Learning of Spatio–Temporal Codes in a Coupled Oscillator System

In this paper, we consider a learning strategy that allows one to transmit information between two coupled phase oscillator systems (called teaching and learning systems) via frequency adaptation. The dynamics of these systems can be modeled with reference to a number of partially synchronized cluster states and transitions between them. Forcing the teaching system by steady but spatially nonhomogeneous inputs produces cyclic sequences of transitions between the cluster states, that is, information about inputs is encoded via a “winnerless competition” process into spatio–temporal codes. The large variety of codes can be learned by the learning system that adapts its frequencies to those of the teaching system. We visualize the dynamics using “weighted order parameters (WOPs)” that are analogous to “local field potentials” in neural systems. Since spatio–temporal coding is a mechanism that appears in olfactory systems, the developed learning rules may help to extract information from these neural ensembles.      

An Expectation–Maximization Method for Spatio–Temporal Blind Source Separation Using an AR-MOG Source Model

In this paper, we develop a maximum-likelihood (ML) spatio-temporal blind source separation (BSS) algorithm, where the temporal dependencies are explained by assuming that each source is an autoregressive (AR) process and the distribution of the associated independent identically distributed (i.i.d.) innovations process is described using a mixture of Gaussians. Unlike most ML methods, the proposed algorithm takes into account both spatial and temporal information, optimization is performed using the expectation-maximization (EM) method, the source model is adapted to maximize the likelihood, and the update equations have a simple, analytical form. The proposed method, which we refer to as autoregressive mixture of Gaussians (AR-MOG), outperforms nine other methods for artificial mixtures of real audio. We also show results for using AR-MOG to extract the fetal cardiac signal from real magnetocardiographic (MCG) data.     

Spatio–Temporal Adaptation in the Unsupervised Development of Networked Visual Neurons

There have been many computational models mimicking the visual cortex that are based on spatial adaptations of unsupervised neural networks. In this paper, we present a new model called neuronal cluster which includes spatial as well as temporal weights in its unified adaptation scheme. The “in-place” nature of the model is based on two biologically plausible learning rules, Hebbian rule and lateral inhibition. We present the mathematical demonstration that the temporal weights are derived from the delay in lateral inhibition. By training with the natural videos, this model can develop spatio–temporal features such as orientation selective cells, motion sensitive cells, and spatio–temporal complex cells. The unified nature of the adaption scheme allows us to construct a multilayered and task-independent attention selection network which uses the same learning rule for edge, motion, and color detection, and we can use this network to engage in attention selection in both static and dynamic scenes.      

Lattice Dynamical Wavelet Neural Networks Implemented Using Particle Swarm Optimization for Spatio–Temporal System Identification

In this brief, by combining an efficient wavelet representation with a coupled map lattice model, a new family of adaptive wavelet neural networks, called lattice dynamical wavelet neural networks (LDWNNs), is introduced for spatio-temporal system identification. A new orthogonal projection pursuit (OPP) method, coupled with a particle swarm optimization (PSO) algorithm, is proposed for augmenting the proposed network. A novel two-stage hybrid training scheme is developed for constructing a parsimonious network model. In the first stage, by applying the OPP algorithm, significant wavelet neurons are adaptively and successively recruited into the network, where adjustable parameters of the associated wavelet neurons are optimized using a particle swarm optimizer. The resultant network model, obtained in the first stage, however, may be redundant. In the second stage, an orthogonal least squares algorithm is then applied to refine and improve the initially trained network by removing redundant wavelet neurons from the network. An example for a real spatio-temporal system identification problem is presented to demonstrate the performance of the proposed new modeling framework.     

Spatio‐Temporal Contours from Deep Volume Raycasting

We visualize contours for spatio‐temporal processes to indicate where and when non‐continuous changes occur or spatial bounds are encountered. All time steps are comprised densely in one visualization, with contours allowing to efficiently analyze processes in the data even in case of spatial or temporal overlap. Contours are determined on the basis of deep raycasting that collects samples across time and depth along each ray. For each sample along a ray, its closest neighbors from adjacent rays are identified, considering time, depth, and value in the process. Large distances are represented as contours in image space, using color to indicate temporal occurrence. This contour representation can easily be combined with volume rendering‐based techniques, providing both full spatial detail for individual time steps and an outline of the whole time series in one view. Our view‐dependent technique supports efficient progressive computation, and requires no prior assumptions regarding the shape or nature of processes in the data. We discuss and demonstrate the performance and utility of our approach via a variety of data sets, comparison and combination with an alternative technique, and feedback by a domain scientist.     

Spatio‐Temporal Filtering of Indirect Lighting for Interactive Global Illumination

We introduce a screen‐space statistical filtering method for real‐time rendering with global illumination. It is inspired by statistical filtering proposed by Meyer et al. to reduce the noise in global illumination over a period of time by estimating the principal components from all rendered frames. Our work extends their method to achieve nearly real‐time performance on modern GPUs. More specifically, our method employs the candid covariance‐free incremental PCA to overcome several limitations of the original algorithm by Meyer et al., such as its high computational cost and memory usage that hinders its implementation on GPUs. By combining the reprojection and per‐pixel weighting techniques, our method handles the view changes and object movement in dynamic scenes as well.     

Visual Analysis of Spatio‐Temporal Data: Applications in Weather Forecasting

Weather conditions affect multiple aspects of human life such as economy, safety, security, and social activities. For this reason, weather forecast plays a major role in society. Currently weather forecasts are based on Numerical Weather Prediction (NWP) models that generate a representation of the atmospheric flow. Interactive visualization of geo‐spatial data has been widely used in order to facilitate the analysis of NWP models. This paper presents a visualization system for the analysis of spatio‐temporal patterns in short‐term weather forecasts. For this purpose, we provide an interactive visualization interface that guides users from simple visual overviews to more advanced visualization techniques. Our solution presents multiple views that include a timeline with geo‐referenced maps, an integrated webmap view, a forecast operation tool, a curve‐pattern selector, spatial filters, and a linked meteogram. Two key contributions of this work are the timeline with geo‐referenced maps and the curve‐pattern selector. The latter provides novel functionality that allows users to specify and search for meaningful patterns in the data. The visual interface of our solution allows users to detect both possible weather trends and errors in the weather forecast model. We illustrate the usage of our solution with a series of case studies that were designed and validated in collaboration with domain experts.     

Strategies for Creating A Learning Organization

Managers having a hard time turning their organizations into learning ones may be having difficulty because there is more than one way to create a learning organization. Equally confounding is that there is more than one way to define what a learning organization is. This article gives IT managers a working definition of a learning organization along with six strategies for creating one. These strategies may also be used to revitalize an organization's learning initiative.     

A Truncated Sum of Processing‐Times–Based Learning Model for a Two‐Machine Flowshop Scheduling Problem

Scheduling with learning effects has gained increasing attention in recent years. A well‐known learning model is called “sum‐of‐processing‐times‐based learning” in which the actual processing time of a job is a nonincreasing function of the jobs already processed. However, the actual processing time of a given job drops to zero precipitously when the normal job processing times are large. Moreover, the concept of learning process is relatively unexplored in a flowshop environment. Motivated by these observations, this article addresses a two‐machine flowshop problem with a truncated learning effect. The objective is to find an optimal schedule to minimize the total completion time. First, a branch‐and‐bound algorithm incorporating with a dominance property and four lower bounds is developed to derive the optimal solution. Then three simulated annealing algorithms are also proposed for near‐optimal solution. The experimental results indicated that the branch‐and‐bound algorithm can solve instances up to 18 jobs, and the proposed simulated annealing algorithm performs well in item of CPU time and error percentage. © 2011 Wiley Periodicals, Inc.     

最大-乘积模糊联想记忆的神经网络学习算法

在模糊系统中,从某种意义上说,乘积关系编码可以比最小关系编码保留更多的信息。提出了最大乘积模糊联想记忆的一种新的神经网络学习算法,并给出了严格的理论证明。该算法能够将多个模糊模式对可靠地编码存储到尽可能少的连接权矩阵中,从而大大地减少存储空间,而且容易实现,并举例验证了它的有效性。     

Defense strategies for Adversarial Machine Learning: A survey

Adversarial Machine Learning (AML) is a recently introduced technique, aiming to deceive Machine Learning (ML) models by providing falsified inputs to render those models ineffective. Consequently, most researchers focus on detecting new AML attacks that can undermine existing ML infrastructures, overlooking at the same time the significance of defense strategies. This article constitutes a survey of the existing literature on AML attacks and defenses with a special focus on a taxonomy of recent works on AML defense techniques for different application domains, such as audio, cyber-security, NLP, and computer vision. The proposed survey also explores the methodology of the defense solutions and compares them using several criteria, such as whether they are attack- and/or domain-agnostic, deploy appropriate AML evaluation metrics, and whether they share their source code and/or their evaluation datasets. To the best of our knowledge, this article constitutes the first survey that seeks to systematize the existing knowledge focusing solely on the defense solutions against AML and providing innovative directions for future research on tackling the increasing threat of AML.     

Special Tutorial: The Organization of Electronic Cyclic Memories

Cyclic memories are memories in which data rotate cyclically past a read/write port. The most common cyclic memories in use today are mechanical drums and fixed-head disks. In the past, small electronic cyclic memories have been made from MOS technology; more recently they have been made from charge-coupled devices and magnetic bubbles. Because of advances in integrated technology, large electronic cyclic memories that might be replacements for drum and disk memories are likely to become available. Whereas it is difficult to predict what technology will eventually emerge for electronic auxiliary memories, present projections suggest that cyclically organized memories based upon magnetic bubbles or charge-coupled devices are potential candidates. The disadvantage of cyclic organization is that access time due to memory latency may be excessive. The problem we investigate in this paper is how to modify electronic cyclic memories in relatively minor and inexpensive ways so as to decrease rotational latency in a system environment.     

溢出代码和访存压力敏感的快速机器学习*

基于遗传算法提出了溢出代码和访存压力敏感的机器学习来调试寄存器分配的权值函数。不同于以往采用目标程序的运行时间作为适应值,通过静态分析寄存器分配产生的溢出代码和基本块中的访存压力来构建适应值,以减少学习时间。这些分析被限定在热点函数中,在保证适应值精度的同时进一步加快了学习速度。实验表明,快速学习仅需要考虑热点函数的编译时间,整个CPU2000CINT测试集在5 h内即可学习完毕。大部分CPU2000CINT测试例子的性能得到了提高。其中perlbmk的性能提升最高可达到7.2%。     

机器学习中原型学习研究进展

随着信息技术在社会各领域的深入渗透,人类社会所拥有的数据总量达到了一个前所未有的高度.一方面,海量数据为基于数据驱动的机器学习方法获取有价值的信息提供了充分的空间;另一方面,高维度、过冗余以及高噪声也是上述繁多、复杂数据的固有特性.为消除数据冗余、发现数据结构、提高数据质量,原型学习是一种行之有效的方式.通过寻找一个原型集来表示目标集,以从样本空间进行数据约简,在增强数据可用性的同时,提升机器学习算法的执行效率.其可行性在众多应用领域中已得到证明.因此,原型学习相关理论与方法的研究是当前机器学习领域的一个研究热点与重点.主要介绍了原型学习的研究背景和应用价值,概括介绍了各类原型学习相关方法的基本特性、原型的质量评估以及典型应用;接着,从原型学习的监督方式及模型设计两个视角重点介绍了原型学习的研究进展,其中,前者主要涉及无监督、半监督和全监督方式,后者包括基于相似度、行列式点过程、数据重构和低秩逼近这四大类原型学习方法;最后,对原型学习的未来发展方向进行了展望.     

Hypernetworks: A Molecular Evolutionary Architecture for Cognitive Learning and Memory

Recent interest in human-level intelligence suggests a rethink of the role of machine learning in computational intelligence. We argue that without cognitive learning the goal of achieving human-level synthetic intelligence is far from completion. Here we review the principles underlying human learning and memory, and identify three of them, i.e., continuity, glocality, and compositionality, as the most fundamental to human-level machine learning. We then propose the recently-developed hypernetwork model as a candidate architecture for cognitive learning and memory. Hypernetworks are a random hypergraph structure higher-order probabilistic relations of data by an evolutionary self-organizing process based on molecular self- assembly. The chemically-based massive interaction for information organization and processing in the molecular hypernetworks, referred to as hyperinteractionism, is contrasted with the symbolist, connectionist, and dynamicist approaches to mind and intelligence. We demonstrate the generative learning capability of the hypernetworks to simulate linguistic recall memory, visual imagery, and language-vision crossmodal translation based on a video corpus of movies and dramas in a multimodal memory game environment. We also offer prospects for the hyperinteractionistic molecular mind approach to a unified theory of cognitive learning.     

一种基于机器学习的虚拟机放置方法

为改善云数据中心的能耗、负载均衡性和服务等级协议(SLA)违背率,对虚拟机放置策略进行优化。基于IaaS环境,提出一种基于机器学习的虚拟机迁移调整方法。根据资源消耗的互补性和不均衡性对虚拟机进行预放置,使用深度神经网络预测物理机负载等级,并利用深度Q网络调整物理机数量。实验结果表明,该方法能够有效均衡负载分布,降低能源开销和SLA违背率。     

Surgical Tool Datasets for Machine Learning Research: A Survey

International Journal of Computer Vision - This paper is a comprehensive survey of datasets for surgical tool detection and related surgical data science and machine learning techniques and...     

基于机器学习的软件模块访存压力优化仿真

采用当前方法对软件模块访存压力进行优化时,优化后的软件模块带宽较高、数据传输延时高,存在有效性差的问题。将机器学习应用在软件模块的访存压力优化过程中,提出基于机器学习的软件模块访存压力优化方法。计算链路的使用率,并将计算结果传送到每条流对应的发送端中,发送端根据接收到的信息对发送速率进行调整,实现拥塞控制。采用多目标规划方法,根据预算值和实际值之间存在的偏差,构建软件模块访存压力优化模型,通过二进制粒子群算法对软件模块访存压力优化模型进行求解,实现软件模块访存压力的优化。仿真结果表明,所提方法的带宽高、数据传输延时小,验证了基于机器学习的软件模块访存压力优化方法的有效性。     

ShutterApp: Spatio‐temporal Exposure Control for Videos

A camera's shutter controls the incoming light that is reaching the camera sensor. Different shutters lead to wildly different results, and are often used as a tool in movies for artistic purpose, e.g., they can indirectly control the effect of motion blur. However, a physical camera is limited to a single shutter setting at any given moment. ShutterApp enables users to define spatio‐temporally‐varying virtual shutters that go beyond the options available in real‐world camera systems. A user provides a sparse set of annotations that define shutter functions at selected locations in key frames. From this input, our solution defines shutter functions for each pixel of the video sequence using a suitable interpolation technique, which are then employed to derive the output video. Our solution performs in real‐time on commodity hardware. Hereby, users can explore different options interactively, leading to a new level of expressiveness without having to rely on specialized hardware or laborious editing.