Controlling Canard Cycles. (arXiv:1911.11861v1 [math.DS])

Canard cycles are periodic orbits that appear as special solutions of fast-slow systems (or singularly perturbed Ordinary Differential Equations). It is well known that canard cycles are difficult to detect, hard to reproduce numerically, and that they are sensible to exponentially small changes in parameters. In this paper we combine techniques from geometric singular perturbation…

An Adaptive View of Adversarial Robustness from Test-time Smoothing Defense. (arXiv:1911.11881v1 [cs.LG])

The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an adaptive view of the issue via evaluating various test-time smoothing defense against white-box untargeted adversarial examples. Through controlled experiments with pretrained ResNet-152 on ImageNet,…

Explaining Models by Propagating Shapley Values of Local Components. (arXiv:1911.11888v1 [cs.LG])

In healthcare, making the best possible predictions with complex models (e.g., neural networks, ensembles/stacks of different models) can impact patient welfare. In order to make these complex models explainable, we present DeepSHAP for mixed model types, a framework for layer wise propagation of Shapley values that builds upon DeepLIFT (an existing approach for explaining neural…

K-MACE and Kernel K-MACE Clustering. (arXiv:1911.11890v1 [math.ST])

Determining the correct number of clusters (CNC) is an important task in data clustering and has a critical effect on finalizing the partitioning results. K-means is one of the popular methods of clustering that requires CNC. Validity index methods use an additional optimization procedure to estimate the CNC for K-means. We propose an alternative validity…

Single Sample Feature Importance: An Interpretable Algorithm for Low-Level Feature Analysis. (arXiv:1911.11901v1 [cs.LG])

Have you ever wondered how your feature space is impacting the prediction of a specific sample in your dataset? In this paper, we introduce Single Sample Feature Importance (SSFI), which is an interpretable feature importance algorithm that allows for the identification of the most important features that contribute to the prediction of a single sample.…

Novelty Detection Via Blurring. (arXiv:1911.11943v1 [cs.LG])

Conventional out-of-distribution (OOD) detection schemes based on variational autoencoder or Random Network Distillation (RND) have been observed to assign lower uncertainty to the OOD than the target distribution. In this work, we discover that such conventional novelty detection schemes are also vulnerable to the blurred images. Based on the observation, we construct a novel RND-based…

An Efficient Machine Learning-based Elderly Fall Detection Algorithm. (arXiv:1911.11976v1 [cs.LG])

Falling is a commonly occurring mishap with elderly people, which may cause serious injuries. Thus, rapid fall detection is very important in order to mitigate the severe effects of fall among the elderly people. Many fall monitoring systems based on the accelerometer have been proposed for the fall detection. However, many of them mistakenly identify…

BLAS: Broadcast Relative Localization and Clock Synchronization for Dynamic Dense Multi-Agent Systems. (arXiv:1911.11995v1 [cs.RO])

The spatiotemporal information plays crucial roles in a multi-agent system (MAS). However, for a highly dynamic and dense MAS in unknown environments, estimating its spatiotemporal states is a difficult problem. In this paper, we present BLAS: a wireless broadcast relative localization and clock synchronization system to address these challenges. Our BLAS system exploits a broadcast…