Search

The banking sector is on the eve of a serious transformation and the thrust behind it is artificial intelligence (AI). Novel AI applications have been already proposed to deal with challenges in the areas of credit scoring, risk assessment, client experience and portfolio management. One of the most critical challenges in the aforementioned sector is fraud detection upon streams of transactions. Recently, deep learning models have been introduced to deal with the specific problem in terms of detecting and forecasting possible fraudulent events. The aim is to estimate the unknown distribution of normal/fraudulent transactions and then to identify deviations that may indicate a potential fraud. In this paper, we elaborate on a novel multistage deep learning model that targets to efficiently manage the incoming streams of transactions and detect the fraudulent ones. We propose the use of two autoencoders to perform feature selection and learn the latent data space representation based on a nonlinear optimization model. On the delivered significant features, we subsequently apply a deep convolutional neural network to detect frauds, thus combining two different processing blocks. The adopted combination has the goal of detecting frauds over the exposed latent data representation and not over the initial data. [ABSTRACT FROM AUTHOR]

Nowadays, the increased amount of users’ devices produce huge volumes of data that should be efficiently managed by modern applications. Streams are adopted to deliver data that, usually, are stored into a number of partitions. Splitting the data offers a lot of advantages as applications can process them in parallel, thus, they increase the speed of processing. Progressive analytics are also adopted to deliver partial responses, during processing, thus, saving time in the execution of applications. Data exploration and analytics queries are very significant for future applications. Usually, such queries demand for an ordered set of objects as a response and require intelligent predictive schemes to deliver the responses on top of the partial results retrieved by the distributed data partitions. A finite set of query processors are adopted to produce these partial results. Processors are placed in front of each partition and report progressive analytics to a central entity. In this paper, we envision the query controller (QC) as the central entity that collects progressive analytics and return the final response to users/applications. The QC receives partial ordered sets of objects and aggregates them to derive the final outcome. We focus on a QC that applies time-optimized techniques and aggregation operators to deliver every response, i.e., ordered sets, over streams of partial ordered subsets. We perform a comprehensive performance assessment with synthetic data and report on the performance of the QC. Our experimental evaluation reveals the pros and cons of the proposed model and a comparison assessment places this paper in the respective literature. [ABSTRACT FROM AUTHOR]

Convolution Neural Networks (CNNs) are gaining ground in deep learning and Artificial Intelligence (AI) domains, and they can benefit from rapid prototyping in order to produce efficient and low-power hardware designs. The inference process of a Deep Neural Network (DNN) is considered a computationally intensive process that requires hardware accelerators to operate in real-world scenarios due to the low latency requirements of real-time applications. As a result, High-Level Synthesis (HLS) tools are gaining popularity since they provide attractive ways to reduce design time complexity directly in register transfer level (RTL). In this paper, we implement a MobileNetV2 model using a state-of-the-art HLS tool in order to conduct a design space exploration and to provide insights on complex hardware designs which are tailored for DNN inference. Our goal is to combine design methodologies with sparsification techniques to produce hardware accelerators that achieve comparable error metrics within the same order of magnitude with the corresponding state-of-the-art systems while also significantly reducing the inference latency and resource utilization. Toward this end, we apply sparse matrix techniques on a MobileNetV2 model for efficient data representation, and we evaluate our designs in two different weight pruning approaches. Experimental results are evaluated with respect to the CIFAR-10 data set using several different design methodologies in order to fully explore their effects on the performance of the model under examination. [ABSTRACT FROM AUTHOR]