One-shot Model Research Articles

Multi-Objective Evolutionary Neural Architecture Search with Weight-Sharing Supernet

Deep neural networks have played a crucial role in the field of deep learning, achieving significant success in practical applications. The architecture of neural networks is key to their performance. In the past few years, these architectures have been manually designed by experts with rich domain knowledge. Additionally, the optimal neural network architecture can vary depending on specific tasks and data distributions. Neural Architecture Search (NAS) is a class of techniques aimed at automatically searching for and designing neural network architectures according to the given tasks and data. Specifically, evolutionary-computation-based NAS methods are known for their strong global search capability and have aroused widespread interest in recent years. Although evolutionary-computation-based NAS has achieved success in a wide range of research and applications, it still faces bottlenecks in training and evaluating a large number of individuals during optimization. In this study, we first devise a multi-objective evolutionary NAS framework based on a weight-sharing supernet to improve the search efficiency of traditional evolutionary-computation-based NAS. This framework combines the population optimization characteristic of evolutionary algorithms with the weight-sharing ideas in one-shot models. We then design a bi-population MOEA/D algorithm based on the proposed framework to effectively solve the NAS problem. By constructing two sub-populations with different optimization objectives, the algorithm can effectively explore network architectures of various sizes in complex search spaces. An inter-population communication mechanism further enhances the algorithm’s exploratory capability, enabling it to find network architectures with uniform distribution and high diversity. Finally, we conduct performance comparison experiments on image classification datasets of different scales and complexities. Experimental results demonstrate the effectiveness of the proposed multi-objective evolutionary NAS framework and the practicality and transferability of the introduced bi-population MOEA/D-based NAS method compared to existing state-of-the-art NAS methods.

AMCG: a graph dual atomic-molecular conditional molecular generator

Drug design is both a time consuming and expensive endeavour. Computational strategies offer viable options to address this task; deep learning approaches in particular are indeed gaining traction for their capability of dealing with chemical structures. A straightforward way to represent such structures is via their molecular graph, which in turn can be naturally processed by graph neural networks. This paper introduces AMCG, a dual atomic-molecular, conditional, latent-space, generative model built around graph processing layers able to support both unconditional and conditional molecular graph generation. Among other features, AMCG is a one-shot model allowing for fast sampling, explicit atomic type histogram assignation and property optimization via gradient ascent. The model was trained on the Quantum Machines 9 (QM9) and ZINC datasets, achieving state-of-the-art performances. Together with classic benchmarks, AMCG was also tested by generating large-scale sampled sets, showing robustness in terms of sustainable throughput of valid, novel and unique molecules.

Neural Architecture Search Using Covariance Matrix Adaptation Evolution Strategy.

Evolution-based neural architecture search methods have shown promising results, but they require high computational resources because these methods involve training each candidate architecture from scratch and then evaluating its fitness, which results in long search time. Covariance Matrix Adaptation Evolution Strategy (CMA-ES) has shown promising results in tuning hyperparameters of neural networks but has not been used for neural architecture search. In this work, we propose a framework called CMANAS which applies the faster convergence property of CMA-ES to the deep neural architecture search problem. Instead of training each individual architecture seperately, we used the accuracy of a trained one shot model (OSM) on the validation data as a prediction of the fitness of the architecture, resulting in reduced search time. We also used an architecture-fitness table (AF table) for keeping a record of the already evaluated architecture, thus further reducing the search time. The architectures are modeled using a normal distribution, which is updated using CMA-ES based on the fitness of the sampled population. Experimentally, CMANAS achieves better results than previous evolution-based methods while reducing the search time significantly. The effectiveness of CMANAS is shown on two different search spaces using four datasets: CIFAR-10, CIFAR-100, ImageNet, and ImageNet16-120. All the results show that CMANAS is a viable alternative to previous evolution-based methods and extends the application of CMA-ES to the deep neural architecture search field.

HCgNet: A hierarchical context-guided network for multi-object tracking

The anchor-free one-shot models, which localize the detections and extract embeddings by estimating center points in a single network have been proven highly effective in multi-object tracking (MOT). However, it is observed that the incomplete or unclear appearances of objects make the existing semantic feature aggregation in one-shot models less effective, which affects the performance of MOT. Moreover, these one-shot MOT models often generate wrong matches between detections and objects, because they ignore the influence of historical tracklet clues on objects. Motivated by these issues, we propose a novel hierarchical context-guided network for one-shot MOT, which performs the detection, embedding extraction, and object refinement by the hierarchical global-wise, patch-wise, and object-wise processing. Specifically, our method learns temporal and spatial context features in a global-wise and patch-wise manner to guide the multi-scale aggregation, so as to locate the area of interest and extract rich embeddings. In this way, the embedding of each detection owns both context relations besides semantic information, which reduces the loss of important information for tracked objects. At last, based on the learned context features, a context-guided object refinement module is designed to learn the tracklet embedding and produce refined objects in each frame, which can alleviate the erroneous matches between objects and detections. Extensive experiments conducted on several benchmarks, including 2D MOT2015, MOT17, and MOT20 datasets, demonstrate the effectiveness of our HCgNet.

Werewolf on campus: A case study in inoculation theory and gamified one-shot library instruction

This case study details the development and results of an information literacy game in which undergraduate students evaluated fictional sources to learn how to recognize a werewolf on campus. The game relied on inoculation theory and fiction to teach students to identify indicators of mis and disinformation outside of any real-world examples that might affect their learning experience. The game showed promise as students were far more engaged and demonstrated better retention later in the semester than students who received a more traditional lecture about disinformation and source evaluation. However, the game would likely be more effective if it were expanded beyond the one-shot model.

One-shot models for local core network placement and traffic optimization in self deployable networks

In recent years, we have witnessed a proliferation of core network (CN) virtualization, coupled with the emergence of self deployable architectures in cellular networks. These advances provide greater flexibility and allow CN functions to be virtualized and co-located with one or more base stations. However, they introduce new challenges, such as the optimal location of CN functions based on the physical architecture. In this paper, we tackle this problem and propose a new generic and efficient solution that locates the best base station to host the CN functions, while optimizing a given performance metric (e.g., maximum flow, max–min fairness, etc.) The core of our solution relies on jointly modeling the problem as a Mixed-Integer Nonlinear Programming (MINLP) and efficiently linearizing the nonlinear constraints. After presenting our model, we evaluate its performances, considering the global maximum flow as an optimization metric. The results showed that our joint modeling significantly reduces the run time compared to existing solutions while achieving the same optimal results. Furthermore, we highlight the genericity of our model, and we show how it can be easily adapted to handle different optimization metrics. We particularly consider some variants to address the fairness problem in conjunction with the local CN placement issue. We perform extensive simulations and discuss the obtained results. The latter allow us to derive insights regarding the tradeoff between maximum flow and fairness of proportional satisfaction, while highlighting the strengths of the proposed joint modeling.

Evolutionary Search for Complete Neural Network Architectures With Partial Weight Sharing

Neural architecture search (NAS) provides an automatic solution in designing network architectures. Unfortunately, the direct search for complete task-dependent network architectures is laborious since training and evaluating complete neural architectures over a large search space are computationally prohibitive. Recently, one-shot NAS (OSNAS) has attracted great attention in the NAS community because it significantly speeds up the candidate architecture evaluation procedure through weight sharing. However, the full weight sharing training paradigm in OSNAS may result in strong interference across candidate architectures and mislead the architecture search. To alleviate the problem, we propose a partial weight sharing OSNAS framework that directly evolves complete neural network architectures. In particular, we suggest a novel node representation scheme that randomly activates a subset of nodes of the one-shot model in each generation to reduce the weight coupling in the one-shot model. During the evolutionary search, a tailored crossover operator randomly samples the nodes from two parent individuals or a single parent to construct new candidate architectures, thus effectively constraining the degree of weight sharing. Furthermore, we introduce a new mutation operator that replaces the chosen nodes of the one-shot model with randomly generated nodes to enhance the exploratory capability. Finally, we encode a set of pyramidal convolution operations in the search space, enabling the evolved neural networks to capture different levels of details in the images. The proposed method is examined and compared with 26 state-of-the-art algorithms on ten image classification tasks, including CIFAR series, CINIC10, ImageNet, and MedMNIST series. The experimental results demonstrate that the proposed method can computationally much more efficiently find neural architectures that achieve comparable classification accuracy to the state-of-the-art designs.

An implementation on Python of the Classical Nelson and Winter Models

This paper addresses the computational implementation in Python of the family of classical Schumpeterian Competition models developed by Nelson and Winter. A simple one-shot model is presented as a seed for the development of evolutionary dynamic models. Then, a parallel development between theory and computational implementation using the inheritance capabilities present in Python is done, in order to contemplate innovation, system dynamics, adaptive innovation policies and patents. The results of the original work are compared to the results found throughout the development of this work.

One-Shots in Special Collections and Archives: Moving from Gatekeeper to Guide

Instruction in special collections and archives spaces has evolved from the once ubiquitous show-and-tell sessions, but it remains reliant on the one-shot model where classes visit the reading room to work with primary source material in a standalone session. As Nicole Pagowsky points out, “One-shots are transactional; content is requested and then deposited into student’ minds…” In special collections, this content takes the form of preselected rare books and manuscripts on a given topic, with which students interact for an hour or so before continuing on with their semester. These sessions, particularly at smaller institutions, are often limited by the breadth of the repository’s collections, which may have only a tenuous connection to course assignments and learning objectives.

Rethinking the Competition Between Detection and ReID in Multiobject Tracking.

Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destroy task-dependent representations learning. To tackle this problem, we propose a novel reciprocal network (REN) with a self-relation and cross-relation design so that to impel each branch to better learn task-dependent representations. The proposed model aims to alleviate the deleterious tasks competition, meanwhile improve the cooperation between detection and ReID. Furthermore, we introduce a scale-aware attention network (SAAN) that prevents semantic level misalignment to improve the association capability of ID embeddings. By integrating the two delicately designed networks into a one-shot online MOT system, we construct a strong MOT tracker, namely CSTrack. Our tracker achieves the state-of-the-art performance on MOT16, MOT17 and MOT20 datasets, without other bells and whistles. Moreover, CSTrack is efficient and runs at 16.4 FPS on a single modern GPU, and its lightweight version even runs at 34.6 FPS. The complete code has been released at https://github.com/JudasDie/SOTS.

Serving Everyone or Serving No One? Examining the Faux-Equity of the One-Shot

While the one-shot model of instruction is the most common model of library instruction, a review of the literature highlights that academic librarians have struggled to identify how and if it is possible to meet curricular needs. This theoretical literature review takes a critical look at the one-shot and argues that this model fails to be the equitable model we think it is. This literature review examines the one-shot by examining its role in combating or upholding information privilege, whether it can be used when supporting learners with disabilities, and what alternatives exist for instruction practices going forward.

ANALYSIS OF INNOVATION STRATEGIES TO INCREASE THE COMPETITIVE ADVANTAGES OF ULOS PRODUCTS IN PEMATANGSIANTAR CITY

One of the production sectors that has become the flagship product of Pematangsiantar City is ulos cloth. Ulos cloth is a typical woven fabric of the Batak community developed for generations in North Sumatra, one of which is the city of Pematangsiantar. This study aims to explore various information related to the number of ulos craftsmen in Pematangsiantar city to facilitate the government in grouping these ulos craftsmen and as a first step to formulate an innovation strategy for the development of creative ulos fabric production to be able to develop superior products armed with knowledge. knowledge, creativity, innovation and being able to create jobs for the community. This type of research is qualitative with a one-shot model, namely an approach model by conducting one-time data collection on an object of research. The research subjects taken in this study were ulos craftsmen spread across eight sub-districts of Pematangsiantar City. The analysis was carried out in eight sub-districts in Pematangsiantar City. Data collection techniques using observation, interviews and questionnaires, field notes and documentation.The results of the study concluded that the innovation strategy applied by the ulos fabric craftsmen was not optimal, this was due to the limited capacity and opportunity to innovate, the ulos craftsmen experienced problems in making product innovations related to technological limitations caused by limited investment capital to buy new machines or equipment. to improve production processes and limited human resources who can operate new machines or make innovations that take advantage of technological developments.

One-shot neural architecture search for fault diagnosis using vibration signals

Machine learning method has been widely applied in industrial fault diagnosis, especially the deep learning method. In the field of industrial fault diagnosis, deep learning is mostly used to extract features of vibration signals to achieve end-to-end fault diagnosis systems. Due to the complexity and variety of actual industrial datasets, some deep learning models are designed to be complicated. However, designing neural network architectures requires rich professional knowledge, experience, and a large number of experiments, increasing the difficulty of developing deep learning models. Fortunately, Neural Architecture Search (NAS), a branch of Automated Machine Learning (AutoML), is developing rapidly. Given a search space, NAS can search for networks that perform better than manually designed. In this paper, a one-shot NAS method for fault diagnosis is proposed. The one-shot model is a supernet that contains all candidate networks in a given search space. The supernet is trained to evaluate the actual performance of candidate networks by measuring the difference between its output probability and the true labels. According to the prediction of supernet, the networks with excellent performance can be searched, using some common search methods such as random search or evolutionary algorithm. Finally, the searched network is trained by reusing the weights of the supernet. To evaluate the proposed method, two search spaces are designed, ResNet and Inception search spaces, to search on PHM 2009 Data Challenge gearbox dataset. The state-of-the-art results are obtained, and accuracies of searched ResNet-A and Inception-A are 84.11% and 83.81%, which are 3.29% and 10.88% higher than Reinforcement Learning based NAS.

Self-validated ensemble models for design of experiments

One of the possible objectives when designing experiments is to build or formulate a model for predicting future observations. When the primary objective is prediction, some typical approaches in the planning phase are to use well-established small-sample experimental designs in the design phase (e.g., Definitive Screening Designs) and to construct predictive models using widely used model selection algorithms such as LASSO. These design and analytic strategies, however, do not guarantee high prediction performance, partly due to the small sample sizes that prevent partitioning the data into training and validation sets, a strategy that is commonly used in machine learning models to improve out-of-sample prediction. In this work, we propose a novel framework for building high-performance predictive models from experimental data that capitalizes on the advantage of having both training and validation sets. However, instead of partitioning the data into two mutually exclusive subsets, we propose a weighting scheme based on the fractional random weight bootstrap that emulates data partitioning by assigning anti-correlated training and validation weights to each observation. The proposed methodology, called Self-Validated Ensemble Modeling (SVEM), proceeds in the spirit of bagging so that it iterates through bootstraps of anti-correlated weights and fitted models, with the final SVEM model being the average of the bootstrapped models. We investigate the performance of the SVEM algorithm with several model-building approaches such as stepwise regression, Lasso, and the Dantzig selector. Finally, through simulation and case studies, we show that SVEM generally generates models with better prediction performance in comparison to one-shot model selection approaches.

Research on multi-feature human pose model recognition based on one-shot learning

With the development of human-computer interaction, virtual reality, and other related fields, human posture recognition has become a hot research topic. Since the human body belongs to a non-rigid model and has time-varying characteristics, the accuracy and robustness of recognition are not ideal. Based on the KinectV2 so-matosensory camera to collect skeletal information, this paper proposes a one-shot learning model matching method based on human body angle and distance characteristics. First, feature extraction is performed on the collected bone information, and the joint point vector angle and joint point displacement are calculated and a threshold is set. Secondly, the pose to be measured is matched with the template pose, and the recognition is successful if the threshold limit is met. Experimental results show that the method can detect and recognize human poses within the defined threshold in real-time, which improves the accuracy and robustness of recognition.

THE ROLE OF SOCIAL MEDIA IN INCREASING MARKET SHARE OF MSME PRODUCTS IN PEMATANGSIANTAR CITY

The increase in product market share cannot be separated from the connectivity of the marketing system and media used. Marketing channels play an important role in increasing sales both in the short and long term. This study aimed to determine the role of social media in increasing the market share of MSME products in Pematangsiantar City. The research design used a literature study and field study models using a qualitative approach with a one-shot model. The research location was in 8 districts in Pematangsiantar City. The population in this study were MSME players scattered in 8 districts in Pematangsiantar City. The samples were collected using a non-probability sampling technique with purposive sampling technique, so that a total sample size of 240 respondents were obtained. Moreover, the data analysis technique used in this study was data analysis with a data reduction model that was obtained from data collection and data display. The results of this study concluded that the use of social media was very dominant in MSME players in the micro sector and Instagram was one type of social media that was often used. Furthermore, the results of the study also suggested that the time factor was the basis for MSME players using social media as a medium for promoting their products.

Pengaruh Kuat Arus Dan Besar Sudut Kampuh Terhadap Kekuatan Impact Dan Nilai Kekerasan Plat Baja Karbon Rendah Dengan Menggunakan Las SMAW

Abstract: Welding is welding that utilizes flame heat in electric arcs to melt electrodes and workpieces. SMAW welding is widely used because of its relatively easy to use, cost-friendly and maximum quality results. In conducting welding has several factors that will affect the quality of the welding results such as a welder, welding current and metal distance and welding seam angle. This study aims to determine whether there is an influence of current variations and magnitude of the seam angle to the value of the impact strength and the hardness value of the SMAW welding results. This study uses a pre-experimental method with a one-shot case model. The results of this study indicate the highest impact strength values of current variations in the 80 Ampere specimen at the angle of seam V 60o in the amount of 0.0799 J / mm2 and in the 80 Ampere specimen in the angle of the 80o V in the seam angle of 0.0942 J / mm2. Then for the highest impact strength value variation of seam angle V group of seam angle specimen V 80o current 80 Amperes is equal to 0.0942 J / mm2 and specimen angle of seam V 80o current 100 Ampere 0.0824 J / mm2. The highest hardness value is obtained with a variation of the current specimen group of 100 Ampere in the angle of seam V 60o that is equal to 187.1 HVN and in the specimen group 100 Ampere with the angle of contact V 80o that is equal to 204.4 HVN. Then the highest hardness value variation angle seam V specimen V 80o with current 80 Amperes is equal to 191.63 HVN and specimen angle of seam V 80o with 100 amperes current that is equal to 204.4 HVN. KeyWords : SMAW, Welding current, V groove, Impact Strength, Hardness

Teaching GIS in a Digital Humanities Environment

The University of Georgia Libraries has been teaching a one credit introductory GIS class as part of the Undergraduate Certificate in Digital Humanities which transforms library education from a one-shot model of teaching map and data literacy, to a credit bearing semester long course that provides a deeper understanding of GIS. The class focuses on student learning objectives, which include the ability to critically evaluate cartographic information, gain a proficiency in data literacy as it applies to geospatial data, gain introductory skills in GIS technologies and to use GIS data to explore and answer humanities based research questions in the Digital Humanities.

Multi-Loss Siamese Neural Network With Batch Normalization Layer for Malware Detection

Malware detection is an essential task in cyber security. As the trend of malicious attacks grows, unknown malware detection with high accuracy becomes more and more challenging. The current deep learning-based approaches for malware detection are typically trained with large amounts of samples using labeled and existing malware families in the training set, thus, their capability to detect new unseen malware (such as a zero-day attack) is limited. To address this issue, we propose a new one-shot model called “Multi-Loss Siamese Neural Network with Batch Normalization Layer” that can work with fewer samples while providing high detection accuracy. Our model utilizes the Siamese Neural Network to detect new variants of malware that is trained with only a few samples. Our model is equipped with batch normalization and multiple loss functions to address the overfitting issue, due to the use of small samples, that can create the vanishing gradient problem as a result of binary cross-entropy loss, and feature embedding space to improve the detection accuracy. In addition, we illustrate a way to convert raw binary files into malware gray scale images, to work with the popular Siamese Neural Network by generating the positive and negative pairs for training. Our experimental results show that our model outperforms existing similar methods.

One-Shot Capacity Bounds on the Simultaneous Transmission of Classical and Quantum Information

We study the communication capabilities of a quantum channel under the most general channel model known as the one-shot model. Unlike classical channels that can only be used to transmit classical information (bits), a quantum channel can be used for transmission of classical information, quantum information (qubits) and simultaneous transmission of classical and quantum information. In this work, we investigate the one-shot capabilities of a quantum channel for simultaneously transmitting of bits and qubits. This problem was studied in the asymptotic regime for a memoryless channel and a regularized characterization of the capacity region was reported. It is known that the transmission of private classical information is closely related to the problem of quantum information transmission. We resort to this idea and find achievable and converse bounds on the simultaneous transmission of the public and private classical information. then by shifting the classical private rate to the quantum information rate, the obtained rate regions will be translated into rate regions of thThis in turn, leads to a rate region for simulttaneous transmission of classical and quantum information. In the case of asymptotic i.i.d. setting, our one-shot result is evaluated to the known results in the literature. Our main tools used in the achievability proofs are position-based decoding and convex-split lemma.