Zhubaker1314

g., less than 10% overheads, but effectively boosts the modeling capability of binary convolution blocks in BCNN. Extensive experiments on ImageNet demonstrate the superior performance of our method in both classification efficiency and accuracy, e.g., BCNN trained with our methods achieves the accuracy of 60.45% on ImageNet, better than many state-of-the-art ones.In online learning, the dynamic regret metric chooses the reference oracle that may change over time, while the typical (static) regret metric assumes the reference solution to be constant over the whole time horizon. The dynamic regret metric is particularly interesting for applications, such as online recommendation (since the customers' preference always evolves over time). While the online gradient (OG) method has been shown to be optimal for the static regret metric, the optimal algorithm for the dynamic regret remains unknown. In this article, we show that proximal OG (a general version of OG) is optimum to the dynamic regret by showing that the proved lower bound matches the upper bound. It is highlighted that we provide a new and general lower bound of dynamic regret. It provides new understanding about the difficulty to follow the dynamics in the online setting.Clustering algorithms based on deep neural networks have been widely studied for image analysis. Most existing methods require partial knowledge of the true labels, namely, the number of clusters, which is usually not available in practice. In this article, we propose a Bayesian nonparametric framework, deep nonparametric Bayes (DNB), for jointly learning image clusters and deep representations in a doubly unsupervised manner. In doubly unsupervised learning, we are dealing with the problem of ``unknown unknowns, where we estimate not only the unknown image labels but also the unknown number of labels as well. The proposed algorithm alternates between generating a potentially unbounded number of clusters in the forward pass and learning the deep networks in the backward pass. With the help of the Dirichlet process mixtures, the proposed method is able to partition the latent representations space without specifying the number of clusters a priori. An important feature of this work is that all the estimation is realized with an end-to-end solution, which is very different from the methods that rely on post hoc analysis to select the number of clusters. Another key idea in this article is to provide a principled solution to the problem of ``trivial solution for deep clustering, which has not been much studied in the current literature. With extensive experiments on benchmark datasets, we show that our doubly unsupervised method achieves good clustering performance and outperforms many other unsupervised image clustering methods.This article develops several centralized and collective neurodynamic approaches for sparse signal reconstruction by solving the L₁-minimization problem. First, two centralized neurodynamic approaches are designed based on the augmented Lagrange method and the Lagrange method with derivative feedback and projection operator. Then, the optimality and global convergence of them are derived. In addition, considering that the collective neurodynamic approaches have the function of information protection and distributed information processing, first, under mild conditions, we transform the L₁-minimization problem into two network optimization problems. Later, two collective neurodynamic approaches based on the above centralized neurodynamic approaches and multiagent consensus theory are proposed to address the obtained network optimization problems. As far as we know, this is the first attempt to use the collective neurodynamic approaches to deal with the L₁-minimization problem in a distributed manner. Finally, several comparative experiments on sparse signal and image reconstruction demonstrate that our proposed centralized and collective neurodynamic approaches are efficient and effective.Photoacoustic (PA) imaging is becoming more attractive because it can obtain high-resolution and high-contrast images through merging the merits of optical and acoustic imaging. High sensitivity receiver is required in deep in-vivo PA imaging due to detecting weak and noisy ultrasound signal. A novel photoacoustic receiver system-on-chip (SoC) with coherent detection (CD) based on the early-and-late acquisition and tracking is developed and first fabricated. In this system, a weak PA signal with negative signal-to-noise-ratio (SNR) can be clearly extracted when the tracking loop is locked to the input. Consequently, the output SNR of the receiver is significantly improved by about 29.9 dB than input one. For the system, a high dynamic range (DR) and high sensitivity analog front-end (AFE), a multiplier, a noise shaping (NS) successive-approximation (SAR) analog-to-digital convertor (ADC), a digital-to-analog convertor (DAC) and integrated digital circuits for the proposed system are implemented on-chip. Measurement results show that the receiver achieves 0.18 µVrms sensitivity at the depth of 1 cm with 1 mJ/cm2 laser output fluence. The contrast-to-noise (CNR) of the imaging is improved by about 22.2 dB. The area of the receiver is 5.71 mm2, and the power consumption of each channel is about 28.8 mW with 1.8 V and 1 V power supply on the TSMC 65 nm CMOS process.In this paper, reduced deep convolutional stack autoencoder (RDCSAE) and improved kernel random vector functional link network (IKRVFLN) are combined to recognize the epileptic seizure using both the multichannel scalp and single-channel electroencephalogram (EEG) signals. The novel RDCSAE structure is designed to extract the most discriminative unsupervised features from EEG signals and fed into the proposed supervised IKRVFLN classifier to train efficiently by reducing the mean-square error cost function for recognizing the epileptic seizure activity with promising accuracy. The proposed RDCSAE-IKRVFLN algorithm is tested over the benchmark Boston Children's Hospital multichannel scalp EEG (sEEG) and Boon University, Germany single-channel EEG databases. The less computational complexity, higher learning speed, better model generalization, accurate epileptic seizure recognition, remarkable classification accuracy, negligible false positive rate per hour (FPR/h) and short event recognition time are the main advantages of the proposed RDCSAE-IKRVFLN method over reduced deep convolutional neural network (RDCNN), RDCSAE and RDCSAE-KRVFLN methods. The proposed RDCSAE-IKRVFLN method is implemented in a high-speed reconfigurable field-programmable gate array (FPGA) hardware environment to design a computer-aided-diagnosis (CAD) system for automatic epileptic seizure diagnosis. The simplicity, feasibility, and practicability of the proposed method validate the stable and reliable performances of epilepsy detection and recognition.Most memristor-based neural networks only consider a single mode of memory or emotion, but ignore the relationship between emotion and memory. In this paper, a memristor-based neural network circuit of emotion congruent memory is proposed and verified by the simulation results. The designed circuit consists of a memory module, an emotion module and an association neuron module. Varieties of memory and emotion functions are considered. The functions such as learning, forgetting, variable rate and emotion generation are implemented by the circuit. Furthermore, mental fatigue and emotion inhibition which are two important self-protective measures of the brain are realized in this paper on the basis of emotion congruent memory. Finally, the paper also considers the congruence between emotion and memory materials and the regulation of emotion on memory. The neural network circuit of emotion congruent memory can provide more references for the application of memristor.The depth of anesthesia monitoring is helpful to guide administrations of general anesthetics during surgical procedures,however, the conventional 2-4 channels electroencephalogram (EEG) derived monitors have their limitations in monitoring conscious states due to low spatial resolution and suboptimal algorithm. In this study, 256-channel high-density EEG signals in 24 subjects receiving three types of general anesthetics (propofol, sevoflurane and ketamine) respectively were recorded both before and after anesthesia.The raw EEG signals were preprocessed by EEGLAB 14.0. Functional connectivity (FC) analysis by traditional coherence analysis (CA) method and a novel sparse representation (SR) method. And the network parameters, average clustering coefficient (ACC) and average shortest path length (ASPL) before and after anesthesia were calculated. The results show SR method find more significant FC differences in frontal and occipital cortices, and whole brain network (p0.05). Further, ASPL calculated by SR for whole brain connections in all of three anesthesia groups increased, which can be a unified EEG biomarker of general anesthetics-induced loss of consciousness (LOC). Therefore FC analysis based on SR analysis has better performance in distinguishing anesthetic-induced LOC from awake state.The design of the light-weight infill structure is a hot research topic in additive manufacturing. In recent years, various infill structures have been proposed to reduce the amount of printing material. However, 3D models filled with them may have very different structural performances under different loading conditions. In addition, most of them are not self-supporting. To mitigate these issues, a novel light-weight infill structure based on the layer construction is proposed in this paper. The layers of the proposed infill structure continuously and periodically transform between triangles and hexagons. The geometries of two adjacent layers are controlled to be self-supporting for different 3D printing technologies. The machine code (Gcode) of the filled 3D model is generated in the construction of the infill structure for 3D printers. this website That means 3D models filled with the proposed infill structure do not need an extra slicing process before printing, which is time consuming in some cases. Structural simulations and physical experiments demonstrate that our infill structure has comparable structural performance under different loading conditions. Furthermore, the relationship between the structural stiffness and the parameters of the infill structure is investigated, which will be helpful for non-professional users.Two of the most popular mediums for virtual reality are head-mounted displays and surround-screen projection systems, such as CAVE Automatic Virtual Environments. In recent years, HMDs suffered a significant reduction in cost and have become widespread consumer products. In contrast, CAVEs are still expensive and remain accessible to a limited number of researchers. This study aims to evaluate both objective and subjective characteristics of a CAVE-like monoscopic low-cost virtual reality surround-screen projection system compared to advanced setups and HMDs. For objective results, we measured the head position estimation accuracy and precision of a low-cost active infrared (IR) based tracking system, used in the proposed low-cost CAVE, relatively to an infrared marker-based tracking system, used in a laboratory-grade CAVE system. For subjective characteristics, we investigated the sense of presence and cybersickness elicited in users during a visual search task outside personal space, beyond arms reach, where the importance of stereo vision is diminished.