Search

It has been empirically observed that the flatness of minima obtained from training deep networks seems to correlate with better generalization. However, for deep networks with positively homogeneous activations, most measures of flatness are not invariant to rescaling of the network parameters. This means that the measure of flatness can be made as small or as large as possible through rescaling, rendering the quantitative measures meaningless. In this paper we show that for deep networks with positively homogenous activations, these rescalings constitute equivalence relations, and that these equivalence relations induce a quotient manifold structure in the parameter space. Using an appropriate Riemannian metric, we propose a Hessian-based measure for flatness that is invariant to rescaling and perform simulations to empirically verify our claim. Finally we perform experiments to verify that our flatness measure correlates with generalization by using minibatch stochastic gradient descent with different batch sizes to find deep network minima with different generalization properties.

Modern ultra-wideband (UWB) radar systems transmit a wide range of frequencies, spanning hundreds of MHz to a few GHz, to achieve improved penetration depth and narrower pulse width. A common challenge faced is the presence of other commercial transmission equipment operating in the same band, causing radio frequency interference (RFI). To overcome this RFI issue, radar systems have been developed to either avoid operating in bands with RFI or suppress the RFI after reception. In this work, we examine both families of operation and demonstrate that 1D convolutional neural networks based on the UNet architecture can provide powerful signal enhancement capabilities on raw UWB radar data. The model is trained purely on simulated data and translated to real UWB data, achieving impressive results compared to traditional sparse-recovery baseline algorithms.

Discovering the underlying dynamics leading up to an industrial asset failure is an important problem to be solved for successful development of Predictive Maintenance techniques. Existing work has largely focused on building complex ML/AI models for developing Predictive Maintenance solution patterns, but has largely avoided developing methods to explain the underlying failure dynamics. In this paper, we use an old but significantly improved change-pattern based technique to analyze IoT sensor data and failure information to generate useful and interpretable failure-centric insight. We discuss a solution pattern that we call ChieF, which when applied on multi-variate time series datasets, discover the leading failure indicators, generate associative patterns among multiple features, and output temporal dynamics of changes. Experimental analysis of ChieF on four datasets uncovers insights that may be valuable for predictive maintenance.

Conventional image discrimination tasks are performed on fully observed images. In challenging real imaging scenarios, where sensing systems are energy demanding or need to operate with limited bandwidth and exposure-time budgets, or defective pixels, where the data collected often suffers from missing information, and this makes the task extremely hard. In this paper, we leverage Convolutional Neural Networks (CNNs) to extract information from partially observed images. While pre-trained CNNs fail significantly even with such a small percentage of the input missing, our proposed framework demonstrates the ability to overcome it after training on fully-observed and partially-observed images at a few observation ratios. We demonstrate that our method is indeed reconstruction-free, retraining-free and generalizable to previously untrained-on observation ratios and it remains effective in two different visual tasks – image classification and object detection. Our framework performs well even for test images with only 10% of pixels available and outperforms the reconstruct-then-classify pipeline in these challenging scenarios for small observation fractions.

In this paper we study the unmixing problem which aims to separate a set of structured signals from their superposition. In this paper, we consider the scenario in which the mixture is observed via nonlinear compressive measurements. We present a fast, robust, greedy algorithm called Unmixing Matching Pursuit (UnmixMP) to solve this problem. We prove rigorously that the algorithm can recover the constituents from their noisy nonlinear compressive measurements with arbitrarily small error. We compare our algorithm to the Demixing with Hard Thresholding (DHT) algorithm [1], in a number of experiments on synthetic and real data.