Search for: All records

Supervised learning method requires a large volume of annotated datasets. Collecting such datasets is time-consuming and expensive. Until now, very few annotated COVID19 imaging datasets are available. Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method should be sensitive enough to detect deviation from normal-appearing tissue of each anatomical region; here, anatomy is the context. We introduce a novel approach with two levels of self-supervised representation learning objectives: one on the regional anatomical level and another on the patient level. We use graph neural networks to incorporate the relationship between different anatomical regions. The structure of the graph is informed by anatomical correspondences between each patient and an anatomical atlas. In addition, the graph representation has the advantage of handling any arbitrarily sized image in full resolution. Experiments on large-scale Computer Tomography (CT) datasets of lung images show that our approach compares favorably to baseline methods that do not account for the context. We use the learned embedding to quantify the clinical progression of COVID-19 and show that our method generalizes well to COVID-19 patients from different hospitals. Qualitative results suggest that our model can identify clinically relevant regions in the images. 

Single-photon sources are a fundamental resource in quantum optics and quantum information science. Photons with differing spectral and temporal shapes do not interfere well and inhibit the performance of quantum applications such as linear optics quantum computing, boson sampling, and quantum networks. Indistinguishability and purity of photons emitted from different sources are crucial properties for many quantum applications. The ability to determine the state of single-photon sources therefore provides a means to assess their quality, compare different sources, and provide feedback for source tuning. Here, we propose and demonstrate a single-configuration experimental method enabling complete characterization of the spectral-temporal state of a pulsed single-photon source having both pure and mixed states. The method involves interference of the unknown single-photon source with a reference at a balanced beam splitter followed by frequency-resolved coincidence detection at the outputs. Fourier analysis of the joint-spectral two-photon interference pattern reveals the density matrix of the single-photon source in the frequency basis. We present an experimental realization of this method for pure and mixed state pulsed single-photon sources.

 

The learning data requirements are analyzed for the construction of stealth attacks in state estimation. In particular, the training data set is used to compute a sample covariance matrix that results in a random matrix with a Wishart distribution. The ergodic attack performance is defined as the average attack performance obtained by taking the expectation with respect to the distribution of the training data set. The impact of the training data size on the ergodic attack performance is characterized by proposing an upper bound for the performance. Simulations on the IEEE 30-Bus test system show that the proposed bound is tight in practical settings.