摘要 :
The paper extends the classical Ant System (AS) algorithms by proposing a novel approach of exponential pheromone deposition by artificial ants ensuring a concentration gradient along solution paths. The stability analysis with a ...
展开
The paper extends the classical Ant System (AS) algorithms by proposing a novel approach of exponential pheromone deposition by artificial ants ensuring a concentration gradient along solution paths. The stability analysis with a deterministic mathematical model based on differential equation yields the proper range of the parameters. A roadmap of connected cities, where the shortest path between a source-destination pair is to be determined, is taken as a problem environment. Exhaustive simulations confirm that the proposed deposition rule, with properly chosen parameter values, outperforms the traditional one with large margin both in terms of solution quality and algorithm convergence.
收起
摘要 :
Unsupervised models can provide supplementary soft constraints to help classify new "target" data because similar instances in the target set are more likely to share the same class label. Such models can also help detect possible...
展开
Unsupervised models can provide supplementary soft constraints to help classify new "target" data because similar instances in the target set are more likely to share the same class label. Such models can also help detect possible differences between training and target distributions, which is useful in applications where concept drift may take place, as in transfer learning settings. This article describes a general optimization framework that takes as input class membership estimates from existing classifiers learned on previously encountered "source" (or training) data, as well as a similarity matrix from a cluster ensemble operating solely on the target (or test) data to be classified, and yields a consensus labeling of the target data. More precisely, the application settings considered are nontransductive semisupervised and transfer learning scenarios where the training data are used only to build an ensemble of classifiers and are subsequently discarded before classifying the target data. The framework admits a wide range of loss functions and classification/clustering methods. It exploits properties of Bregman divergences in conjunction with Legendre duality to yield a principled and scalable approach. A variety of experiments show that the proposed framework can yield results substantially superior to those provided by naively applying classifiers learned on the original task to the target data. In addition, we show that the proposed approach, even not being conceptually transductive, can provide better results compared to some popular transductive learning techniques.
收起
摘要 :
The advent and spread of novel coronavirus (nCoV) has posed a new public health crisis since December 2019. Several cases of unexplained pneumonia occurred in Wuhan, Hubei Province, China, only a month before the Chinese Spring fe...
展开
The advent and spread of novel coronavirus (nCoV) has posed a new public health crisis since December 2019. Several cases of unexplained pneumonia occurred in Wuhan, Hubei Province, China, only a month before the Chinese Spring festival. After the diagnosis of broncho-alveolar fluid samples of people infected, the new coronavirus was identified using next-generation sequence technology. This work aims to provide information regarding COVID-19 that will help the researchers to identify the vital therapeutic targets for SARS-CoV-2 and also will provide insights into some significant findings of recent times highlighted by scientific communities around the globe. In this review, we have tried to explore multiple aspects related to COVID-19, including epidemiology, etiology, COVID-19 variants, vaccine candidates, potential therapeutic targets, the role of natural products, and computational studies in drug design and development, repurposing, and analysis of crystal structures available for COVID-19 related protein structures. Druggable targets include all viral enzymes and proteins involved in viral replication and regulation of host cellular machines. The medical community tracks several therapies to combat the infection by investigating various antiviral and immunomodulatory mechanisms. While some vaccines are approved in this worldwide health crisis, a more precise therapy or drug is formally recommended to be used against SARS-CoV-2 infection. Natural products other than synthetic drugs have been tested by in silico analysis against COVID-19. However, important issues still need to be addressed regarding in vivo bioavailability and better efficacy.
收起
摘要 :
This contribution demonstrates how artificial ants can extract regular geometric shapes from grey scale images. We propose here two methods the first of which is a modified version of existing Ant System algorithm. The second meth...
展开
This contribution demonstrates how artificial ants can extract regular geometric shapes from grey scale images. We propose here two methods the first of which is a modified version of existing Ant System algorithm. The second method proposed is Ant Regeneration and Recombination System (ARRS). Our schemes comprise of three steps. Firstly, MATLAB edge detection operator converts a grey scale image into a binary one. Our schemes are then applied on this binary image to detect closed loops. Finally, these closed loops are tested for different geometric shapes. The schemes with incredible time and memory efficiency can detect both intersecting and non intersecting regular shapes.
收起
摘要 :
The abundance of digital text has led to extensive research on topic models that reason about documents using latent representations. Since for many online or streaming textual sources such as news outlets, the number, and nature ...
展开
The abundance of digital text has led to extensive research on topic models that reason about documents using latent representations. Since for many online or streaming textual sources such as news outlets, the number, and nature of topics change over time, there have been several efforts that attempt to address such situations using dynamic versions of topic models. Unfortunately, existing approaches encounter more complex inferencing when their model parameters are varied over time, resulting in high computation complexity and performance degradation. This paper introduces the DM-DTM, a dual Markov chain dynamic topic model, for characterizing a corpus that evolves over time. This model uses a gamma Markov chain and a Dirichlet Markov chain to allow the topic popularities and word-topic assignments, respectively, to vary smoothly over time. Novel applications of the Negative-Binomial augmentation trick result in simple, efficient, closed-form updates of all the required conditional posteriors, resulting in far lower computational requirements as well as less sensitivity to initial conditions, as compared to existing approaches. Moreover, via a gamma process prior, the number of desired topics is inferred directly from the data rather than being pre-specified and can vary as the data changes. Empirical comparisons using multiple real-world corpora demonstrate a clear superiority of DM-DTM over strong baselines for both static and dynamic topic models.
收起
原文获取