In the proposed thesis, we study a special class of belief networks which contain both probabilistic and deterministic information. Deterministic information occurs as zero probabilities in the belief network. A majority of the work in the belief network community (see for example papers in conferences like UAI, AAAI, IJCAI and NIPS) addresses probabilistic inference tasks under the assumption ...

Clustering and visualization of large text document collections aids in browsing, navigation, and information retrieval. We present a document clustering and visualization method based on Latent Dirichlet Allocation and self-organizing maps (LDA-SOM). LDA-SOM clusters documents based on topical content and renders clusters in an intuitive twodimensional format. Document topics are inferred usin...

Convolutional neural networks have demonstrated their powerful ability on various tasks in recent years. However, they are extremely vulnerable to adversarial examples. I.e., clean images, with imperceptible perturbations added, can easily cause convolutional neural networks to fail. In this paper, we propose to utilize randomization to mitigate adversarial effects. Specifically, we use two ran...

The principle of peer review is central to the evaluation of research, by ensuring that only high-quality items are funded or published. But peer review has also received criticism, as the selection of reviewers may introduce biases in the system. In 2014, the organizers of the “Neural Information Processing Systems” conference conducted an experiment in which 10% of submitted manuscripts (166 ...

Figure 1: Illustration of stimuli used during test trials. Functions are reconstructed from human clicked locations. F18 is the Dirac function with a non-zero element at-270.

We present a ray-tracing study of the propagation of PC 3 Alfven mode waves originating at the dayside magnetopause. This study reveals interesting features of a magnetospheric filter effect for these waves. PC 3 Alfven mode waves cannot penetrate to low Earth altitudes unless the wave frequency is below approximately 30 mHz. Configurations of the dispersion curves and the refractive index show...

This project is one of the research topics in Professor William Dally’s group. In this project, we developed a pruning based method to learn both weights and connections for Long Short Term Memory (LSTM). In this method, we discard the unimportant connections in a pretrained LSTM, and make the weight matrix sparse. Then, we retrain the remaining model. After we remaining model is converge, we p...

BACKGROUND In neonatology the role of chest physiotherapy is still uncertain because of the controversial outcomes. METHODS The aim of this study was to test the applicability in preterm infants of 'reflex rolling', from the Vojta method, in preterm neonates with lung pathology, with particular attention to the effects on blood gases and oxygen saturation, on the spontaneous breathing, on the...

Major intrinsic proteins (MIPs), commonly known as aquaporins, transport not only water in plants but also other substrates of physiological significance and heavy metals. In most of the higher plants, MIPs are divided into five subfamilies (PIPs, TIPs, NIPs, SIPs and XIPs). Herein, we identified 68, 42, 38 and 28 full-length MIPs, respectively in the genomes of four monocot grass plants, speci...

Though convolutional neural networks have achieved stateof-the-art performance on various vision tasks, they are extremely vulnerable to adversarial examples, which are obtained by adding humanimperceptible perturbations to the original images. Adversarial examples can thus be used as an useful tool to evaluate and select the most robust models in safety-critical applications. However, most of ...