simultaneous Coherent Structure Coloring (sCSC) google
Existing methods that aim to automatically cluster data into physically meaningful subsets typically require assumptions regarding the number, size, or shape of the coherent subgroups. We present a new method, simultaneous Coherent Structure Coloring (sCSC), which accomplishes the task of unsupervised clustering without a priori guidance regarding the underlying structure of the data. To illustrate the versatility of the method, we apply it to frontier physics problems at vastly different temporal and spatial scales: in a theoretical model of geophysical fluid dynamics, in laboratory measurements of vortex ring formation and entrainment, and in atomistic simulation of the Protein G system. The theoretical flow involves sparse sampling of non-equilibrium dynamics, where this new technique can find and characterize the structures that govern fluid transport using two orders of magnitude less data than required by existing methods. Application of the method to empirical measurements of vortex formation leads to the discovery of a well defined region in which vortex ring entrainment occurs, with potential implications ranging from flow control to cardiovascular diagnostics. Finally, the protein folding example demonstrates a data-rich application governed by equilibrium dynamics, where the technique in this manuscript automatically discovers the hierarchy of distinct processes that govern protein folding and clusters protein configurations accordingly. We anticipate straightforward translation to many other fields where existing analysis tools, such as k-means and traditional hierarchical clustering, require ad hoc assumptions on the data structure or lack the interpretability of the present method. The method is also potentially generalizable to fields where the underlying processes are less accessible, such as genomics and neuroscience. …

Stochastic Adaptive Neural Architecture Search (SANAS) google
The problem of keyword spotting i.e. identifying keywords in a real-time audio stream is mainly solved by applying a neural network over successive sliding windows. Due to the difficulty of the task, baseline models are usually large, resulting in a high computational cost and energy consumption level. We propose a new method called SANAS (Stochastic Adaptive Neural Architecture Search) which is able to adapt the architecture of the neural network on-the-fly at inference time such that small architectures will be used when the stream is easy to process (silence, low noise, …) and bigger networks will be used when the task becomes more difficult. We show that this adaptive model can be learned end-to-end by optimizing a trade-off between the prediction performance and the average computational cost per unit of time. Experiments on the Speech Commands dataset show that this approach leads to a high recognition level while being much faster (and/or energy saving) than classical approaches where the network architecture is static. …

CornerNet google
We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detecting objects as paired keypoints, we eliminate the need for designing a set of anchor boxes commonly used in prior single-stage detectors. In addition to our novel formulation, we introduce corner pooling, a new type of pooling layer that helps the network better localize corners. Experiments show that CornerNet achieves a 42.1% AP on MS COCO, outperforming all existing one-stage detectors. …

Advertisements