Samsung XPR series is ideal for a wide range of outdoor applications, providing higher reliability and exceptional image quality even in the toughest environment. Let our expertise help you with your next LED project.
Learn more: http://smsng.co/xpr... Read More إقرأ المزيد | Share it now!

UK railway operator keeps mobile initiative on track with complete Samsung solution, including Knox configure, Knox E-FOTA and Managed Service.... Read More إقرأ المزيد | Share it now!

Samsung helps Madeira schools improve classroom interaction and student success with tablets managed by Knox Manage.... Read More إقرأ المزيد | Share it now!

#SAIF #SamsungAIForum... Read More إقرأ المزيد | Share it now!

Generative Adversarial Networks (GANs) are a popular generative modelling approach known for producing appealing samples, but their theoretical properties are not yet fully understood, and they are notably difficult to train. In the first part of this talk, I will provide some insights on why GANs are a more meaningful framework to model high dimensional data like images than the more traditional maximum likelihood approach, interpreting them as “parametric adversarial divergences” and rooting the analysis with statistical decision theory. In the second part of the talk, I will address the difficulty of training GANs from the optimization perspective by importing tools from the mathematical programming literature. I will survey the “variational inequality” framework which contains most formulations of GANs introduced so far, and present theoretical and empirical results on adapting the standard methods (such as the extragradient method) from this literature to the training of GANs.... Read More إقرأ المزيد | Share it now!

Automatic text summarization is an important tool for enhancing users’ ability to make decisions in the face of overwhelming amounts of data. Key to making this technology useful and practical is to have high-performing systems that work on a variety of texts and settings. However, existing systems are usually developed and tested on standard research benchmarks based on news texts. In this talk, I discuss how current systems exploit biases in these benchmark tasks in order to perform well without deeply understanding the contents of the input. In particular, they heavily exploit the fact that important sentences tend to appear near the beginning of news articles. I present our lab’s extractive summarization system, BanditSum, which frames summarization as a contextual bandit problem, and our efforts to induce BanditSum to focus on both the position of a sentence and its contents in making content selection decisions, leading to improved summarization performance. Next, I argue that effective summarization requires advances in abstractive summarization, which analyzes the contents of the source texts in order to generate novel summary sentences. However, existing datasets do not require or support the learning of the type of reasoning and generalization which would demonstrate abstraction’s utility. I discuss the ongoing work in my lab in this direction, both from the perspective of analyzing and improving existing abstractive approaches, and from the perspective of developing new datasets and tasks in which abstraction is necessary.... Read More إقرأ المزيد | Share it now!

Standard neural sequence generation methods assume a pre-specified generation order, such as left-to-right generation. Despite its wild success in recent years, there’s a lingering question of whether this is necessary and if there is any other way to generate such a sequence in an order automatically learned from data without having to pre-specify it or relying on external tools. I will discuss in this talk three alternatives; parallel decoding, recursive set prediction, and insertion-based generation.... Read More إقرأ المزيد | Share it now!

Learning of layered or “deep” representations has recently enabled low-cost sensors for autonomous vehicles and efficient automated analysis of visual semantics in online media. But these models have typically required prohibitive amounts of training data, and thus may only work well in the environment they have been trained in. I’ll describe recent methods in adversarial adaptive learning that excel when learning across modalities and domains. Further, these models have been unsatisfying in their complexity–with millions of parameters–and their resulting opacity. I’ll report approaches which achieve explainable deep learning models, including both introspective approaches that visualize compositional structure in a deep network, and third-person approaches that can provide a natural language justification for the classification decision of a deep model.... Read More إقرأ المزيد | Share it now!

Humans are much better than current AI systems at generalizing out-of-distribution. What ingredients can bring us closer to that level of competence? We propose 4 ingredients combined: (a) meta-learning (to learn end-to-end to generalize to modified distributions, sampled from a distribution over distributions), (b) designing modular architectures with the property that modules are fairly independent of each other and interacting sparsely while made to be composed in new ways easily, (c) capturing causal structure decomposed into independent mechanisms so as to correctly infer the effect of interventions by agents which modify the data distribution, and (d) building better and more stable models of the invariant properties of possibly changing environments by taking advantage of the interactions between the learner and its environment to learn semantic high-level variables and their interactions, i.e., adopting an agent perspective on learning to benefit deep learning of abstract representations. The last ingredient implies that learning purely from text is not sufficient and we need to strive for learning agents which build a model of the world, to which linguistic labels can be associated, i.e., performing grounded language learning. Whereas this agent perspective is reminiscent of deep reinforcement learning, the focus is not on how deep learning can help reinforcement learning (as a function approximation black box) but rather how the agent perspective common in reinforcement learning can help deep learning discover better representations of knowledge.... Read More إقرأ المزيد | Share it now!