Explore the vast range of titles available.

Software implementations of brain-inspired computing underlie many important computational tasks, from image processing to speech recognition, artificial intelligence and deep learning applications. Yet, unlike real neural tissue, traditional computing architectures physically separate the core computing functions of memory and processing, making fast, efficient and low-energy computing difficult to achieve. To overcome such limitations, an attractive alternative is to design hardware that mimics neurons and synapses. Such hardware, when connected in networks or neuromorphic systems, processes information in a way more analogous to brains. Here we present an all-optical version of such a neurosynaptic system, capable of supervised and unsupervised learning. We exploit wavelength division multiplexing techniques to implement a scalable circuit architecture for photonic neural networks, successfully demonstrating pattern recognition directly in the optical domain. Such photonic neurosynaptic networks promise access to the high speed and high bandwidth inherent to optical systems, thus enabling the direct processing of optical telecommunication and visual data.

Artificial-intelligence researchers are trying to fix the flaws of neural networks.

We present kallisto, an RNA-seq quantification program that is two orders of magnitude faster than previous approaches and achieves similar accuracy. Kallisto pseudoaligns reads to a reference, producing a list of transcripts that are compatible with each read while avoiding alignment of individual bases. We use kallisto to analyze 30 million unaligned paired-end RNA-seq reads in <10 min on a standard laptop computer. This removes a major computational bottleneck in RNA-seq analysis.

Image-based cell profiling is a high-throughput strategy for the quantification of phenotypic differences among a variety of cell populations. It paves the way to studying biological systems on a large scale by using chemical and genetic perturbations. The general workflow for this technology involves image acquisition with high-throughput microscopy systems and subsequent image processing and analysis. Here, we introduce the steps required to create high-quality image-based (i.e., morphological) profiles from a collection of microscopy images. We recommend techniques that have proven useful in each stage of the data analysis process, on the basis of the experience of 20 laboratories worldwide that are refining their image-based cell-profiling methodologies in pursuit of biological discovery. The recommended techniques cover alternatives that may suit various biological goals, experimental designs, and laboratories' preferences.

From bacteria following simple chemical gradients to the brain distinguishing complex odour information , the ability to recognize molecular patterns is essential for biological organisms. This type of information-processing function has been implemented using DNA-based neural networks , but has been limited to the recognition of a set of no more than four patterns, each composed of four distinct DNA molecules. Winner-take-all computation has been suggested as a potential strategy for enhancing the capability of DNA-based neural networks. Compared to the linear-threshold circuits and Hopfield networks used previously , winner-take-all circuits are computationally more powerful , allow simpler molecular implementation and are not constrained by the number of patterns and their complexity, so both a large number of simple patterns and a small number of complex patterns can be recognized. Here we report a systematic implementation of winner-take-all neural networks based on DNA-strand-displacement reactions. We use a previously developed seesaw DNA gate motif , extended to include a simple and robust component that facilitates the cooperative hybridization that is involved in the process of selecting a 'winner'. We show that with this extended seesaw motif DNA-based neural networks can classify patterns into up to nine categories. Each of these patterns consists of 20 distinct DNA molecules chosen from the set of 100 that represents the 100 bits in 10 × 10 patterns, with the 20 DNA molecules selected tracing one of the handwritten digits '1' to '9'. The network successfully classified test patterns with up to 30 of the 100 bits flipped relative to the digit patterns 'remembered' during training, suggesting that molecular circuits can robustly accomplish the sophisticated task of classifying highly complex and noisy information on the basis of similarity to a memory.

This exploration primarily aims to jointly apply the local FCN (fully convolution neural network) and YOLO-v5 (You Only Look Once-v5) to the detection of small targets in remote sensing images. Firstly, the application effects of R-CNN (Region-Convolutional Neural Network), FRCN (Fast Region-Convolutional Neural Network), and R-FCN (Region-Based-Fully Convolutional Network) in image feature extraction are analyzed after introducing the relevant region proposal network. Secondly, YOLO-v5 algorithm is established on the basis of YOLO algorithm. Besides, the multi-scale anchor mechanism of Faster R-CNN is utilized to improve the detection ability of YOLO-v5 algorithm for small targets in the image in the process of image detection, and realize the high adaptability of YOLO-v5 algorithm to different sizes of images. Finally, the proposed detection method YOLO-v5 algorithm + R-FCN is compared with other algorithms in NWPU VHR-10 data set and Vaihingen data set. The experimental results show that the YOLO-v5 + R-FCN detection method has the optimal detection ability among many algorithms, especially for small targets in remote sensing images such as tennis courts, vehicles, and storage tanks. Moreover, the YOLO-v5 + R-FCN detection method can achieve high recall rates for different types of small targets. Furthermore, due to the deeper network architecture, the YOL v5 + R-FCN detection method has a stronger ability to extract the characteristics of image targets in the detection of remote sensing images. Meanwhile, it can achieve more accurate feature recognition and detection performance for the densely arranged target images in remote sensing images. This research can provide reference for the application of remote sensing technology in China, and promote the application of satellites for target detection tasks in related fields.

In today's data-driven world, the ability to process large data volumes is crucial. Key tasks, such as pattern recognition and image classification, are well suited for artificial neural networks (ANNs) inspired by the brain. Neuromorphic computing approaches aimed towards physical realizations of ANNs have been traditionally supported by micro-electronic platforms, but recently, photonic techniques for neuronal emulation have emerged given their unique properties (e.g. ultrafast operation, large bandwidths, low cross-talk). Yet, hardware-friendly systems of photonic spiking neurons able to perform processing tasks at high speeds and with continuous operation remain elusive. This work provides a first experimental report of Vertical-Cavity Surface-Emitting Laser-based spiking neurons demonstrating different functional processing tasks, including coincidence detection and pattern recognition, at ultrafast rates. Furthermore, our approach relies on simple hardware implementations using off-the-shelf components. These results therefore hold exciting prospects for novel, compact and high-speed neuromorphic photonic platforms for future computing and Artificial Intelligence systems.

This paper introduces Quicksilver, a fast deformable image registration method. Quicksilver registration for image-pairs works by patch-wise prediction of a deformation model based directly on image appearance. A deep encoder-decoder network is used as the prediction model. While the prediction strategy is general, we focus on predictions for the Large Deformation Diffeomorphic Metric Mapping (LDDMM) model. Specifically, we predict the momentum-parameterization of LDDMM, which facilitates a patch-wise prediction strategy while maintaining the theoretical properties of LDDMM, such as guaranteed diffeomorphic mappings for sufficiently strong regularization. We also provide a probabilistic version of our prediction network which can be sampled during the testing time to calculate uncertainties in the predicted deformations. Finally, we introduce a new correction network which greatly increases the prediction accuracy of an already existing prediction network. We show experimental results for uni-modal atlas-to-image as well as uni-/multi-modal image-to-image registrations. These experiments demonstrate that our method accurately predicts registrations obtained by numerical optimization, is very fast, achieves state-of-the-art registration results on four standard validation datasets, and can jointly learn an image similarity measure. Quicksilver is freely available as an open-source software. •We propose a deep learning approach to rapidly predict 3D deformable registrations.•We predict the initial momentum of LDDMM patch-wise, assuring diffeomorphisms.•We propose a correction network to further improve prediction accuracy.•We achieve an order of magnitude speed-up compared to a standard optimization method.•We extensively validate our approach on over 2400 image registrations pairs.

Understanding and interpreting classification decisions of automated image classification systems is of high value in many applications, as it allows to verify the reasoning of the system and provides additional information to the human expert. Although machine learning methods are solving very successfully a plethora of tasks, they have in most cases the disadvantage of acting as a black box, not providing any information about what made them arrive at a particular decision. This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of nonlinear classifiers. We introduce a methodology that allows to visualize the contributions of single pixels to predictions for kernel-based classifiers over Bag of Words features and for multilayered neural networks. These pixel contributions can be visualized as heatmaps and are provided to a human expert who can intuitively not only verify the validity of the classification decision, but also focus further analysis on regions of potential interest. We evaluate our method for classifiers trained on PASCAL VOC 2009 images, synthetic image data containing geometric shapes, the MNIST handwritten digits data set and for the pre-trained ImageNet model available as part of the Caffe open source package.

Despite its great potential in studying brain anatomy and structure, diffusion magnetic resonance imaging (dMRI) is marred by artefacts more than any other commonly used MRI technique. In this paper we present a non-parametric framework for detecting and correcting dMRI outliers (signal loss) caused by subject motion. Signal loss (dropout) affecting a whole slice, or a large connected region of a slice, is frequently observed in diffusion weighted images, leading to a set of unusable measurements. This is caused by bulk (subject or physiological) motion during the diffusion encoding part of the imaging sequence. We suggest a method to detect slices affected by signal loss and replace them by a non-parametric prediction, in order to minimise their impact on subsequent analysis. The outlier detection and replacement, as well as correction of other dMRI distortions (susceptibility-induced distortions, eddy currents (EC) and subject motion) are performed within a single framework, allowing the use of an integrated approach for distortion correction. Highly realistic simulations have been used to evaluate the method with respect to its ability to detect outliers (types 1 and 2 errors), the impact of outliers on retrospective correction of movement and distortion and the impact on estimation of commonly used diffusion tensor metrics, such as fractional anisotropy (FA) and mean diffusivity (MD). Data from a large imaging project studying older adults (the Whitehall Imaging sub-study) was used to demonstrate the utility of the method when applied to datasets with severe subject movement. The results indicate high sensitivity and specificity for detecting outliers and that their deleterious effects on FA and MD can be almost completely corrected. •We present a framework for correction of distortions, subject movement and signal dropout in diffusion weighted images.•It has been validated on realistic simulated data.•One can reliably correct for signal dropout as long as the affected slices constitute no more than 10% of the total.