Our legal question answering system combines legal information retrieval and textual entailment, and we propose a legal question answering system that exploits a deep convolutional neural network. We have evaluated our system using the training data from the competition on legal information extraction/entailment (COLIEE). The competition focuses on the legal information processing related to an...

Spanish is the third-most used language on the Internet, after English and Chinese, with a total of 7.7% of Internet users (more than 277 million of users) and a huge users growth of more than 1,400%. However, most work on sentiment analysis has focused on English. This paper describes a deep learning system for Spanish sentiment analysis. To the best of our knowledge, this is the first work th...

Nowadays, neural networks play an important role in the task of relation classification. By designing different neural architectures, researchers have improved the performance to a large extent, compared with traditional methods. However, existing neural networks for relation classification are usually of shallow architectures (e.g., one-layer convolution neural networks or recurrent networks)....

HTTP injection attacks are well known cyber security threats with fatal consequences. These initiated by malicious entities (either human or computer) send dangerous unsafe contents into the parameters of requests. Combatting demands for development Web Intrusion Detection Systems (WIDS). Common WIDS follow a rule-based approach signature-based which have common problem high false-positive rate...

Generative networks are effective tools for digital materials (DM) inverse design. However, the optimization performance of generative is restricted by increasing discrepancy between optimized input and prescribed domain as design loop increases. Herein, a correction technique incorporated into deep neural network (GDNN) convolutional (GDCNN). The performed pulling machine learning (ML)-optimiz...

Deep neural networks frequently require the careful tuning of model hyperparameters. Recent research has shown that automated early termination of underperformance runs can speed up hyperparameter searches. However, these studies have used only learning curve for predicting the eventual model performance. In this study, we propose using weight features extracted from network weights at an early...

Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the robustness of convolutional neural networks to perturbations to the internal weights and architecture of the network itself. We show that convolutional networks are surprisingly r...