Adversarial learning is one of the most successful approaches to modelling high-dimensional probability distributions from data. The quantum computing community has recently begun to generalize this idea and to look for potential applications. In this work, we derive an adversarial algorithm for the problem of approximating an unknown quantum pure state. Although this could be done on error-corrected quantum computers, the adversarial formulation enables us to execute the algorithm on near-term quantum computers. Two ansatz circuits are optimized in tandem: One tries to approximate the target state, the other tries to distinguish between target and approximated state. Supported by numerical simulations, we show that resilient backpropagation algorithms perform remarkably well in optimizing the two circuits. We use the bipartite entanglement entropy to design an efficient heuristic for the stopping criteria. Our approach may find application in quantum state tomography.

Batch Normalization (BN) is a common technique used both in discriminative and generative networks in order to speed-up training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks for representing class-specific information using conditional Batch Normalization (cBN). In this paper we propose to generalize both BN and cBN using a Whitening and Coloring based batch normalization. We apply our method to conditional and unconditional image generation tasks and we show that replacing the BN feature standardization and scaling with our feature whitening and coloring improves the final qualitative results and the training speed. We test our approach on different datasets and we show a consistent improvement orthogonal to different GAN frameworks. Our CIFAR-10 supervised results are higher than all previous works on this dataset.

We introduce a new feature map for barcodes that arise in persistent homology computation. The main idea is to first realize each barcode as a path in a convenient vector space, and to then compute its path signature which takes values in the tensor algebra of that vector space. The composition of these two operations - barcode to path, path to tensor series - results in a feature map that has several desirable properties for statistical learning, such as universality and characteristicness, and achieves state-of-the-art results on common classification benchmarks.

Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of learning control policies for unknown linear dynamical systems so as to maximize a quadratic reward function. We present a method to optimize the expected value of the reward over the posterior distribution of the unknown system parameters, given data. The algorithm involves sequential convex programing, and enjoys reliable local convergence and robust stability guarantees. Numerical simulations and stabilization of a real-world inverted pendulum are used to demonstrate the approach, with strong performance and robustness properties observed in both.

Deep learning has been widely accepted as a promising solution for medical image segmentation, given a sufficiently large representative dataset of images with corresponding annotations. With ever increasing amounts of annotated medical datasets, it is infeasible to train a learning method always with all data from scratch. This is also doomed to hit computational limits, e.g., memory or runtime feasible for training. Incremental learning can be a potential solution, where new information (images or anatomy) is introduced iteratively. Nevertheless, for the preservation of the collective information, it is essential to keep some "important" (i.e., representative) images and annotations from the past, while adding new information. In this paper, we introduce a framework for applying incremental learning for segmentation and propose novel methods for selecting representative data therein. We comparatively evaluate our methods in different scenarios using MR images and validate the increased learning capacity with using our methods.

In recent years an increasing number of researchers and practitioners have been suggesting algorithms for large-scale neural network architecture search: genetic algorithms, reinforcement learning, learning curve extrapolation, and accuracy predictors. None of them, however, demonstrated high-performance without training new experiments in the presence of unseen datasets. We propose a new deep neural network accuracy predictor, that estimates in fractions of a second classification performance for unseen input datasets, without training. In contrast to previously proposed approaches, our prediction is not only calibrated on the topological network information, but also on the characterization of the dataset-difficulty which allows us to re-tune the prediction without any training. Our predictor achieves a performance which exceeds 100 networks per second on a single GPU, thus creating the opportunity to perform large-scale architecture search within a few minutes. We present results of two searches performed in 400 seconds on a single GPU. Our best discovered networks reach 93.67% accuracy for CIFAR-10 and 81.01% for CIFAR-100, verified by training. These networks are performance competitive with other automatically discovered state-of-the-art networks however we only needed a small fraction of the time to solution and computational resources.

We propose NetGAN - the first implicit generative model for graphs able to mimic real-world networks. We pose the problem of graph generation as learning the distribution of biased random walks over the input graph. The proposed model is based on a stochastic neural network that generates discrete output samples and is trained using the Wasserstein GAN objective. NetGAN is able to produce graphs that exhibit well-known network patterns without explicitly specifying them in the model definition. At the same time, our model exhibits strong generalization properties, as highlighted by its competitive link prediction performance, despite not being trained specifically for this task. Being the first approach to combine both of these desirable properties, Net-GAN opens exciting avenues for further research.

Matt Pickett, Founder of the nonprofit, Oceans Unmanned, holds a DJI drone that will assist in the disentangling of humpback whales in Hawaii. In April 2018, the Washington Post reported that a sperm whale was found dead off the coast of Spain with 64 pounds of plastic debris in his stomach. Each fall, pods of endangered humpback whales numbering around 10,000, make their 3,000-mile journey towards Hawaii to winter over in the warm waters of the National Oceanic and Atmospheric Administration's (NOAA) Hawaiian Islands Humpback Whale National Marine Sanctuary. Along the way, these whales encounter man-made environmental hazards such as fishing gear lines and marine debris which become tangled around the whale's body and fins cutting into the whale's flesh and sometimes even dragging them down to the bottom of the sea where they drown. The work to untangle a 45-foot, 40-ton whale is dangerous to both the rescue team and the whale.

The startup that claims responsibility for the conception of 10,000 babies has raised $30million in Series B fundraising to expand into other aspects of female health. The Ava bracelet is a $249 wearable device with an accompanying app that helps women track their fertility cycles. Designed to be worn overnight, the technology measures nine physiological variables to monitor a woman's fertility or pregnancy. The funding comes from previous unnamed investors as well as new European venture capital participants Btov and SVC. In late 2016, Ava raised a Series A round of $9.7million in funding.

Over years, a crucial part of data-gathering behavior has revolved around what other people think. With the constantly growing popularity and availability of opinion-driven resources such as personal blogs and online review sites, new challenges and opportunities are emerging as people have started using advanced technologies to make decisions now. Sentiment analysis or opinion mining, refers to the use of computational linguistics, text analytics and natural language processing to identify and extract information from source materials. Sentiment analysis is considered one of the most popular applications of text analytics. The primary aspect of sentiment analysis includes data analysis on the body of the text for understanding the opinion expressed by it and other key factors comprising modality and mood.