Training Convolutional Neural Networks Based on Ternary Optical Processor

The square rooting is one of the most important basic operations in computers. Researchers have been studying its algorithms and obtained many algorithm implementations. But improving the accuracy and speed of the square rooting has always been a problem of great concern in electronic computers, embedded systems, and other new computing systems. Based on the parallel carry-free modified signed digit (MSD) adder, the bitwise square rooting of MSD numbers and the floating numbers are proposed in this paper. The parallel square rooting for single MSD integers and multiple MSD integers are presented on a ternary optical computer (TOC) processor. The clock cycles required for the square rooting of multiple groups of MSDs of equal length are the same with that of the single MSD data, which is ( 3 + log ( ⌈ n / 2 ⌉ ) ) ⌈ n / 2 ⌉ for n-bit MSD integer requires. It is proved that the square rooting for any MSD form and for the binary form of a decimal number may differ only at the lowest digit in their final binary square rooting representations. As an experiment, the square rooting is designed and implemented on a 192-bit prototype SD16 of TOC. Theoretical proof and optical experiments show that the bitwise MSD square rooting is feasible and can greatly improve the efficiency of square rooting for big data. It makes full use of the advantages of the ternary optical processor with a large number of digits, reconfigurable computing functions, and bitwise allocation.

The application of SJ-MSD adder to mean value filtering processing

In this study, a method of predicting the seismic responses of building structures based on a convolutional neural network (CNN) is proposed. In the method, the time histories of acceleration responses previously measured in a building during earthquakes are used in the CNN input layer, with the corresponding time histories of the displacement responses being used in the CNN output layer. The correlations between the features automatically extracted from the acceleration responses by the convolution and pooling operations in the various CNN layers and the displacement responses in the CNN output layer are established through CNN training. The trained CNN predicts the displacement responses for a future earthquake event using only the measured acceleration responses. To verify the validity of the proposed method, a numerical study on the ASCE benchmark model and an experimental study on a reinforced concrete frame structure are conducted. In the numerical study, the structural responses of the ASCE model subject to artificial earthquakes are utilized for CNN training, and the performance of the trained CNN is verified through seismic response prediction. In the experimental study, shaking table tests are performed for various earthquakes to measure the seismic responses of the reinforced concrete test structure. The seismic response prediction performance of the proposed method is examined using CNN trained with the measured seismic responses. Furthermore, the performances of CNNs trained with different numbers of datasets generated by the proposed data generation method based on data overlapping with the same data pool are discussed with related to the number of CNN training iteration number.

Design and implementation of parallel radix-4 MSD iterative division of ternary optical computer

This study presents a convolutional neural network (CNN)‐based response estimation model for structural health monitoring (SHM) of tall buildings subject to wind loads. In this model, the wind‐induced responses are estimated by CNN trained with previously measured sensor signals; this enables the SHM system to operate stably even when a sensor fault or data loss occurs. In the presented model, top‐level wind‐induced displacement in the time and frequency domains, and wind data in the frequency domain are configured into the input map of the CNN to reflect the resisting capacity of a tall building, the change in the dynamic characteristics of the building due to wind loads, and the relationship between wind load and the building. To evaluate stress, which is used as a safety indicator for structural members in the building, the maximum and minimum strains of columns are set as the output layer of the CNN. The CNN is trained using measured wind and wind response data to predict the column strains during a future wind load. The presented model is validated using data from a wind tunnel test of a building model. The performance of the presented model is verified through strain estimation with data that were not used in the CNN training. To assess the validity of the presented input map configuration, the estimation performance is compared with a CNN that considered only the time domain responses as input. Furthermore, the effects of the variations in the configuration of the CNN on the wind response estimation performance are examined.

Road detection aims at detecting the (drivable) road surface ahead vehicle and plays a crucial role in driver assistance system. To improve the accuracy and robustness of road detection approaches in complex environments, a new road detection method based on CNN (convolutional neural network) and MRF (markov random field) is proposed. The original road image is segmented into super-pixels of uniform size using simple linear iterative clustering (SLIC) algorithm. On this basis, we train the CNN which can automatically learn the features that are most beneficial to classification. Then, the trained CNN is applied to classify road region and non-road region. Finally, based on the relationship between the super-pixels neighborhood, we utilize MRF to optimize the classification results of CNN. Quantitative and qualitative experiments on the publicly datasets demonstrate that the proposed method is robust in complex environments. Furthermore, compared with state-of-the-art algorithms, the approach provides the better performance.

ABSTRACTIn recent years, object-based segmentation methods and shallow-model classification algorithms have been widely integrated for remote sensing image supervised classification. However, as the image resolution increases, remote sensing images contain increasingly complex characteristics, leading to higher intraclass heterogeneity and interclass homogeneity and thus posing substantial challenges for the application of segmentation methods and shallow-model classification algorithms. As important methods of deep learning technology, convolutional neural networks (CNNs) can hierarchically extract higher-level spatial features from images, providing CNNs with a more powerful recognition ability for target detection and scene classification in high-resolution remote sensing images. However, the input of the traditional CNN is an image patch, the shape of which is scarcely consistent with a given segment. This inconsistency may lead to errors when directly using CNNs in object-based remote sensing classification: jagged errors may appear along the land cover boundaries, and some land cover areas may overexpand or shrink, leading to many obvious classification errors in the resulting image. To address the above problem, this paper proposes an object-based and heterogeneous segment filter convolutional neural network (OHSF-CNN) for high-resolution remote sensing image classification. Before the CNN processes an image patch, the OHSF-CNN includes a heterogeneous segment filter (HSF) to process the input image. For the segments in the image patch that are obviously different from the segment to be classified, the HSF can differentiate them and reduce their negative influence on the CNN training and decision-making processes. Experimental results show that the OHSF-CNN not only can take full advantage of the recognition capabilities of deep learning methods but also can effectively avoid the jagged errors along land cover boundaries and the expansion/shrinkage of land cover areas originating from traditional CNN structures. Moreover, compared with the traditional methods, the proposed OHSF-CNN can achieve higher classification accuracy. Furthermore, the OHSF-CNN algorithm can serve as a bridge between deep learning technology and object-based segmentation algorithms thereby enabling the application of object-based segmentation methods to more complex high-resolution remote sensing images.

Convolutional kernel networks based on a convex combination of cosine kernels

This paper investigates two-types of shape representations for individual Maya codical glyphs: traditional bag-of-words built on knowledge-driven local shape descriptors (HOOSC), and Convolutional Neural Networks (CNN) based representations, learned from data. For CNN representations, first, we evaluate the activations of typical CNNs that are pretrained on large-scale image datasets; second, we train a CNN from scratch with all the available individual segments. One of the main challenges while training CNNs is the limited amount of available data (and handling data imbalance issue). Here, we attempt to solve this imbalance issue by introducing class-weights into the loss computation during training. Another possibility is oversampling the minority class samples during batch selection. We show that deep representations outperform the other, but CNN training requires special care for small-scale unbalanced data, that is usually the case in the cultural heritage domain.

Information extraction and coding of free-text pathology reports is an important activity for cancer registries to support national cancer surveillance. Cancer registrars must process high volumes of pathology reports on an annual basis. In this study, we investigated an automated approach using a coarse-to-fine training of convolutional neural networks (CNNs) for extracting the primary site, histological grade and laterality from unstructured cancer pathology text reports. Our proposed training scheme consists of two stages. In the first stage, the multi-task learning (MTL) with hard parameter sharing approach is used to train a multi-task MT-CNN model for all the tasks. Then, the TM-CNN model parameters are used to initialize a CNN model for each task to be fine trained individually using its corresponding dataset. The performance of our proposed approach was compared against a state-of-the-art CNN and the commonly used SVM classifier. We observed that the proposed model consistently outperformed the base line models, especially for the less prevalent classes. Specifically, the proposed training approach achieved a micro-F score of 0.7749 over 12 ICD-O-3 topography codes which is a significant improvement as compared with state-of-the-art CNN (0.7101) and the SVM (0.6019) classifiers. Also, the results demonstrate the potential of the proposed method for handling class imbalance within each task. It significantly improves macro-F score by 24% and 12% of the primary site and histology grade tasks, respectively.

Recently, deep learning (DL) became one of the essential tools in bioinformatics. A modified convolutional neural network (CNN) is employed in this paper for building an integrated model for deoxyribonucleic acid (DNA) classification. In any CNN model, convolutional layers are used to extract features followed by max-pooling layers to reduce the dimensionality of features. A novel method based on downsampling and CNNs is introduced for feature reduction. The downsampling is an improved form of the existing pooling layer to obtain better classification accuracy. The two-dimensional discrete transform (2D DT) and two-dimensional random projection (2D RP) methods are applied for downsampling. They convert the high-dimensional data to low-dimensional data and transform the data to the most significant feature vectors. However, there are parameters which directly affect how a CNN model is trained. In this paper, some issues concerned with the training of CNNs have been handled. The CNNs are examined by changing some hyperparameters such as the learning rate, size of minibatch, and the number of epochs. Training and assessment of the performance of CNNs are carried out on 16S rRNA bacterial sequences. Simulation results indicate that the utilization of a CNN based on wavelet subsampling yields the best trade-off between processing time and accuracy with a learning rate equal to 0.0001, a size of minibatch equal to 64, and a number of epochs equal to 20.

BackgroundArtificial intelligence (AI) is increasingly a part of daily life and offers great possibilities to enrich health care. Imaging applications of AI have been mostly developed by large, well‐funded companies and currently are inaccessible to the comparatively small market of point‐of‐care ultrasound (POCUS) programs. Given this absence of commercial solutions, we sought to create and test a do‐it‐yourself (DIY) deep learning algorithm to classify ultrasound images to enhance the quality assurance work‐flow for POCUS programs.MethodsWe created a convolutional neural network using publicly available software tools and pre‐existing convolutional neural network architecture. The convolutional neural network was subsequently trained using ultrasound images from seven ultrasound exam types: pelvis, heart, lung, abdomen, musculoskeletal, ocular, and central vascular access from 189 publicly available POCUS videos. Approximately 121,000 individual images were extracted from the videos, 80% were used for model training and 10% each for cross validation and testing. We then tested the algorithm for accuracy against a set of 160 randomly extracted ultrasound frames from ultrasound videos not previously used for training and that were performed on different ultrasound equipment. Three POCUS experts blindly categorized the 160 random images, and results were compared to the convolutional neural network algorithm. Descriptive statistics and Krippendorff alpha reliability estimates were calculated.ResultsThe cross validation of the convolutional neural network approached 99% for accuracy. The algorithm accurately classified 98% of the test ultrasound images. In the new POCUS program simulation phase, the algorithm accurately classified 70% of 160 new images for moderate correlation with the ground truth, α = 0.64. The three blinded POCUS experts correctly classified 93%, 94%, and 98% of the images, respectively. There was excellent agreement among the experts with α = 0.87. Agreement between experts and algorithm was good with α = 0.74. The most common error was misclassifying musculoskeletal images for both the algorithm (40%) and POCUS experts (40.6%). The algorithm took 7 minutes 45 seconds to review and classify the new 160 images. The 3 expert reviewers took 27, 32, and 45 minutes to classify the images, respectively.ConclusionsOur algorithm accurately classified 98% of new images, by body scan area, related to its training pool, simulating POCUS program workflow. Performance was diminished with exam images from an unrelated image pool and ultrasound equipment, suggesting additional images and convolutional neural network training are necessary for fine tuning when using across different POCUS programs. The algorithm showed theoretical potential to improve workflow for POCUS program directors, if fully implemented. The implications of our DIY AI for POCUS are scalable and further work to maximize the collaboration between AI and POCUS programs is warranted.

The use of convolutional neural networks (CNNs) has dramatically advanced our ability to recognize images with machine learning methods. We aimed to construct a CNN that could recognize the anatomical location of esophagogastroduodenoscopy (EGD) images in an appropriate manner. A CNN-based diagnostic program was constructed based on GoogLeNet architecture, and was trained with 27,335 EGD images that were categorized into four major anatomical locations (larynx, esophagus, stomach and duodenum) and three subsequent sub-classifications for stomach images (upper, middle, and lower regions). The performance of the CNN was evaluated in an independent validation set of 17,081 EGD images by drawing receiver operating characteristics (ROC) curves and calculating the area under the curves (AUCs). ROC curves showed high performance of the trained CNN to classify the anatomical location of EGD images with AUCs of 1.00 for larynx and esophagus images, and 0.99 for stomach and duodenum images. Furthermore, the trained CNN could recognize specific anatomical locations within the stomach, with AUCs of 0.99 for the upper, middle, and lower stomach. In conclusion, the trained CNN showed robust performance in its ability to recognize the anatomical location of EGD images, highlighting its significant potential for future application as a computer-aided EGD diagnostic system.

Glass forming ability prediction of bulk metallic glasses based on fused strategy

Convolutional Neural Network (CNN) is a powerful and successful deep learning technique for a variety of computer vision and image analysis applications. Interpreting and explaining the decisions of CNNs is one of the most challengeable tasks despite its significant success in various image analysis tasks. Topological Data Analysis (TDA) is an approach that exploits algebraic invariants from topology to analyse high dimensional and noisy datasets as well as growing challenges of big data applications. Persistent homology (PH) is an algebraic topology method for measuring topological features of shapes and/or functions at different distance or similarity resolutions. This work is an attempt to investigate the algebraic properties of pretrained CNN convolutional layer filters based on random Gaussian/Uniform distribution. We shall investigate the stability and sensitivity of the condition number of CNN filters during and post the model training with focus on class discriminability of the PH features of the convolved images. We shall demonstrate a strong link between the condition number of the CNN filters and their discriminating power of the PH representation. In particular, we shall establish that if small perturbation added to the original images then feature maps with well-conditioned filters will produce similar topological features to the original image. Our investigation and findings are based on training CNN's with Digits, MNIST and CIFAR-10 datasets. Our ultimate interest in applying the results of these findings in designing appropriate CNN models for classifications of ultrasound tumor scan images. Preliminary results for these applications are encouraging.