Recent work has developed Bayesian methods for the automatic statistical analysis and description of single time series as well as of homogeneous sets of time series data. We extend prior work to create an interpretable kernel embedding for heterogeneous time series. Our method adds practically no computational cost compared to prior results by leveraging previously discarded intermediate results. We show the practical utility of our method by leveraging the learned embeddings for clustering, pattern discovery, and anomaly detection. These applications are beyond the ability of prior relational kernel learning approaches.

Submitted to the Annals of Applied Statistics SCALABLE MODELING OF SPATIOTEMPORAL DATA USING THE VARIATIONAL AUTOENCODER: AN APPLICATION IN GLAUCOMA By Samuel I. Berchuck, Felipe A. Medeiros and Sayan Mukherjee Duke University As big spatial data becomes increasingly prevalent, classical spatiotemporal (ST) methods often do not scale well. While methods have been developed to account for high-dimensional spatial objects, the setting where there are exceedingly large samples of spatial observations has had less attention. The variational autoencoder (V AE), an unsupervised generative model based on deep learning and approximate Bayesian inference, fills this void using a latent variable specification that is inferred jointly across the large number of samples. In this manuscript, we compare the performance of the V AE with a more classical ST method when analyzing longitudinal visual fields from a large cohort of patients in a prospective glaucoma study. Through simulation and a case study, we demonstrate that the V AE is a scalable method for analyzing ST data, when the goal is to obtain accurate predictions. R code to implement the V AE can be found on GitHub: https://github.com/berchuck/vaeST. 1. Introduction. As high-speed computing and medical imaging become increasingly inexpensive, massive amounts of data are generated that have to be analyzed and are often spatial in nature (Bearden and Thompson, 2017; Smith and Nichols, 2018). In the case of medical imaging, the number of patients that can be imaged has skyrocketed in recent years, allowing for studies that include images from many thousands of patients (Van Essen et al., 2013; Miller et al., 2016). The current spatial statistics literature focuses heavily on scalability in terms of the number of spatial locations (Banerjee, 2017), however largely ignores the setting where a joint model is needed for spatiotemporal (ST) data that are generated from a large cohort. Historically, learning an appropriate generating process in this setting was untenable, typically leading to simplifying assumptions, such as point-wise (PW) modeling of locations across time (Fitzke et al., 1996). In particular, generative models using deep learning have shown great promise in modeling complex distributions, p( x), for x x 1: M in some potentially high-dimensional space X . Sampling from X is often intractable, so instead generative modeling learns a distribution q (x) that can be sampled from and is close to p (x) (Doersch, 2016). As such, generative modeling can be viewed as an approximate method for performing inference in high-dimensional contexts, when there is an overwhelming availability of observations x . Generative modeling, and in particular the variational auto-encoder (V AE), are well-suited for modeling large cohorts of ST data, because they can characterize variability in a spatial data source through joint modeling (Kingma and Welling, 2013).

For machine learning perception problems, human-level classification performance is used as an estimate of top algorithm performance. Thus, it is important to understand as precisely as possible the factors that impact human-level performance. Knowing this 1) provides a benchmark for model performance, 2) tells a project manager what type of data to obtain for human labelers in order to get accurate labels, and 3) enables ground-truth analysis--largely conducted by humans--to be carried out smoothly. In this empirical study, we explored the relationship between resolution and human classification performance using the MNIST data set down-sampled to various resolutions. The quantitative heuristic we derived could prove useful for predicting machine model performance, predicting data storage requirements, and saving valuable resources in the deployment of machine learning projects. It also has the potential to be used in a wide variety of fields such as remote sensing, medical imaging, scientific imaging, and astronomy.

In this paper, we advocate for the study of fairness techniques in low data situations. We propose two algorithms Fairness Warnings and Fair-MAML. The first is a model-agnostic algorithm that provides interpretable boundary conditions for when a fairly trained model may not behave fairly on similar but slightly different tasks within a given domain. The second is a fair meta-learning approach to train models that can be trained through gradient descent with the objective of "learning how to learn fairly". This method encodes more general notions of fairness and accuracy into the model so that it can learn new tasks within a domain both quickly and fairly from only a few training points. We demonstrate experimentally the individual utility of each model using relevant baselines for comparison and provide the first experiment to our knowledge of K-shot fairness, i.e. training a fair model on a new task with only K data points. Then, we illustrate the usefulness of both algorithms as a combined method for training models from a few data points on new tasks while using Fairness Warnings as interpretable boundary conditions under which the newly trained model may not be fair.

Prediction of future states of the environment and interacting agents is a key competence required for autonomous agents to operate successfully in the real world. Prior work for structured sequence prediction based on latent variable models imposes a uni-modal standard Gaussian prior on the latent variables. This induces a strong model bias which makes it challenging to fully capture the multi-modality of the distribution of the future states. In this work, we introduce Conditional Flow Variational Autoencoders which uses our novel conditional normalizing flow based prior. We show that using our novel complex multi-modal conditional prior we can capture complex multi-modal conditional distributions. Furthermore, we study for the first time latent variable collapse with normalizing flows and propose solutions to prevent such failure cases. Our experiments on three multi-modal structured sequence prediction datasets -- MNIST Sequences, Stanford Drone and HighD -- show that the proposed method obtains state of art results across different evaluation metrics.

We developed four variants of the model, ranging in size from small (124 million parameters) to large ( 1.5 billion parameters). We chose a staged release process, releasing the smallest model in February, but withholding larger models due to concerns about the potential for misuse, such as generating fake news content, impersonating others in email, or automating abusive social media content production [ 46 ]. We released the next model size in May as part of a staged release process. We are now releasing our 774 million parameter model. While large language models' flexibility and generative capabilities raise misuse concerns, they also have a range of beneficial uses - they can assist in prose, poetry, and programming; analyze dataset biases; and more.

Last-mile delivery systems commonly propose the use of autonomous robotic vehicles to increase scalability and efficiency. The economic inefficiency of collecting accurate prior maps for navigation motivates the use of planning algorithms that operate in unmapped environments. However, these algorithms typically waste time exploring regions that are unlikely to contain the delivery destination. Context is key information about structured environments that could guide exploration toward the unknown goal location, but the abstract idea is difficult to quantify for use in a planning algorithm. Some approaches specifically consider contextual relationships between objects, but would perform poorly in object-sparse environments like outdoors. Recent deep learning-based approaches consider context too generally, making training/transferability difficult. Therefore, this work proposes a novel formulation of utilizing context for planning as an image-to-image translation problem, which is shown to extract terrain context from semantic gridmaps, into a metric that an exploration-based planner can use. The proposed framework has the benefit of training on a static dataset instead of requiring a time-consuming simulator. Across 42 test houses with layouts from satellite images, the trained algorithm enables a robot to reach its goal 189\% faster than with a context-unaware planner, and within 63\% of the optimal path computed with a prior map. The proposed algorithm is also implemented on a vehicle with a forward-facing camera in a high-fidelity, Unreal simulation of neighborhood houses.

In the finance sector, studies focused on anomaly detection are often associated with time-series and transactional data analytics. In this paper, we lay out the opportunities for applying anomaly and deviation detection methods to text corpora and challenges associated with them. We argue that language models that use distributional semantics can play a significant role in advancing these studies in novel directions, with new applications in risk identification, predictive modeling, and trend analysis.

Robots powered by artificial intelligence have been popping up in hotels, airports and shopping malls. Now, they're showing up at assisted living homes, too. With names like Stevie, Paro and Pillo, these robots can do everything from keeping the elderly company to reminding them to take their medication at the right time. "Robotics has the potential to play a huge role in elder care facilities and hospitals to enable people to do more with less," says Conor McGinn, a roboticist and assistant professor at Trinity College Dublin. Watch the video above to learn more about how robots are being used in elderly care.

With glass interior walls, exposed plumbing and a staff of young researchers dressed like Urban Outfitters models, New York University's AI Now Institute could easily be mistaken for the offices of any one of New York's innumerable tech startups. For many of those small companies (and quite a few larger ones) the objective is straightforward: leverage new advances in computing, especially artificial intelligence (AI), to disrupt industries from social networking to medical research. But for Meredith Whittaker and Kate Crawford, who co-founded AI Now together in 2017, it's that disruption itself that's under scrutiny. They are two of many experts who are working to ensure that, as corporations, entrepreneurs and governments roll out new AI applications, they do so in a way that's ethically sound. "These tools are now impacting so many parts of our everyday life, from healthcare to criminal justice to education to hiring, and it's happening simultaneously," says Crawford.