BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Yi Wei

Yi Wei appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Machine LearningSoftware EngineeringComputer Visioneess.SPcond-mat.dis-nnInformation RetrievalInformation Theorymath.ITNeurons and CognitionQuantitative MethodsRoboticsSocial and Information NetworksBiological PhysicsBiomoleculesDistributed, Parallel, and Cluster Computingeess.IVhep-phmath-phmath.MP

Catalog footprint

What is connected

28works
19topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

28 published item(s)

preprint2026arXiv

Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks

Batch normalization (BN) is central to modern deep networks, but its effect on the realized function during training remains less understood than its optimization benefits. We study training-time BN in continuous piecewise-affine (CPA) networks through the geometry of switching hyperplanes and the induced affine-region partition. Conditioned on a mini-batch, we show that BN defines for each neuron a reference hyperplane through the batch centroid, and that breakpoint-switching hyperplanes are parallel translates whose offsets are expressed in batch-standardized coordinates and are independent of the raw bias. This yields an exact criterion for when a switching hyperplane intersects a local $\ell_\infty$ window and motivates a local region-density functional based on exact affine-region counts. Under explicit sufficient conditions, we show that BN increases expected local partition refinement in ReLU and more general piecewise-affine networks, and that this mechanism transfers locally through depth inside parent affine regions where the upstream representation map is an affine embedding. These results provide a function-level geometric account of training-time BN as a batch-conditional recentering mechanism near the data.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo

In this paper, we introduce a deep multi-view stereo (MVS) system that jointly predicts depths, surface normals and per-view confidence maps. The key to our approach is a novel solver that iteratively solves for per-view depth map and normal map by optimizing an energy potential based on the locally planar assumption. Specifically, the algorithm updates depth map by propagating from neighboring pixels with slanted planes, and updates normal map with local probabilistic plane fitting. Both two steps are monitored by a customized confidence map. This solver is not only effective as a post-processing tool for plane-based depth refinement and completion, but also differentiable such that it can be efficiently integrated into deep learning pipelines. Our multi-view stereo system employs multiple optimization steps of the solver over the initial prediction of depths and surface normals. The whole system can be trained end-to-end, decoupling the challenging problem of matching pixels within poorly textured regions from the cost-volume based neural network. Experimental results on ScanNet and RGB-D Scenes V2 demonstrate state-of-the-art performance of the proposed deep MVS system on multi-view depth estimation, with our proposed solver consistently improving the depth quality over both conventional and deep learning based MVS pipelines. Code is available at https://github.com/thuzhaowang/idn-solver.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Channel Tracking and Prediction for IRS-aided Wireless Communications

For intelligent reflecting surface (IRS)-aided wireless communications, channel estimation is essential and usually requires excessive channel training overhead when the number of IRS reflecting elements is large. The acquisition of accurate channel state information (CSI) becomes more challenging when the channel is not quasi-static due to the mobility of the transmitter and/or receiver. In this work, we study an IRS-aided wireless communication system with a time-varying channel model and propose an innovative two-stage transmission protocol. In the first stage, we send pilot symbols and track the direct/reflected channels based on the received signal, and then data signals are transmitted. In the second stage, instead of sending pilot symbols first, we directly predict the direct/reflected channels and all the time slots are used for data transmission. Based on the proposed transmission protocol, we propose a two-stage channel tracking and prediction (2SCTP) scheme to obtain the direct and reflected channels with low channel training overhead, which is achieved by exploiting the temporal correlation of the time-varying channels. Specifically, we first consider a special case where the IRS-access point (AP) channel is assumed to be static, for which a Kalman filter (KF)-based algorithm and a long short-term memory (LSTM)-based neural network are proposed for channel tracking and prediction, respectively. Then, for the more general case where the IRS-AP, user-IRS and user-AP channels are all assumed to be time-varying, we present a generalized KF (GKF)-based channel tracking algorithm, where proper approximations are employed to handle the underlying non-Gaussian random variables. Numerical simulations are provided to verify the effectiveness of our proposed transmission protocol and channel tracking/prediction algorithms as compared to existing ones.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection

In this paper, we propose the LiDAR Distillation to bridge the domain gap induced by different LiDAR beams for 3D object detection. In many real-world applications, the LiDAR points used by mass-produced robots and vehicles usually have fewer beams than that in large-scale public datasets. Moreover, as the LiDARs are upgraded to other product models with different beam amount, it becomes challenging to utilize the labeled data captured by previous versions' high-resolution sensors. Despite the recent progress on domain adaptive 3D detection, most methods struggle to eliminate the beam-induced domain gap. We find that it is essential to align the point cloud density of the source domain with that of the target domain during the training process. Inspired by this discovery, we propose a progressive framework to mitigate the beam-induced domain shift. In each iteration, we first generate low-beam pseudo LiDAR by downsampling the high-beam point clouds. Then the teacher-student framework is employed to distill rich information from the data with more beams. Extensive experiments on Waymo, nuScenes and KITTI datasets with three different LiDAR-based detectors demonstrate the effectiveness of our LiDAR Distillation. Notably, our approach does not increase any additional computation cost for inference.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Smart Explorer: Recognizing Objects in Dense Clutter via Interactive Exploration

Recognizing objects in dense clutter accurately plays an important role to a wide variety of robotic manipulation tasks including grasping, packing, rearranging and many others. However, conventional visual recognition models usually miss objects because of the significant occlusion among instances and causes incorrect prediction due to the visual ambiguity with the high object crowdedness. In this paper, we propose an interactive exploration framework called Smart Explorer for recognizing all objects in dense clutters. Our Smart Explorer physically interacts with the clutter to maximize the recognition performance while minimize the number of motions, where the false positives and negatives can be alleviated effectively with the optimal accuracy-efficiency trade-offs. Specifically, we first collect the multi-view RGB-D images of the clutter and reconstruct the corresponding point cloud. By aggregating the instance segmentation of RGB images across views, we acquire the instance-wise point cloud partition of the clutter through which the existed classes and the number of objects for each class are predicted. The pushing actions for effective physical interaction are generated to sizably reduce the recognition uncertainty that consists of the instance segmentation entropy and multi-view object disagreement. Therefore, the optimal accuracy-efficiency trade-off of object recognition in dense clutter is achieved via iterative instance prediction and physical interaction. Extensive experiments demonstrate that our Smart Explorer acquires promising recognition accuracy with only a few actions, which also outperforms the random pushing by a large margin.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Channel Estimation for IRS-aided Multiuser Communications with Reduced Error Propagation

Intelligent reflecting surface (IRS) has emerged as a promising paradigm to improve the capacity and reliability of a wireless communication system by smartly reconfiguring the wireless propagation environment. To achieve the promising gains of IRS, the acquisition of the channel state information (CSI) is essential, which however is practically difficult since the IRS does not employ any transmit/receive radio frequency (RF) chains in general and it has limited signal processing capability. In this paper, we study the uplink channel estimation problem for an IRS-aided multiuser single-input multi-output (SIMO) system, and propose a novel two-phase channel estimation (2PCE) strategy which can alleviate the negative effects caused by error propagation in the existing three-phase channel estimation approach, i.e., the channel estimation errors in previous phases will deteriorate the estimation performance in later phases, and enhance the channel estimation performance with the same amount of channel training overhead as in the existing approach. Moreover, the asymptotic mean squared error (MSE) of the 2PCE strategy is analyzed when the least-square (LS) channel estimation method is employed, and we show that the 2PCE strategy can outperform the existing approach. Finally, extensive simulation results are presented to validate the effectiveness of the 2PCE strategy.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

DST: Data Selection and joint Training for Learning with Noisy Labels

Training a deep neural network heavily relies on a large amount of training data with accurate annotations. To alleviate this problem, various methods have been proposed to annotate the data automatically. However, automatically generating annotations will inevitably yields noisy labels. In this paper, we propose a Data Selection and joint Training (DST) method to automatically select training samples with accurate annotations. Specifically, DST fits a mixture model according to the original annotation as well as the predicted label for each training sample, and the mixture model is utilized to dynamically divide the training dataset into a correctly labeled dataset, a correctly predicted set and a wrong dataset. Then, DST is trained with these datasets in a supervised manner. Due to confirmation bias problem, we train the two networks alternately, and each network is tasked to establish the data division to teach another network. For each iteration, the correctly labeled and predicted labels are reweighted respectively by the probabilities from the mixture model, and a uniform distribution is used to generate the probabilities of the wrong samples. Experiments on CIFAR-10, CIFAR-100 and Clothing1M demonstrate that DST is the comparable or superior to the state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks

A bipartite network is a graph structure where nodes are from two distinct domains and only inter-domain interactions exist as edges. A large number of network embedding methods exist to learn vectorial node representations from general graphs with both homogeneous and heterogeneous node and edge types, including some that can specifically model the distinct properties of bipartite networks. However, these methods are inadequate to model multiplex bipartite networks (e.g., in e-commerce), that have multiple types of interactions (e.g., click, inquiry, and buy) and node attributes. Most real-world multiplex bipartite networks are also sparse and have imbalanced node distributions that are challenging to model. In this paper, we develop an unsupervised Dual HyperGraph Convolutional Network (DualHGCN) model that scalably transforms the multiplex bipartite network into two sets of homogeneous hypergraphs and uses spectral hypergraph convolutional operators, along with intra- and inter-message passing strategies to promote information exchange within and across domains, to learn effective node embedding. We benchmark DualHGCN using four real-world datasets on link prediction and node classification tasks. Our extensive experiments demonstrate that DualHGCN significantly outperforms state-of-the-art methods, and is robust to varying sparsity levels and imbalanced node distributions.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Network Clustering for Multi-task Learning

The Multi-Task Learning (MTL) technique has been widely studied by word-wide researchers. The majority of current MTL studies adopt the hard parameter sharing structure, where hard layers tend to learn general representations over all tasks and specific layers are prone to learn specific representations for each task. Since the specific layers directly follow the hard layers, the MTL model needs to estimate this direct change (from general to specific) as well. To alleviate this problem, we introduce the novel cluster layer, which groups tasks into clusters during training procedures. In a cluster layer, the tasks in the same cluster are further required to share the same network. By this way, the cluster layer produces the general presentation for the same cluster, while produces relatively specific presentations for different clusters. As transitions the cluster layers are used between the hard layers and the specific layers. The MTL model thus learns general representations to specific representations gradually. We evaluate our model with MTL document classification and the results demonstrate the cluster layer is quite efficient in MTL.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A PDD Decoder for Binary Linear Codes With Neural Check Polytope Projection

Linear Programming (LP) is an important decoding technique for binary linear codes. However, the advantages of LP decoding, such as low error floor and strong theoretical guarantee, etc., come at the cost of high computational complexity and poor performance at the low signal-to-noise ratio (SNR) region. In this letter, we adopt the penalty dual decomposition (PDD) framework and propose a PDD algorithm to address the fundamental polytope based maximum likelihood (ML) decoding problem. Furthermore, we propose to integrate machine learning techniques into the most time-consuming part of the PDD decoding algorithm, i.e., check polytope projection (CPP). Inspired by the fact that a multi-layer perception (MLP) can theoretically approximate any nonlinear mapping function, we present a specially designed neural CPP (NCPP) algorithm to decrease the decoding latency. Simulation results demonstrate the effectiveness of the proposed algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

ADMM-based Decoder for Binary Linear Codes Aided by Deep Learning

Inspired by the recent advances in deep learning (DL), this work presents a deep neural network aided decoding algorithm for binary linear codes. Based on the concept of deep unfolding, we design a decoding network by unfolding the alternating direction method of multipliers (ADMM)-penalized decoder. In addition, we propose two improved versions of the proposed network. The first one transforms the penalty parameter into a set of iteration-dependent ones, and the second one adopts a specially designed penalty function, which is based on a piecewise linear function with adjustable slopes. Numerical results show that the resulting DL-aided decoders outperform the original ADMM-penalized decoder for various low density parity check (LDPC) codes with similar computational complexity.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Deep Hierarchical Classification for Category Prediction in E-commerce System

In e-commerce system, category prediction is to automatically predict categories of given texts. Different from traditional classification where there are no relations between classes, category prediction is reckoned as a standard hierarchical classification problem since categories are usually organized as a hierarchical tree. In this paper, we address hierarchical category prediction. We propose a Deep Hierarchical Classification framework, which incorporates the multi-scale hierarchical information in neural networks and introduces a representation sharing strategy according to the category tree. We also define a novel combined loss function to punish hierarchical prediction losses. The evaluation shows that the proposed approach outperforms existing approaches in accuracy.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval

In this paper, we address the text and image matching in cross-modal retrieval of the fashion industry. Different from the matching in the general domain, the fashion matching is required to pay much more attention to the fine-grained information in the fashion images and texts. Pioneer approaches detect the region of interests (i.e., RoIs) from images and use the RoI embeddings as image representations. In general, RoIs tend to represent the "object-level" information in the fashion images, while fashion texts are prone to describe more detailed information, e.g. styles, attributes. RoIs are thus not fine-grained enough for fashion text and image matching. To this end, we propose FashionBERT, which leverages patches as image features. With the pre-trained BERT model as the backbone network, FashionBERT learns high level representations of texts and images. Meanwhile, we propose an adaptive loss to trade off multitask learning in the FashionBERT modeling. Two tasks (i.e., text and image matching and cross-modal retrieval) are incorporated to evaluate FashionBERT. On the public dataset, experiments demonstrate FashionBERT achieves significant improvements in performances than the baseline and state-of-the-art approaches. In practice, FashionBERT is applied in a concrete cross-modal retrieval application. We provide the detailed matching performance and inference efficiency analysis.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN

Network embedding aims to learn low-dimensional representations of nodes while capturing structure information of networks. It has achieved great success on many tasks of network analysis such as link prediction and node classification. Most of existing network embedding algorithms focus on how to learn static homogeneous networks effectively. However, networks in the real world are more complex, e.g., networks may consist of several types of nodes and edges (called heterogeneous information) and may vary over time in terms of dynamic nodes and edges (called evolutionary patterns). Limited work has been done for network embedding of dynamic heterogeneous networks as it is challenging to learn both evolutionary and heterogeneous information simultaneously. In this paper, we propose a novel dynamic heterogeneous network embedding method, termed as DyHATR, which uses hierarchical attention to learn heterogeneous information and incorporates recurrent neural networks with temporal attention to capture evolutionary patterns. We benchmark our method on four real-world datasets for the task of link prediction. Experimental results show that DyHATR significantly outperforms several state-of-the-art baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

SWIM: Synthesizing What I Mean

Modern programming frameworks come with large libraries, with diverse applications such as for matching regular expressions, parsing XML files and sending email. Programmers often use search engines such as Google and Bing to learn about existing APIs. In this paper, we describe SWIM, a tool which suggests code snippets given API-related natural language queries such as "generate md5 hash code". We translate user queries into the APIs of interest using clickthrough data from the Bing search engine. Then, based on patterns learned from open-source code repositories, we synthesize idiomatic code describing the use of these APIs. We introduce \emph{structured call sequences} to capture API-usage patterns. Structured call sequences are a generalized form of method call sequences, with if-branches and while-loops to represent conditional and repeated API usage patterns, and are simple to extract and amenable to synthesis. We evaluated SWIM with 30 common C# API-related queries received by Bing. For 70% of the queries, the first suggested snippet was a relevant solution, and a relevant solution was present in the top 10 results for all benchmarked queries. The online portion of the workflow is also very responsive, at an average of 1.5 seconds per snippet.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

The influence of initial solutions to exact solutions of the (2+1)-dimensional generalized Nizhnik-Novikov-Veselov equations

The (2+1)-dimensional generalized Nizhnik-Novikov-Veselov equations (GNNVEs) are investigated in order to search the influence of initial solution to exact solutions. The GNNVEs are converted into the combined equations of differently two bilinear forms by means of the homogeneous balance of undetermined coefficients method. Accordingly, the two class of exact N-soliton solutions and three wave solutions are obtained respectively by using the Hirota direct method combined with the simplified version of Hereman and the three wave method. The proposed method is also a standard and computable method, which can be generalized to deal with some nonlinear partial differential equations (NLPDEs).

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

An Exactly Solvable Model of Random Site-Specific Recombinations

Cre-lox and other systems are used as genetic tools to control site-specific recombination (SSR) events in genomic DNA. If multiple recombination sites are organized in a compact cluster within the same genome, a series of random recombination events may generate substantial cell specific genomic diversity. This diversity is used, for example, to distinguish neurons in the brain of the same multicellular mosaic organism, within the brainbow approach to neuronal connectome. In this paper we study an exactly solvable statistical model for SSR operating on a cluster of recombination sites. We consider two types of recombination events: inversions and excisions. Both of these events are available in the Cre-lox system. We derive three properties of the sequences generated by multiple recombination events. First, we describe the set of sequences that can in principle be generated by multiple inversions operating on the given initial sequence. We call this description the ergodicity theorem. On the basis of this description we calculate the number of sequences that can be generated from an initial sequence. This number of sequences is experimentally testable. Second, we demonstrate that after a large number of random inversions every sequence that can be generated is generated with equal probability. Lastly, we derive the equations for the probability to find a sequence as a function of time in the limit when excisions are much less frequent than inversions, such as in shufflon sequences.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Automated Fixing of Programs with Contracts

This paper describes AutoFix, an automatic debugging technique that can fix faults in general-purpose software. To provide high-quality fix suggestions and to enable automation of the whole debugging process, AutoFix relies on the presence of simple specification elements in the form of contracts (such as pre- and postconditions). Using contracts enhances the precision of dynamic analysis techniques for fault detection and localization, and for validating fixes. The only required user input to the AutoFix supporting tool is then a faulty program annotated with contracts; the tool produces a collection of validated fixes for the fault ranked according to an estimate of their suitability. In an extensive experimental evaluation, we applied AutoFix to over 200 faults in four code bases of different maturity and quality (of implementation and of contracts). AutoFix successfully fixed 42% of the faults, producing, in the majority of cases, corrections of quality comparable to those competent programmers would write; the used computational resources were modest, with an average time per fix below 20 minutes on commodity hardware. These figures compare favorably to the state of the art in automated program fixing, and demonstrate that the AutoFix approach is successfully applicable to reduce the debugging burden in real-world scenarios.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Optimizing weights of protein energy function to improve ab initio protein structure prediction

Predicting protein 3D structure from amino acid sequence remains as a challenge in the field of computational biology. If protein structure homologues are not found, one has to construct 3D structural conformations from the very beginning by the so-called ab initio approach, using some empirical energy functions. A successful algorithm in this category, Rosetta, creates an ensemble of decoy conformations by assembling selected best short fragments of known protein structures and then recognizes the native state as the highly populated one with a very low energy. Typically, an energy function is a combination of a variety of terms characterizing different structural features, say hydrophobic interactions, van der Waals force, hydrogen bonding, etc. It is critical for an energy function to be capable to distinguish native-like conformations from non-native ones and to drive most initial conformations assembled from fragments to a native-like one in a conformation search process. In this paper we propose a linear programming algorithm to optimize weighting of a total of 14 energy terms used in Rosetta. We reverse the Monte Carlo process of Rosetta to approach native-like conformations to a process generating from the native state an ensemble of initial conformations most relevant to the native state. Intuitively, an ideal weighting scheme would result in a large "basin of attraction" of the native structure, which leads to an objective function for the linear programming. We have examined the proposal on several benchmark proteins, and the experimental results suggest that the optimized weights enlarge the attraction basin of the native state and improve the quality of the predicted native states as well. In addition, a comparison of optimal weighting schema for proteins of different classes indicates that in different protein classes energy terms may have different effects.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Statistical model of evolution of brain parcellation

We study the distribution of brain and cortical area sizes [parcellation units (PUs)] obtained for three species: mouse, macaque, and human. We find that the distribution of PU sizes is close to lognormal. We analyze the mathematical model of evolution of brain parcellation based on iterative fragmentation and specialization. In this model, each existing PU has a probability to be split that depends on PU size only. This model shows that the same evolutionary process may have led to brain parcellation in these three species. Our model suggests that region-to-region (macro) connectivity is given by the outer product form. We show that most experimental data on non-vanishing macaque cortex macroconnectivity (62% for area V1) can be explained by the outer product power-law form suggested by our model. We propose a multiplicative Hebbian learning rule for the macroconnectome that could yield the correct scaling of connection strengths between areas. We thus propose a universal evolutionary model that may have contributed to both brain parcellation and mesoscopic level connectivity in mammals.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

What Good Are Strong Specifications?

Experience with lightweight formal methods suggests that programmers are willing to write specification if it brings tangible benefits to their usual development activities. This paper considers stronger specifications and studies whether they can be deployed as an incremental practice that brings additional benefits without being unacceptably expensive. We introduce a methodology that extends Design by Contract to write strong specifications of functional properties in the form of preconditions, postconditions, and invariants. The methodology aims at being palatable to developers who are not fluent in formal techniques but are comfortable with writing simple specifications. We evaluate the cost and the benefits of using strong specifications by applying the methodology to testing data structure implementations written in Eiffel and C#. In our extensive experiments, testing against strong specifications detects twice as many bugs as standard contracts, with a reasonable overhead in terms of annotation burden and run-time performance while testing. In the wide spectrum of formal techniques for software quality, testing against strong specifications lies in a "sweet spot" with a favorable benefit to effort ratio.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Eigenvalue spectra of asymmetric random matrices for multi-component neural networks

This paper focuses on large neural networks whose synaptic connectivity matrices are randomly chosen from certain random matrix ensembles. The dynamics of these networks can be characterized by the eigenvalue spectra of their connectivity matrices. In reality, neurons in a network do not necessarily behave in a similar way, but may belong to several different categories. The first study of the spectra of two-component neural networks was carried out by Rajan and Abbott. In their model, neurons are either 'excitatory' or 'inhibitory', and strengths of synapses from different types of neurons have Gaussian distributions with different means and variances. A surprising finding by Rajan and Abbott is that the eigenvalue spectra of these types of random synaptic matrices do not depend on the mean values of their elements. In this paper we prove that this is true even for a much more general type of random neural network, where there is a finite number of types of neurons, and their synaptic strengths have correlated distributions. Furthermore, using the diagrammatic techniques, we calculate the explicit formula for the spectra of synaptic matrices of multi-component neural networks.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Long-term memory stabilized by noise-induced rehearsal

Cortical networks can maintain memories for decades despite the short lifetime of synaptic strength. Can a neural network store long-lasting memories in unstable synapses? Here, we study the effects of random noise on the stability of memory stored in synapses of an attractor neural network. The model includes ongoing spike timing dependent plasticity (STDP). We show that certain classes of STDP rules can lead to the stabilization of memory patterns stored in the network. The stabilization results from rehearsals induced by noise. We show that unstructured neural noise, after passing through the recurrent network weights, carries the imprint of all memory patterns in temporal correlations. Under certain conditions, STDP combined with these correlations, can lead to reinforcement of all existing patterns, even those that are never explicitly visited. Thus, unstructured neural noise can stabilize the existing structure of synaptic connectivity. Our findings may provide the functional reason for highly irregular spiking displayed by cortical neurons and provide justification for models of system memory consolidation. Therefore, we propose that irregular neural activity is the feature that helps cortical networks maintain stable connections.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

The Search for the Laws of Automatic Random Testing

Can one estimate the number of remaining faults in a software system? A credible estimation technique would be immensely useful to project managers as well as customers. It would also be of theoretical interest, as a general law of software engineering. We investigate possible answers in the context of automated random testing, a method that is increasingly accepted as an effective way to discover faults. Our experimental results, derived from best-fit analysis of a variety of mathematical functions, based on a large number of automated tests of library code equipped with automated oracles in the form of contracts, suggest a poly-logarithmic law. Although further confirmation remains necessary on different code bases and testing techniques, we argue that understanding the laws of testing may bring significant benefits for estimating the number of detectable faults and comparing different projects and practices.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

Aneka Cloud Application Platform and Its Integration with Windows Azure

Aneka is an Application Platform-as-a-Service (Aneka PaaS) for Cloud Computing. It acts as a framework for building customized applications and deploying them on either public or private Clouds. One of the key features of Aneka is its support for provisioning resources on different public Cloud providers such as Amazon EC2, Windows Azure and GoGrid. In this chapter, we will present Aneka platform and its integration with one of the public Cloud infrastructures, Windows Azure, which enables the usage of Windows Azure Compute Service as a resource provider of Aneka PaaS. The integration of the two platforms will allow users to leverage the power of Windows Azure Platform for Aneka Cloud Computing, employing a large number of compute instances to run their applications in parallel. Furthermore, customers of the Windows Azure platform can benefit from the integration with Aneka PaaS by embracing the advanced features of Aneka in terms of multiple programming models, scheduling and management services, application execution services, accounting and pricing services and dynamic provisioning services. Finally, in addition to the Windows Azure Platform we will illustrate in this chapter the integration of Aneka PaaS with other public Cloud platforms such as Amazon EC2 and GoGrid, and virtual machine management platforms such as Xen Server. The new support of provisioning resources on Windows Azure once again proves the adaptability, extensibility and flexibility of Aneka.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

Code-based Automated Program Fixing

Many programmers, when they encounter an error, would like to have the benefit of automatic fix suggestions---as long as they are, most of the time, adequate. Initial research in this direction has generally limited itself to specific areas, such as data structure classes with carefully designed interfaces, and relied on simple approaches. To provide high-quality fix suggestions in a broad area of applicability, the present work relies on the presence of contracts in the code, and on the availability of dynamic analysis to gather evidence on the values taken by expressions derived from the program text. The ideas have been built into the AutoFix-E2 automatic fix generator. Applications of AutoFix-E2 to general-purpose software, such as a library to manipulate documents, show that the approach provides an improvement over previous techniques, in particular purely model-based approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

Stateful Testing: Finding More Errors in Code and Contracts

Automated random testing has shown to be an effective approach to finding faults but still faces a major unsolved issue: how to generate test inputs diverse enough to find many faults and find them quickly. Stateful testing, the automated testing technique introduced in this article, generates new test cases that improve an existing test suite. The generated test cases are designed to violate the dynamically inferred contracts (invariants) characterizing the existing test suite. As a consequence, they are in a good position to detect new errors, and also to improve the accuracy of the inferred contracts by discovering those that are unsound. Experiments on 13 data structure classes totalling over 28,000 lines of code demonstrate the effectiveness of stateful testing in improving over the results of long sessions of random testing: stateful testing found 68.4% new errors and improved the accuracy of automatically inferred contracts to over 99%, with just a 7% time overhead.

0 citations0 reviewsNo code linkedOpen access
preprint1998arXiv

Comment on the hadronic decay of excited heavy quarkonia

We make comments on ref.[Z.Phys. C73, 541 (1997)], and provide partial wave analysis to the decays of excited heavy S-wave $1^-$ quarkonia into the basic $1^-$ quarkonia state plus $ππ$. It is revealed that there exist contributions of D-wave transition in $ψ'\longrightarrow J/ψππ$, $Υ(2S)\longrightarrow Υ(1S) ππ$ and $Υ(3S)\longrightarrow Υ(1S) ππ$ by using the data-fitting results in ref.[Z.Phys C73, 541 (1997)]. A possible experimental method to measure the D-wave directly is discussed.

0 citations0 reviewsNo code linkedOpen access