Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs. However, while complex symbolic datasets often exhibit a latent hierarchical structure, state-of-the-art methods typically learn embeddings in Euclidean vector spaces, which do not account for this property. For this purpose, we introduce a new approach for learning hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an n-dimensional Poincar\'e ball. Due to the underlying hyperbolic geometry, this allows us to learn parsimonious representations of symbolic data by simultaneously capturing hierarchy and similarity. We introduce an efficient algorithm to learn the embeddings based on Riemannian optimization and show experimentally that Poincar\'e embeddings outperform Euclidean embeddings significantly on data with latent hierarchies, both in terms of representation capacity and in terms of generalization ability.

Autonomous systems can substantially enhance a human's efficiency and effectiveness in complex environments. Machines, however, are often unable to observe the preferences of the humans that they serve. Despite the fact that the human's and machine's objectives are aligned, asymmetric information, along with heterogeneous sensitivities to risk by the human and machine, make their joint optimization process a game with strategic interactions. We propose a framework based on risk-sensitive dynamic games; the human seeks to optimize her risk-sensitive criterion according to her true preferences, while the machine seeks to adaptively learn the human's preferences and at the same time provide a good service to the human. We develop a class of performance measures for the proposed framework based on the concept of regret. We then evaluate their dependence on the risk-sensitivity and the degree of uncertainty. We present applications of our framework to self-driving taxis, and robo-financial advising.

It is difficult to train a personalized task-oriented dialogue system because the data collected from each individual is often insufficient. Personalized dialogue systems trained on a small dataset can overfit and make it difficult to adapt to different user needs. One way to solve this problem is to consider a collection of multiple users' data as a source domain and an individual user's data as a target domain, and to perform a transfer learning from the source to the target domain. By following this idea, we propose "PETAL"(PErsonalized Task-oriented diALogue), a transfer-learning framework based on POMDP to learn a personalized dialogue system. The system first learns common dialogue knowledge from the source domain and then adapts this knowledge to the target user. This framework can avoid the negative transfer problem by considering differences between source and target users. The policy in the personalized POMDP can learn to choose different actions appropriately for different users. Experimental results on a real-world coffee-shopping data and simulation data show that our personalized dialogue system can choose different optimal actions for different users, and thus effectively improve the dialogue quality under the personalized setting.

Data quantization learns encoding results of data with certain requirements, and provides a broad perspective of many real-world applications to data handling. Nevertheless, the results of encoder is usually limited to multivariate inputs with the random mapping, and side information of binary codes are hardly to mostly depict the original data patterns as possible. In the literature, cosine based random quantization has attracted much attentions due to its intrinsic bounded results. Nevertheless, it usually suffers from the uncertain outputs, and information of original data fails to be fully preserved in the reduced codes. In this work, a novel binary embedding method, termed adaptive training quantization (ATQ), is proposed to learn the ideal transform of random encoder, where the limitation of cosine random mapping is tackled. As an adaptive learning idea, the reduced mapping is adaptively calculated with idea of data group, while the bias of random transform is to be improved to hold most matching information. Experimental results show that the proposed method is able to obtain outstanding performance compared with other random quantization methods.

The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space. We specifically study the topology of classification regions created by deep networks, as well as their associated decision boundary. Through a systematic empirical investigation, we show that state-of-the-art deep nets learn connected classification regions, and that the decision boundary in the vicinity of datapoints is flat along most directions. We further draw an essential connection between two seemingly unrelated properties of deep networks: their sensitivity to additive perturbations in the inputs, and the curvature of their decision boundary. The directions where the decision boundary is curved in fact remarkably characterize the directions to which the classifier is the most vulnerable. We finally leverage a fundamental asymmetry in the curvature of the decision boundary of deep nets, and propose a method to discriminate between original images, and images perturbed with small adversarial examples. We show the effectiveness of this purely geometric approach for detecting small adversarial perturbations in images, and for recovering the labels of perturbed images.

Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclassified by such classifiers. In this paper, we propose the first quantitative analysis of the robustness of classifiers to universal perturbations, and draw a formal link between the robustness to universal perturbations, and the geometry of the decision boundary. Specifically, we establish theoretical bounds on the robustness of classifiers under two decision boundary models (flat and curved models). We show in particular that the robustness of deep networks to universal perturbations is driven by a key property of their curvature: there exists shared directions along which the decision boundary of deep networks is systematically positively curved. Under such conditions, we prove the existence of small universal perturbations. Our analysis further provides a novel geometric method for computing universal perturbations, in addition to explaining their properties.

BEIJING, May 25, 2017 (GLOBE NEWSWIRE) -- Gridsum Holding Inc. ("Gridsum" or the "Company") (NASDAQ:GSUM), a leading provider of cloud-based big-data analytics, machine learning and AI solutions in China, today announced that, as a part of its strategic evolution, it has consolidated all of its artificial intelligence ("AI") activities strategically, technically and organizationally into a new division called the Gridsum Prophet. Gridsum is a first mover in China in big data intelligence. Since 2005, the Company has utilized a distributed big-data computing architecture, developed and implemented sophisticated natural language processing ("NLP"), and leveraged machine learning directed toward large enterprise clients. During that time, from serving large enterprise customers, the Company has accumulated deep domain knowledge and expertise as well as a massive amount of data that fuels its machine learning algorithms. Since this early inception, the Company has continued to stay at the forefront through focus and investment, hiring and training extraordinary engineers and architects and, importantly, playing an active and leading role in the AI academic and developer communities.

NVIDIA Volta Architecture – Volta is the world's most powerful GPU computing architecture, created to drive the next wave of advancement in AI and high performance computing. The first Volta-based processor is the Tesla V100 data center GPU, which brings extraordinary speed and scalability for AI inferencing and training, as well as for accelerating HPC and graphics workloads. New Volta-Based DGX Systems -- The company announced a new lineup of NVIDIA DGX AI supercomputers with unmatched computing performance. Using NVIDIA Tesla V100 data center GPUs based on the new Volta architecture and a fully optimized AI software package, the systems deliver groundbreaking AI computing power three times faster than the prior DGX generation, providing the performance of up to 800 CPUs in a single system. NVIDIA GPU Cloud Platform – NVIDIA GPU Cloud (NGC) is a cloud-based platform that will give developers convenient access -- via their PC, DGX system or the cloud -- to a comprehensive software suite for harnessing the transformative powers of AI.

Dr. Andrea Trevino presents a beginner introduction to the widely-used K-means clustering algorithm in this tutorial. K-means clustering is a type of unsupervised learning, which is used when the resulting categories or groups in the data are unknown. This algorithm finds the groups that exist organically in the data and the results allow the user to label new data quickly. Clustering, in general, is a key tool for understanding your data. This algorithm can be used in a number of applications, including behavioral segmentation, inventory categorization, sorting sensor measurements, and detecting bots or anomalies, to name a few. This tutorial covers the iterative algorithm that determines the clusters and works through a delivery fleet data example in Python.

Sogaard said that these deep learning techniques have shown promise in finding disease patterns across large groups of people, but the ultimate goal is to eventually help individual patients. Sogaard believes a handful of cloud computing providers will have AI technologies that drug companies could eventually use for research and development. Federal regulations have not yet caught up to the rapid pace of innovation that could one day help predict and diagnose diseases using a combination of genomic, protein, and medical imaging data. But Sogaard is hopeful, and based on Pfizer's meetings with regulators, he believes the Federal Drug Administration is "open-minded" to AI-assisted medical treatment.