Ultrasound (US) imaging is based on the time-reversal principle, in which individual channel RF measurements are back-propagated and accumulated to form an image after applying specific delays. While this time reversal is usually implemented as a delay-and-sum (DAS) beamformer, the image quality quickly degrades as the number of measurement channels decreases. To address this problem, various types of adaptive beamforming techniques have been proposed using predefined models of the signals. However, the performance of these adaptive beamforming approaches degrade when the underlying model is not sufficiently accurate. Here, we demonstrate for the first time that a single universal deep beamformer trained using a purely data-driven way can generate significantly improved images over widely varying aperture and channel subsampling patterns. In particular, we design an end-to-end deep learning framework that can directly process sub-sampled RF data acquired at different subsampling rate and detector configuration to generate high quality ultrasound images using a single beamformer. Experimental results using B-mode focused ultrasound confirm the efficacy of the proposed methods.

Community detection was a hot topic on network analysis, where the main aim is to perform unsupervised learning or clustering in networks. Recently, semi-supervised learning has received increasing attention among researchers. In this paper, we propose a new algorithm, called weighted inverse Laplacian (WIL), for predicting labels in partially labeled networks. The idea comes from the first hitting time in random walk, and it also has nice explanations both in information propagation and the regularization framework. We propose a partially labeled degree-corrected block model (pDCBM) to describe the generation of partially labeled networks. We show that WIL ensures the misclassification rate is of order $O(\frac{1}{d})$ for the pDCBM with average degree $d=\Omega(\log n),$ and that it can handle situations with greater unbalanced than traditional Laplacian methods. WIL outperforms other state-of-the-art methods in most of our simulations and real datasets, especially in unbalanced networks and heterogeneous networks.

If you want to tell people the truth, make them laugh, otherwise they'll kill you. (source unclear) Machine learning and deep learning are the technologies of the day for developing intelligent automatic systems. However, a key hurdle for progress in the field is the literature itself: we often encounter papers that report results that are difficult to reconstruct or reproduce, results that mis-represent the performance of the system, or contain other biases that limit their validity. In this semi-humorous article, we discuss issues that arise in running and reporting results of machine learning experiments. The purpose of the article is to provide a list of watch out points for researchers to be aware of when developing machine learning models or writing and reviewing machine learning papers.

In this paper, a unified susceptible-exposed-infected-susceptible-aware (SEIS-A) framework is proposed to combine epidemic spreading with individuals' on-line self-consultation behaviors. An epidemic spreading prediction model is established based on the SEIS-A framework. The prediction process contains two phases. In phase I, the time series data of disease density are decomposed through the empirical mode decomposition (EMD) method to obtain the intrinsic mode functions (IMFs). In phase II, the ensemble learning techniques which use the on-line query data as an additional input are applied to these IMFs. Finally, experiments for prediction of weekly consultation rates of Hand-foot-and-mouth disease (HFMD) in Hong Kong are conducted to validate the effectiveness of the proposed method. The main advantage of this method is that it outperforms other methods on fluctuating complex data.

Object-based factorizations provide a useful level of abstraction for interacting with the world. Building explicit object representations, however, often requires supervisory signals that are difficult to obtain in practice. We present a paradigm for learning object-centric representations for physical scene understanding without direct supervision of object properties. Our model, Object-Oriented Prediction and Planning (O2P2), jointly learns a perception function to map from image observations to object representations, a pairwise physics interaction function to predict the time evolution of a collection of objects, and a rendering function to map objects back to pixels. For evaluation, we consider not only the accuracy of the physical predictions of the model, but also its utility for downstream tasks that require an actionable representation of intuitive physics. After training our model on an image prediction task, we can use its learned representations to build block towers more complicated than those observed during training.

We study fair allocation of indivisible goods to agents with unequal entitlements. Fair allocation has been the subject of many studies in both divisible and indivisible settings. Our emphasis is on the case where the goods are indivisible and agents have unequal entitlements. This problem is a generalization of the work by Procaccia and Wang (2014) wherein the agents are assumed to be symmetric with respect to their entitlements. Although Procaccia and Wang show an almost fair (constant approximation) allocation exists in their setting, our main result is in sharp contrast to their observation. We show that, in some cases with n agents, no allocation can guarantee better than 1/n approximation of a fair allocation when the entitlements are not necessarily equal. Furthermore, we devise a simple algorithm that ensures a 1/n approximation guarantee. Our second result is for a restricted version of the problem where the valuation of every agent for each good is bounded by the total value he wishes to receive in a fair allocation. Although this assumption might seem without loss of generality, we show it enables us to find a 1/2 approximation fair allocation via a greedy algorithm. Finally, we run some experiments on real-world data and show that, in practice, a fair allocation is likely to exist. We also support our experiments by showing positive results for two stochastic variants of the problem, namely stochastic agents and stochastic items.

I'm back this semester as a DH Prototyping Fellow, and together, Alyssa Collins and I are working on a project titled "Twitterature: Methods and Metadata." Specifically, we're hoping to develop a simple way of using Twitter data for literary research. The project is still in its early stages, but we've been collecting a lot of data and are now beginning to visualize it (I'm particularly interested in the geolocation of tweets, so I'm trying out a few mapping options). In this post, I want to layout our methods for collecting Twitter data. Okay, Alyssa and I have been using a python based Twitter scraping script, which we modified to search Twitter without any time limitations (the official Twitter search function is limited to tweets of the past two weeks). So, to run the Twitter scraping script, I entered the following in my command line: python3 TwitterScraper.py.

A neural network trained to find Alzheimer's. Scientists from California state University teaching artificial intelligence to determine the likelihood of developing Alzheimer's disease six years before diagnosis. One of the researchers Jae Ho San explains that Alzheimer's disease in the early stages it is difficult to determine due to the lack of obvious symptoms. Diagnostics is to measure the level of glucose in different areas of the brain. Changes occur very slowly, but the neural network can capture.

A neural network trained to find Alzheimer's. Scientists from California state University teaching artificial intelligence to determine the likelihood of developing Alzheimer's disease six years before diagnosis. One of the researchers Jae Ho San explains that Alzheimer's disease in the early stages it is difficult to determine due to the lack of obvious symptoms. Diagnostics is to measure the level of glucose in different areas of the brain. Changes occur very slowly, but the neural network can capture.

China has for the first time released video showing its latest stealth drone in flight, state media said Sunday. China Central Television (CCTV) on Saturday ran video featuring the "saucer-like" Sky Hawk drone, and state-run Global Times claimed that the new drone's cutting-edge technology will allow it to fly faster, farther and escape detection. The Global Times, quoting the CCTV report, said the China Aerospace Science and Industry Corp.-developed drone, known as the Sky Hawk, had conducted the flight test at an undisclosed location in the country. Video showed the drone taking off and landing, marking the first time that the aircraft has been publicly seen in flight, according to the reports. The drone reportedly made its maiden flight last February, but no video had been published before Saturday's broadcast.