we propose a novel approach for generating the privileged information. We utilise different activation functions while processing the normal and privileged information in the proposed deep architectures. To the best of our knowledge, this is first time that a separate privileged information is generated. The proposed dRVFL+ and edRVFL+ models are employed for the diagnosis of Alzheimer's disease. Experimental results demonstrate the superiority of the proposed dRVFL+ and edRVFL+ models over baseline models. Thus, the proposed edRVFL+ model can be utilised in clinical setting for the diagnosis of AD.

Robust noise-aware algorithm for randomized neural network and its convergence properties

The concept of randomized neural networks (RNNs), such as the random vector functional link network (RVFL) and extreme learning machine (ELM), is a widely accepted and efficient network method for constructing single-hidden layer feedforward networks (SLFNs). Due to its exceptional approximation capabilities, RNN is being extensively used in various fields. While the RNN concept has shown great promise, its performance can be unpredictable in imperfect conditions, such as weight noises and outliers. Thus, there is a need to develop more reliable and robust RNN algorithms. To address this issue, this paper proposes a new objective function that addresses the combined effect of weight noise and training data outliers for RVFL networks. Based on the half-quadratic optimization method, we then propose a novel algorithm, named noise-aware RNN (NARNN), to optimize the proposed objective function. The convergence of the NARNN is also theoretically validated. We also discuss the way to use the NARNN for ensemble deep RVFL (edRVFL) networks. Finally, we present an extension of the NARNN to concurrently address weight noise, stuck-at-fault, and outliers. The experimental results demonstrate that the proposed algorithm outperforms a number of state-of-the-art robust RNN algorithms.

Convolutional Neural Networks in the Diagnosis of Colon Adenocarcinoma

Colorectal cancer is one of the most lethal cancers because of late diagnosis and challenges in the selection of therapy options. The histopathological diagnosis of colon adenocarcinoma is hindered by poor reproducibility and a lack of standard examination protocols required for appropriate treatment decisions. In the current study, using state-of-the-art approaches on benchmark datasets, we analyzed different architectures and ensembling strategies to develop the most efficient network combinations to improve binary and ternary classification. We propose an innovative two-stage pipeline approach to diagnose colon adenocarcinoma grading from histological images in a similar manner to a pathologist. The glandular regions were first segmented by a transformer architecture with subsequent classification using a convolutional neural network (CNN) ensemble, which markedly improved the learning efficiency and shortened the learning time. Moreover, we prepared and published a dataset for clinical validation of the developed artificial neural network, which suggested the discovery of novel histological phenotypic alterations in adenocarcinoma sections that could have prognostic value. Therefore, AI could markedly improve the reproducibility, efficiency, and accuracy of colon cancer diagnosis, which are required for precision medicine to personalize the treatment of cancer patients.

Gravity-Based Community Vulnerability Evaluation Model in Social Networks: GBCVE

The usage of social media around the world is ever-increasing. Social media statistics from 2019 show that there are 3.5 billion social media users worldwide. However, the existence of community structure renders the network vulnerable to attacks and large-scale losses. How does one comprehensively consider the multiple information sources and effectively evaluate the vulnerability of the community? To answer this question, we design a gravity-based community vulnerability evaluation (GBCVE) model for multiple information considerations. Specifically, we construct the community network by the Jensen-Shannon divergence and log-sigmoid transition function to show the relationship between communities. The number of edges inside community and outside of each community, as well as the gravity index are the three important factors used in this model for evaluating the community vulnerability. These three factors correspond to the interior information of the community, small-scale interaction relationship, and large-scale interaction relationship, respectively. A fuzzy ranking algorithm is then used to describe the vulnerability relationship between different communities, and the sensitivity of different weighting parameters is then analyzed by Sobol' indices. We validate and demonstrate the applicability of our proposed community vulnerability evaluation method via three real-world complex network test examples. Our proposed model can be applied to find vulnerable components in a network to mitigate the influence of public opinions or natural disasters in real time. The community vulnerability evaluation results from our proposed model are expected to shed light on other properties of communities within social networks and have real-world applications across network science.

Random Fourier features-based sparse representation classifier for identifying DNA-binding proteins

DNA-binding proteins (DBPs) protect DNA from nuclease hydrolysis, inhibit the action of RNA polymerase, prevents replication and transcription from occurring simultaneously on a piece of DNA. Most of the conventional methods for detecting DBPs are biochemical methods, but the time cost is high. In recent years, a variety of machine learning-based methods that have been used on a large scale for large-scale screening of DBPs. To improve the prediction performance of DBPs, we propose a random Fourier features-based sparse representation classifier (RFF-SRC), which randomly map the features into a high-dimensional space to solve nonlinear classification problems. And L_2,1-matrix norm is introduced to get sparse solution of model. To evaluate performance, our model is tested on several benchmark data sets of DBPs and 8 UCI data sets. RFF-SRC achieves better performance in experimental results.

Research Review for Broad Learning System: Algorithms, Theory, and Applications

In recent years, the appearance of the broad learning system (BLS) is poised to revolutionize conventional artificial intelligence methods. It represents a step toward building more efficient and effective machine-learning methods that can be extended to a broader range of necessary research fields. In this survey, we provide a comprehensive overview of the BLS in data mining and neural networks for the first time, focusing on summarizing various BLS methods from the aspects of its algorithms, theories, applications, and future open research questions. First, we introduce the basic pattern of BLS manifestation, the universal approximation capability, and essence from the theoretical perspective. Furthermore, we focus on BLS's various improvements based on the current state of the theoretical research, which further improves its flexibility, stability, and accuracy under general or specific conditions, including classification, regression, semisupervised, and unsupervised tasks. Due to its remarkable efficiency, impressive generalization performance, and easy extendibility, BLS has been applied in different domains. Next, we illustrate BLS's practical advances, such as computer vision, biomedical engineering, control, and natural language processing. Finally, the future open research problems and promising directions for BLSs are pointed out.

Efficient and accurate diagnosis of otomycosis using an ensemble deep-learning model

Otomycosis accounts for over 15% of cases of external otitis worldwide. It is common in humid regions and Chinese cultures with ear-cleaning custom. Aspergillus and Candida are the major pathogens causing long-term infection. Early endoscopic and microbiological examinations, performed by otologists and microbiologists, respectively, are important for the appropriate medical treatment of otomycosis. The deep-learning model is a novel automatic diagnostic program that provides quick and accurate diagnoses using a large database of images acquired in clinical settings. The aim of the present study was to introduce a machine-learning model to accurately and quickly diagnose otomycosis caused by Aspergillus and Candida. We propose a computer-aided decision-making system based on a deep-learning model comprising two subsystems: Java web application and image classification. The web application subsystem provides a user-friendly webpage to collect consulted images and display the calculation results. The image classification subsystem mainly trained neural network models for end-to-end data inference. The end user uploads a few images obtained with the ear endoscope, and the system returns the classification results to the user in the form of category probability values. To accurately diagnose otomycosis, we used otoendoscopic images and fungal culture secretion. Fungal fluorescence, culture, and DNA sequencing were performed to confirm the pathogens Aspergillus or Candida spp. In addition, impacted cerumen, external otitis, and normal external auditory canal endoscopic images were retained for reference. We merged these four types of images into an otoendoscopic image gallery. To achieve better accuracy and generalization abilities after model-training, we selected 2,182 of approximately 4,000 ear endoscopic images as training samples and 475 as validation samples. After selecting the deep neural network models, we tested the ResNet, SENet, and EfficientNet neural network models with different numbers of layers. Considering the accuracy and operation speed, we finally chose the EfficientNetB6 model, and the probability values of the four categories of otomycosis, impacted cerumen, external otitis, and normal cases were outputted. After multiple model training iterations, the average accuracy of the overall validation sample reached 92.42%. The results suggest that the system could be used as a reference for general practitioners to obtain more accurate diagnoses of otomycosis.

SiamATL: Online Update of Siamese Tracking Network via Attentional Transfer Learning

Visual object tracking with semantic deep features has recently attracted much attention in computer vision. Especially, Siamese trackers, which aim to learn a decision making-based similarity evaluation, are widely utilized in the tracking community. However, the online updating of the Siamese fashion is still a tricky issue due to the limitation, which is a tradeoff between model adaption and degradation. To address such an issue, in this article, we propose a novel attentional transfer learning-based Siamese network (SiamATL), which fully exploits the previous knowledge to inspire the current tracker learning in the decision-making module. First, we explicitly model the template and surroundings by using an attentional online update strategy to avoid template pollution. Then, we introduce an instance-transfer discriminative correlation filter (ITDCF) to enhance the distinguishing ability of the tracker. Finally, we suggest a mutual compensation mechanism that integrates cross-correlation matching and ITDCF detection into the decision-making subnetwork to achieve online tracking. Comprehensive experiments demonstrate that our approach outperforms state-of-the-art tracking algorithms on multiple large-scale tracking datasets.

SAFNet: A deep spatial attention network with classifier fusion for breast cancer detection

Breast cancer is a top dangerous killer for women. An accurate early diagnosis of breast cancer is the primary step for treatment. A novel breast cancer detection model called SAFNet is proposed based on ultrasound images and deep learning. We employ a pre-trained ResNet-18 embedded with the spatial attention mechanism as the backbone model. Three randomized network models are trained for prediction in the SAFNet, which are fused by majority voting to produce more accurate results. A public ultrasound image dataset is utilized to evaluate the generalization ability of our SAFNet using 5-fold cross-validation. The simulation experiments reveal that the SAFNet can produce higher classification results compared with four existing breast cancer classification methods. Therefore, our SAFNet is an accurate tool to detect breast cancer that can be applied in clinical diagnosis.

Progressive Multistage Learning for Discriminative Tracking

Visual tracking is typically solved as a discriminative learning problem that usually requires high-quality samples for online model adaptation. It is a critical and challenging problem to evaluate the training samples collected from previous predictions and employ sample selection by their quality to train the model. To tackle the above problem, we propose a joint discriminative learning scheme with the progressive multistage optimization policy of sample selection for robust visual tracking. The proposed scheme presents a novel time-weighted and detection-guided self-paced learning strategy for easy-to-hard sample selection, which is capable of tolerating relatively large intraclass variations while maintaining interclass separability. Such a self-paced learning strategy is jointly optimized in conjunction with the discriminative tracking process, resulting in robust tracking results. Experiments on the benchmark datasets demonstrate the effectiveness of the proposed learning framework.

Multifuse multilayer multikernel RVFLN+ of process modes decomposition and approximate entropy data from iEEG/sEEG signals for epileptic seizure recognition

In this paper, the extracted features using variational mode decomposition (VMD) and approximate entropy (ApEn) privileged information of the input EEG signals are combined with multilayer multikernel random vector functional link network plus (MMRVFLN+) classifier to recognize the epileptic seizure epochs efficaciously. In our experiment Bonn University single-channel intracranial electroencephalogram (iEEG) and Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) multichannel scalp EEG (sEEG) recordings are considered to evaluate the efficacy of the proposed method. The VMD is applied on chaotic, non-stationary, nonlinear, and complex EEG signal to decompose it into three band-limited intrinsic mode functions (BLIMFs). The Hilbert transform (HT) is applied on BLIMFs to extract informative spectral and temporal features. The ApEn is computed from the raw EEG signals as the privileged information and given to the multi-hidden layer structure to obtain the most discriminative compressed form. The scatter plots show the distinct nature of compressed privileged ApEn information among the seizure pattern classes. The linear as well as nonlinear mapping, local and global kernel function, high-learning speed, less computationally complex MMRVFLN+ classifier is proposed to recognize the seizure events accurately by importing the efficacious features with ApEn as the input. The advanced signal processing algorithm i.e., Hilbert Huang transform (HHT) with ApEn and MMRVFLN+ are combined to compare the performance with the proposed VMDHTApEn-MMRVFLN+ method. The proposed method has remarkable recognition ability, superior classification accuracy, and excellent overall performance as compared to other methods. The digital architecture of the multifuse MMRVFLN+ is developed and implemented on a high-speed reconfigurable FPGA hardware platform to validate the effectiveness of the proposed method. The superior classification accuracy, the negligible false positive rate per hour (FPR/h), simplicity, feasibility, robustness, and practicability of the proposed method validate its ability to recognize the epileptic seizure epochs automatically.

Robust Online Sequential RVFLNs for Data Modeling of Dynamic Time-Varying Systems With Application of an Ironmaking Blast Furnace

By dealing with robust modeling and online learning together in a unified random vector functional-link networks (RVFLNs) framework, this paper presents a novel robust online sequential RVFLNs for data modeling of dynamic time-varying systems together with its application for a blast furnace (BF) ironmaking process. First, to overcome the difficulties caused by the nonlinear time-varying dynamics of process and to enable the RVFLNs to learn online and to avoid data saturation, an improved online sequential version of RVFLNs (OS-RVFLNs) is presented by sequential learning with forgetting factor. It has been shown that the improved OS-RVFLNs with forgetting factor is not only suitable for the large-scale and real-time data transfer situation but also can adjust the sensitivity of the algorithm to different samples. Second, in order to solve the issue of modeling robustness when the dataset is contaminated with various outliers, a Cauchy distribution function weighted M-estimator is introduced to strengthen the robustness of the improved OS-RVFLNs. The non-Gaussian Cauchy distribution function is used to estimate the weights of different data and thus the corresponding contribution on modeling can be properly distinguished. Experiments using actual industrial data of a large BF ironmaking process have demonstrated that the proposed algorithm produces a much stronger robustness and better estimation accuracy than other algorithms.

Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks

Deeper and wider convolutional neural networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such overparameterized neural network has received increased attention. A typical pruning algorithm is a three-stage pipeline, i.e., training, pruning, and retraining. Prevailing approaches fix the pruned filters to zero during retraining and, thus, significantly reduce the optimization space. Besides, they directly prune a large number of filters at first, which would cause unrecoverable information loss. To solve these problems, we propose an asymptotic soft filter pruning (ASFP) method to accelerate the inference procedure of the deep neural networks. First, we update the pruned filters during the retraining stage. As a result, the optimization space of the pruned model would not be reduced but be the same as that of the original model. In this way, the model has enough capacity to learn from the training data. Second, we prune the network asymptotically. We prune few filters at first and asymptotically prune more filters during the training procedure. With asymptotic pruning, the information of the training set would be gradually concentrated in the remaining filters, so the subsequent training and pruning process would be stable. The experiments show the effectiveness of our ASFP on image classification benchmarks. Notably, on ILSVRC-2012, our ASFP reduces more than 40% FLOPs on ResNet-50 with only 0.14% top-5 accuracy degradation, which is higher than the soft filter pruning by 8%.

Unified Graph-Based Multicue Feature Fusion for Robust Visual Tracking

Visual tracking is a complex problem due to unconstrained appearance variations and a dynamic environment. The extraction of complementary information from the object environment via multiple features and adaption to the target's appearance variations are the key problems of this paper. To this end, we propose a robust object tracking framework based on the unified graph fusion (UGF) of multicue to adapt to the object's appearance. The proposed cross-diffusion of sparse and dense features not only suppresses the individual feature deficiencies but also extracts the complementary information from multicue. This iterative process builds robust unified features which are invariant to object deformations, fast motion, and occlusion. Robustness of the unified feature also enables the random forest classifier to precisely distinguish the foreground from the background, adding resilience to background clutter. In addition, we present a novel kernel-based adaptation strategy using outlier detection and a transductive reliability metric. The adaptation strategy updates the appearance model to accommodate variations in scale, illumination, and rotation. Both qualitative and quantitative analyses on benchmark video sequences from OTB-50, OTB-100, VOT2017/18, and UAV123 show that the proposed UGF tracker performs favorably against 18 other state-of-the-art trackers under various object tracking challenges.

SG-FCN: A Motion and Memory-Based Deep Learning Model for Video Saliency Detection

Data-driven saliency detection has attracted strong interest as a result of applying convolutional neural networks to the detection of eye fixations. Although a number of image-based salient object and fixation detection models have been proposed, video fixation detection still requires more exploration. Different from image analysis, motion and temporal information is a crucial factor affecting human attention when viewing video sequences. Although existing models based on local contrast and low-level features have been extensively researched, they failed to simultaneously consider interframe motion and temporal information across neighboring video frames, leading to unsatisfactory performance when handling complex scenes. To this end, we propose a novel and efficient video eye fixation detection model to improve the saliency detection performance. By simulating the memory mechanism and visual attention mechanism of human beings when watching a video, we propose a step-gained fully convolutional network by combining the memory information on the time axis with the motion information on the space axis while storing the saliency information of the current frame. The model is obtained through hierarchical training, which ensures the accuracy of the detection. Extensive experiments in comparison with 11 state-of-the-art methods are carried out, and the results show that our proposed model outperforms all 11 methods across a number of publicly available datasets.

An unsupervised parameter learning model for RVFL neural network

With the direct input-output connections, a random vector functional link (RVFL) network is a simple and effective learning algorithm for single-hidden layer feedforward neural networks (SLFNs). RVFL is a universal approximator for continuous functions on compact sets with fast learning property. Owing to its simplicity and effectiveness, RVFL has attracted significant interest in numerous real-world applications. In reality, the performance of RVFL is often challenged by randomly assigned network parameters. In this paper, we propose a novel unsupervised network parameter learning method for RVFL, named sparse pre-trained random vector functional link (SP-RVFL for short) network. The proposed SP-RVFL uses a sparse autoencoder with ℓ₁-norm regularization to adaptively learn superior network parameters for specific learning tasks. By doing so, the learned network parameters in SP-RVFL are embedded with the valuable information of input data, which alleviate the randomly generated parameter issue and improve the algorithmic performance. Experiments and comparisons on 16 diverse benchmarks from different domains confirm the effectiveness of the proposed SP-RVFL. The corresponding results also demonstrate that RVFL outperforms extreme learning machine (ELM).

Bayesian Random Vector Functional-Link Networks for Robust Data Modeling

Random vector functional-link (RVFL) networks are randomized multilayer perceptrons with a single hidden layer and a linear output layer, which can be trained by solving a linear modeling problem. In particular, they are generally trained using a closed-form solution of the (regularized) least-squares approach. This paper introduces several alternative strategies for performing full Bayesian inference (BI) of RVFL networks. Distinct from standard or classical approaches, our proposed Bayesian training algorithms allow to derive an entire probability distribution over the optimal output weights of the network, instead of a single pointwise estimate according to some given criterion (e.g., least-squares). This provides several known advantages, including the possibility of introducing additional prior knowledge in the training process, the availability of an uncertainty measure during the test phase, and the capability of automatically inferring hyper-parameters from given data. In this paper, two BI algorithms for regression are first proposed that, under some practical assumptions, can be implemented by a simple iterative process with closed-form computations. Simulation results show that one of the proposed algorithms, Bayesian RVFL, is able to outperform standard training algorithms for RVFL networks with a proper regularization factor selected carefully via a line search procedure. A general strategy based on variational inference is also presented, with an application to data modeling problems with noisy outputs or outliers. As we discuss in this paper, using recent advances in automatic differentiation this strategy can be applied to a wide range of additional situations in an immediate fashion.

Expanding Training Data for Facial Image Super-Resolution

The quality of training data is very important for learning-based facial image super-resolution (SR). The more similarity between training data and testing input is, the better SR results we can have. To generate a better training set of low/high resolution training facial images for a particular testing input, this paper is the first work that proposes expanding the training data for improving facial image SR. To this end, observing that facial images are highly structured, we propose three constraints, i.e., the local structure constraint, the correspondence constraint and the similarity constraint, to generate new training data, where local patches are expanded with different expansion parameters. The expanded training data can be used for both patch-based facial SR methods and global facial SR methods. Extensive testings on benchmark databases and real world images validate the effectiveness of training data expansion on improving the SR quality.

A novel type of activation function in artificial neural networks: Trained activation function

Determining optimal activation function in artificial neural networks is an important issue because it is directly linked with obtained success rates. But, unfortunately, there is not any way to determine them analytically, optimal activation function is generally determined by trials or tuning. This paper addresses, a simpler and a more effective approach to determine optimal activation function. In this approach, which can be called as trained activation function, an activation function was trained for each particular neuron by linear regression. This training process was done based on the training dataset, which consists the sums of inputs of each neuron in the hidden layer and desired outputs. By this way, a different activation function was generated for each neuron in the hidden layer. This approach was employed in random weight artificial neural network (RWN) and validated by 50 benchmark datasets. Achieved success rates by RWN that used trained activation functions were higher than obtained success rates by RWN that used traditional activation functions. Obtained results showed that proposed approach is a successful, simple and an effective way to determine optimal activation function instead of trials or tuning in both randomized single and multilayer ANNs.

Multiview Convolutional Neural Networks for Multidocument Extractive Summarization

Multidocument summarization has gained popularity in many real world applications because vital information can be extracted within a short time. Extractive summarization aims to generate a summary of a document or a set of documents by ranking sentences and the ranking results rely heavily on the quality of sentence features. However, almost all previous algorithms require hand-crafted features for sentence representation. In this paper, we leverage on word embedding to represent sentences so as to avoid the intensive labor in feature engineering. An enhanced convolutional neural networks (CNNs) termed multiview CNNs is successfully developed to obtain the features of sentences and rank sentences jointly. Multiview learning is incorporated into the model to greatly enhance the learning capability of original CNN. We evaluate the generic summarization performance of our proposed method on five Document Understanding Conference datasets. The proposed system outperforms the state-of-the-art approaches and the improvement is statistically significant shown by paired t -test.

Trajectory Predictor by Using Recurrent Neural Networks in Visual Tracking

Motion models have been proved to be a crucial part in the visual tracking process. In recent trackers, particle filter and sliding windows-based motion models have been widely used. Treating motion models as a sequence prediction problem, we can estimate the motion of objects using their trajectories. Moreover, it is possible to transfer the learned knowledge from annotated trajectories to new objects. Inspired by recent advance in deep learning for visual feature extraction and sequence prediction, we propose a trajectory predictor to learn prior knowledge from annotated trajectories and transfer it to predict the motion of target objects. In this predictor, convolutional neural networks extract the visual features of target objects. Long short-term memory model leverages the annotated trajectory priors as well as sequential visual information, which includes the tracked features and center locations of the target object, to predict the motion. Furthermore, to extend this method to videos in which it is difficult to obtain annotated trajectories, a dynamic weighted motion model that combines the proposed trajectory predictor with a random sampler is proposed. To evaluate the transfer performance of the proposed trajectory predictor, we annotated a real-world vehicle dataset. Experiment results on both this real-world vehicle dataset and an online tracker benchmark dataset indicate that the proposed method outperforms several state-of-the-art trackers.