Random Self-Ensemble (RSE)
Recent studies have revealed the vulnerability of deep neural networks – A small adversarial perturbation that is imperceptible to human can easily make a well-trained deep neural network mis-classify. This makes it unsafe to apply neural networks in security-critical applications. In this paper, we propose a new defensive algorithm called Random Self-Ensemble (RSE) by combining two important concepts: ${\bf randomness}$ and ${\bf ensemble}$. To protect a targeted model, RSE adds random noise layers to the neural network to prevent from state-of-the-art gradient-based attacks, and ensembles the prediction over random noises to stabilize the performance. We show that our algorithm is equivalent to ensemble an infinite number of noisy models $f_\epsilon$ without any additional memory overhead, and the proposed training procedure based on noisy stochastic gradient descent can ensure the ensemble model has good predictive capability. Our algorithm significantly outperforms previous defense techniques on real datasets. For instance, on CIFAR-10 with VGG network (which has $92\%$ accuracy without any attack), under the state-of-the-art C&W attack within a certain distortion tolerance, the accuracy of unprotected model drops to less than $10\%$, the best previous defense technique has $48\%$ accuracy, while our method still has $86\%$ prediction accuracy under the same level of attack. Finally, our method is simple and easy to integrate into any neural network. …

Rufus
Rufus turns your website into a customer conversation. We use a proprietary blend of curated language sets and state of the art machine learning to engage customers more intelligently than ever. Nobody understands your customers like you do, that’s why we work directly with you to create a custom solution that fits your needs. Let Rufus engage your passing web visitors and turn them into highly qualified leads. Rufus can also handle your tier 1 and 2 support cases, and ties into your existing customer support tracking software. Think of Rufus as a customer relationship manager that can chat with 1000 people at a time. It will know every single aspect or detail about your product or service and deliver it’s messaging in a fun and extremely engaging manner. With custom language sets and purposeful personas, that match your brand and your targeted audience – Rufus will truly become your company’s new best friend …

Hierarchical Deep Learning for Text Classification (HDLTex)
The continually increasing number of documents produced each year necessitates ever improving information processing methods for searching, retrieving, and organizing text. Central to these information processing methods is document classification, which has become an important application for supervised learning. Recently the performance of these traditional classifiers has degraded as the number of documents has increased. This is because along with this growth in the number of documents has come an increase in the number of categories. This paper approaches this problem differently from current document classification methods that view the problem as multi-class classification. Instead we perform hierarchical classification using an approach we call Hierarchical Deep Learning for Text classification (HDLTex). HDLTex employs stacks of deep learning architectures to provide specialized understanding at each level of the document hierarchy. …