Search

This article proposes auction-inspired multi-player generative adversarial networks training, which mitigates the mode collapse problem of GANs. Mode collapse occurs when an over-fitted generator generates a limited range of samples, often concentrating on a small subset of the data distribution. Despite the restricted diversity of generated samples, the discriminator can still be deceived into distinguishing these samples as real samples from the actual distribution. In the absence of external standards, a model cannot recognize its failure during the training phase. We extend the two-player game of generative adversarial networks to the multi-player game. During the training, the values of each model are determined by the bids submitted by other players in an auction-like process.

Detecting fake news has received a lot of attention. Many previous methods concatenate independently encoded unimodal data, ignoring the benefits of integrated multimodal information. Also, the absence of specialized feature extraction for text and images further limits these methods. This paper introduces an end-to-end model called TT-BLIP that applies the bootstrapping language-image pretraining for unified vision-language understanding and generation (BLIP) for three types of information: BERT and BLIP\textsubscript{Txt} for text, ResNet and BLIP\textsubscript{Img} for images, and bidirectional BLIP encoders for multimodal information. The Multimodal Tri-Transformer fuses tri-modal features using three types of multi-head attention mechanisms, ensuring integrated modalities for enhanced representations and improved multimodal data analysis. The experiments are performed using two fake news datasets, Weibo and Gossipcop. The results indicate TT-BLIP outperforms the state-of-the-art models., Comment: 8 pages, submitted to conference

Despite the efficient market hypothesis, many studies suggest the existence of inefficiencies in the stock market leading to the development of techniques to gain above-market returns. Systematic trading has undergone significant advances in recent decades with deep learning schemes emerging as a powerful tool for analyzing and predicting market behavior. In this paper, a method is proposed that is inspired by how professional technical analysts trade. This scheme looks at stock prices of the previous 600 days and predicts whether the stock price will rise or fall 10% or 20% within the next D days. The proposed method uses the Resnet's (a deep learning model) skip connections and logits to increase the probability of the prediction. The model was trained and tested using historical data from both the Korea and US stock markets. The backtest is done using the data from 2020 to 2022. Using the proposed method for the Korea market it gave return of 75.36% having Sharpe ratio of 1.57, which far exceeds the market return by 36% and 0.61, respectively. On the US market it gives total return of 27.17% with Sharpe ratio of 0.61, which outperforms other benchmarks such as NASDAQ, S&P500, DOW JONES index by 17.69% and 0.27, respectively., Comment: 35 pages, 14 figures

Deep learning has recently become one of the most compute/data-intensive methods and is widely used in many research areas and businesses. One of the critical challenges of deep learning is that it has many parameters that can be adjusted, and the optimal value may need to be determined for faster operation and high accuracy. The focus of this paper is the adjustable parameters of the dataloader. The dataloader in a system mainly groups the data appropriately and loads it to the main memory for the deep learning model to use. We introduce an automated framework called Dataloader Parameter Tuner (DPT) that determines the optimal value for the parameters required for the dataloader. This framework discovers the optimal values for the number of dataloader's subprocesses (i.e., worker) and prefetch factor through grid search to accelerate the data transfer for machine learning systems.

Multiple modalities for certain information provide a variety of perspectives on that information, which can improve the understanding of the information. Thus, it may be crucial to generate data of different modality from the existing data to enhance the understanding. In this paper, we investigate the cross-modal audio-to-image generation problem and propose Cross-Modal Contrastive Representation Learning (CMCRL) to extract useful features from audios and use it in the generation phase. Experimental results show that CMCRL enhances quality of images generated than previous research., Comment: 7 pages, 3 figures, Accepted to MUE 2022

Recent deep learning models are difficult to train using a large batch size, because commodity machines may not have enough memory to accommodate both the model and a large data batch size. The batch size is one of the hyper-parameters used in the training model, and it is dependent on and is limited by the target machine memory capacity because the batch size can only fit into the remaining memory after the model is uploaded. Moreover, the data item size is also an important factor because if each data item size is larger then the batch size that can fit into the remaining memory becomes smaller. This paper proposes a framework called Micro-Batch Streaming (MBS) to address this problem. This method helps deep learning models to train by providing a batch streaming method that splits a batch into a size that can fit in the remaining memory and streams them sequentially. A loss normalization algorithm based on the gradient accumulation is used to maintain the performance. The purpose of our method is to allow deep learning models to train using larger batch sizes that exceed the memory capacity of a system without increasing the memory size or using multiple devices (GPUs)., Comment: In submitted

The emergence of quantum computing enables for researchers to apply quantum circuit on many existing studies. Utilizing quantum circuit and quantum differential programming, many research are conducted such as \textit{Quantum Machine Learning} (QML). In particular, quantum reinforcement learning is a good field to test the possibility of quantum machine learning, and a lot of research is being done. This work will introduce the concept of quantum reinforcement learning using a variational quantum circuit, and confirm its possibility through implementation and experimentation. We will first present the background knowledge and working principle of quantum reinforcement learning, and then guide the implementation method using the PennyLane library. We will also discuss the power and possibility of quantum reinforcement learning from the experimental results obtained through this work.

The skip-gram (SG) model learns word representation by predicting the words surrounding a center word from unstructured text data. However, not all words in the context window contribute to the meaning of the center word. For example, less relevant words could be in the context window, hindering the SG model from learning a better quality representation. In this paper, we propose an enhanced version of the SG that leverages context information to produce word representation. The proposed model, Contextual Skip-gram, is designed to predict contextual words with both the center words and the context information. This simple idea helps to reduce the impact of irrelevant words on the training process, thus enhancing the final performance

This paper proposes a distributed deep learning framework for privacy-preserving medical data training. In order to avoid patients' data leakage in medical platforms, the hidden layers in the deep learning framework are separated and where the first layer is kept in platform and others layers are kept in a centralized server. Whereas keeping the original patients' data in local platforms maintain their privacy, utilizing the server for subsequent layers improves learning performance by using all data from each platform during training., Comment: 2019 IEEE/IFIP International Conference on Dependable Systems and Networks Supplemental

An ad hoc grid is a wireless heterogeneous computing environment without a fixed infrastructure. This study considers wireless devices that have different capabilities, have limited battery capacity, support dynamic voltage scaling, and are expected to be used for eight hours at a time and then recharged. To maximize the performance of the system, it is essential to assign resources to tasks (match) and order the execution of tasks on each resource (schedule) in a manner that exploits the heterogeneity of the resources and tasks while considering the energy constraints of the devices. In the single-hop ad hoc grid heterogeneous environment considered in this study, tasks arrive unpredictably, are independent (no precedent constraints for tasks), and have priorities and deadlines. The problem is to map (match and schedule) tasks onto devices such that the number of highest priority tasks completed by their deadlines during eight hours is maximized while efficiently utilizing the overall system energy. A model for dynamically mapping tasks onto wireless devices is introduced. Seven dynamic mapping heuristics for this environment are designed and compared to each other and to a mathematical bound.

Nonlinear fiber devices have been attracting considerable attention in recent years, due to their inherent ultrafast response time and potential applications in optical communication systems. They usually require long fibers to generate sufficient nonlinear phase shifts, since nonlinearities of conventional silica-core silica-clad fibers are too low. These long devices, however, cause the serious problems of pulse walk-off, pulse broadening, and polarization fluctuation which are major limiting factors for response time, switching bandwidth, and maximum transmittable bit-rate. Therefore, short device length is indispensable for achieving ultrafast switching and higher bit-rate data transmission. To shorten the required device length, fiber nonlinearities should be increased. In this dissertation, as a way of increasing fiber nonlinearities, high-nonlinearity materials of Litharge, Bismite, Tellurite, and Chalcogenide glasses have been considered. Although they have high nonlinearities, they also have high group-velocity dispersion and high losses deteriorating the performance of nonlinear fiber devices seriously. The aim of this work is to investigate how these high-nonlinearity glasses affect the performance of nonlinear fiber devices, taking into consideration both the advantages and disadvantages. To achieve it, the critical properties of various nonlinear fiber devices constructed with the different types of high-nonlinearity glasses and different types of fibers have been evaluated. It turned out that the required device lengths of nonlinear fiber devices constructed with the high-nonlinearity glasses were significantly reduced and high group-velocity dispersions and losses could not be major problems due to the extremely short device length. As a result, it would be possible to suppress the problems of pulse walk-off, pulse broadening, and polarization fluctuation in nonlinear fiber devices by introducing high-nonlinearity glasses, thus enabling ultrafast swit

When user's tasks in a distributed heterogeneous computing environment are allocated resources, and the total demand placed on system resources by the tasks, for a given interval of time, exceeds the resources available, some tasks will receive degraded service, receive no service at all, or may be dropped from the system. One part of a measure to quantify the success of a resource management system (RMS) in such an environment is the collective value of the tasks completed during an interval of time, as perceived by the user, the application, or the policy maker. For the case where a task may be a data communication request, the collective value of data communication requests that are satisfied during an interval of time is measured. The Flexible Integrated System Capability (FISC) measure defined here is one way of obtaining a multi-dimensional measure for quantifying this collective value. While the FISC measure itself is not sufficient for scheduling purposes, it can be a critical part of a scheduler or a scheduling heuristic. The primary contribution of this work is providing a way to measure the collective value accrued by an RMS using a broad range of attributes and to construct a flexible framework that can be extended for particular problem domains., DABT63-99-C-0012.

When users' tasks in a distributed heterogeneous computing environment are allocated resources, and the total demand placed on system resources by the tasks, for a given interval of time, exceeds the resources available, some tasks will receive degraded service, receive no service at all, or may be dropped from the system. One part of a measure to quantify the success of a resource management system (RMS) in such an environment is the collective value of the tasks completed during an interval of time, as perceived by the user, the application, or the policy maker. For the case where a task may be a data communication request, the collective value of data communication requests that are satisfied during an interval of time is measured. The Flexible Integrated System Capability (FISC) measure defined here is one way of obtaining a multi-dimensional measure for quantifying this collective value. While the FISC measure itself is not sufficient for scheduling purposes, it can be a critical part of a scheduler or a scheduling heuristic. The primary contribution of this work is providing a way to measure the collective value accrued by an RMS using a broad range of attributes and to construct a flexible framework that can be extended for particular problem domains.

In a distributed heterogeneous computing environment, users' tasks are allocated resources to simultaneously satisfy, to varying degrees, the tasks different, and possibly conflicting, quality of service (QoS) requirements. When the total demand placed on system resources by the tasks, for a given interval of time, exceeds the resources available, some tasks will receive degraded service or no service at all. One part of a measure to quantify the success of a resource management system (RMS) in such a distributed environment is the collective value of the tasks completed during an interval of time, as perceived by the user, application, or policy maker. The Flexible Integrated System Capability (FISC) ratio introduced here is a measure for quantifying this collective value. The FISC ratio is a multi-dimensional measure, and may include priorities, versions of a task or data, deadlines, situational mode, security, application- and domain-specific QoS, and dependencies. In addition to being used for evaluating and comparing RMSs, the FISC ratio can be incorporated as part of the objective function in a system's scheduling heuristics., Prepared in cooperation with Purdue Univ., West Layette, IN, Anteon Corp., Monterey, CA, Univ. of Southern California, Dept. of EE Systems, Los Angeles, CA and NOEMIX Inc. , San Diego, CA.

The Management System for Heterogeneous Networks (MSHN) is a resource management system for use in heterogeneous environments. This paper describes the goals of MSHN, its srchitecture, and both completed and ongoing research experiments. MSHN's main goal is to determine the best way to support the execution of many different applications, each with its own quality of service (QoS) requirements, in an distributed, heterogeneous environment. MSHN's architecture consists of seven distributed, potentially replicated components that communicate with one another using CORBA (Common Object Request Broker Architecture). MSHN's experimental investigations include: (1) the accurate, transparent determination of the end-to-end status of resources; (2) the identification of optimization criteria and how non-determinanism and the granularity of models affect the performance of various scheduling heuristics that optimize those criteria; (3) the determination of how security should be incorporated between components as well as how to account for security as a QoS attribute; and (4) the identification of problems inherent in application and systems characterization.

The Management System for Heterogeneous Networks (MSHN) is a resource management system for use in heterogeneous environments. This paper describes the goals of MSHN, its architecture, and both completed and ongoing research experiments. MSHN's main goal is to determine the best way to support the execution of many different applications, each with its own quality of service (QoS) requirements, in a distributed, heterogeneous environment. MSHN's architecture consists of seven distributed, potentially replicated components that communicate with one another using CORBA (Common Object Request Broker Architecture). MSHN's experimental investigations include: (1) the accurate, transparent determination of the end-to-end status of resources; (2) the identification of optimization criteria and how non-determinism and the granularity of models affect the performance of various scheduling heuristics that optimize those criteria; (3) the determination of how security should be incorporated between components as well as how to account for security as a QoS attribute; and (4) the identification of problems inherent in application and system characterization.

In a distributed heterogeneous computing environment, users' tasks are allocated resources to simultaneously satisfy, to varying degrees, the tasks' different, and possibly conflicting, quality of service (QoS) requirements. When the total demand placed on system resources by the tasks, for a given interval of time, exceeds the resources available, some tasks will receive degraded service or no service at all. One part of a measure to quantify the success of a resource management system (RMS) in such a distributed environment is the collective value of the tasks completed during an interval of time, as perceived by the user, application, or policy maker. The Flexible Integrated System Capability (FISC) ratio introduced here is a measure for quantifying this collective value. The FISC ratio is a multi-dimensional measure, and may include priorities, versions of a task or data, deadlines, situational mode, security, application- and domainspecific QoS, and dependencies. In addition to being used for evaluating and comparing RMSs, the FISC ratio can be incorporated as part of the objective function in a system's scheduling heuristics.