Predicting the future is a crucial first step to effective control, since systems that can predict the future can select plans that lead to desired outcomes. In this work, we study the problem of future prediction at the level of 3D scenes, represented by point clouds captured by a LiDAR sensor, i.e., directly learning to forecast the evolution of >100,000 points that comprise a complete scene. We term this Scene Point Cloud Sequence Forecasting (SPCSF). By directly predicting the densest-possible 3D representation of the future, the output contains richer information than other representations such as future object trajectories. We design a method, SPCSFNet, evaluate it on the KITTI and nuScenes datasets, and find that it demonstrates excellent performance on the SPCSF task. To show that SPCSF can benefit downstream tasks such as object trajectory forecasting, we present a new object trajectory forecasting pipeline leveraging SPCSFNet. Specifically, instead of forecasting at the object level as in conventional trajectory forecasting, we propose to forecast at the sensor level and then apply detection and tracking on the predicted sensor data. As a result, our new pipeline can remove the need of object trajectory labels and enable large-scale training with unlabeled sensor data. Surprisingly, we found our new pipeline based on SPCSFNet was able to outperform the conventional pipeline using state-of-the-art trajectory forecasting methods, all of which require future object trajectory labels. Finally, we propose a new evaluation procedure and two new metrics to measure the end-to-end performance of the trajectory forecasting pipeline. Our code will be made publicly available at https://github.com/xinshuoweng/SPCSF

Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong learning settings where the goal is to learn each consecutive task rapidly from as little data as possible. To reduce this burden, we develop a lifelong learning method based on coupled dictionary learning that utilizes high-level task descriptions to model inter-task relationships. We show that using task descriptors improves the performance of the learned task policies, providing both theoretical justification for the benefit and empirical demonstration of the improvement across a variety of learning problems. Given only the descriptor for a new task, the lifelong learner is also able to accurately predict a model for the new task through zero-shot learning using the coupled dictionary, eliminating the need to gather training data before addressing the task.

Most causal discovery algorithms find causal structure among a set of observed variables. Learning the causal structure among latent variables remains an important open problem, particularly when using high-dimensional data. In this paper, we address a problem for which it is known that inputs cause outputs, and these causal relationships are encoded by a causal network among a set of an unknown number of latent variables. We developed a deep learning model, which we call a redundant input neural network (RINN), with a modified architecture and a regularized objective function to find causal relationships between input, hidden, and output variables. More specifically, our model allows input variables to directly interact with all latent variables in a neural network to influence what information the latent variables should encode in order to generate the output variables accurately. In this setting, the direct connections between input and latent variables makes the latent variables partially interpretable; furthermore, the connectivity among the latent variables in the neural network serves to model their potential causal relationships to each other and to the output variables. A series of simulation experiments provide support that the RINN method can successfully recover latent causal structure between input and output variables.

With the adoption of Semantic Web technologies, an increasing number of vocabularies and ontologies have been developed in different domains, ranging from Biology to Agronomy or Geosciences. However, many of these ontologies are still difficult to find, access and understand by researchers due to a lack of documentation, URI resolving issues, versioning problems, etc. In this chapter we describe guidelines and best practices for creating accessible, understandable and reusable ontologies on the Web, using standard practices and pointing to existing tools and frameworks developed by the Semantic Web community. We illustrate our guidelines with concrete examples, in order to help researchers implement these practices in their future vocabularies.

Effective triage is critical to mitigating the effect of increased volume by accurately determining patient acuity, need for resources, and establishing effective acuity-based patient prioritization. The purpose of this retrospective study was to determine whether historical EHR data can be extracted and synthesized with clinical natural language processing (C-NLP) and the latest ML algorithms (KATE) to produce highly accurate ESI predictive models. An ML model (KATE) for the triage process was developed using 166,175 patient encounters from two participating hospitals. The model was then tested against a gold set that was derived from a random sample of triage encounters at the study sites and correct acuity assignments were recorded by study clinicians using the Emergency Severity Index (ESI) standard as a guide. At the two study sites, KATE predicted accurate ESI acuity assignments 75.9% of the time, compared to nurses (59.8%) and average individual study clinicians (75.3%). KATE accuracy was 26.9% higher than the average nurse accuracy (p-value < 0.0001). On the boundary between ESI 2 and ESI 3 acuity assignments, which relates to the risk of decompensation, KATE was 93.2% higher with 80% accuracy, compared to triage nurses with 41.4% accuracy (p-value < 0.0001). KATE provides a triage acuity assignment substantially more accurate than the triage nurses in this study sample. KATE operates independently of contextual factors, unaffected by the external pressures that can cause under triage and may mitigate the racial and social biases that can negatively affect the accuracy of triage assignment. Future research should focus on the impact of KATE providing feedback to triage nurses in real time, KATEs impact on mortality and morbidity, ED throughput, resource optimization, and nursing outcomes.

This work presents a hybrid and hierarchical deep learning model for mid-term load forecasting. The model combines exponential smoothing (ETS), advanced Long Short-Term Memory (LSTM) and ensembling. ETS extracts dynamically the main components of each individual time series and enables the model to learn their representation. Multi-layer LSTM is equipped with dilated recurrent skip connections and a spatial shortcut path from lower layers to allow the model to better capture long-term seasonal relationships and ensure more efficient training. A common learning procedure for LSTM and ETS, with a penalized pinball loss, leads to simultaneous optimization of data representation and forecasting performance. In addition, ensembling at three levels ensures a powerful regularization. A simulation study performed on the monthly electricity demand time series for 35 European countries confirmed the high performance of the proposed model and its competitiveness with classical models such as ARIMA and ETS as well as state-of-the-art models based on machine learning.

To accommodate diverse Quality-of-Service (QoS) requirements in 5th generation cellular networks, base stations need real-time optimization of radio resources in time-varying network conditions. This brings high computing overheads and long processing delays. In this work, we develop a deep learning framework to approximate the optimal resource allocation policy that minimizes the total power consumption of a base station by optimizing bandwidth and transmit power allocation. We find that a fully-connected neural network (NN) cannot fully guarantee the QoS requirements due to the approximation errors and quantization errors of the numbers of subcarriers. To tackle this problem, we propose a cascaded structure of NNs, where the first NN approximates the optimal bandwidth allocation, and the second NN outputs the transmit power required to satisfy the QoS requirement with given bandwidth allocation. Considering that the distribution of wireless channels and the types of services in the wireless networks are non-stationary, we apply deep transfer learning to update NNs in non-stationary wireless networks. Simulation results validate that the cascaded NNs outperform the fully connected NN in terms of QoS guarantee. In addition, deep transfer learning can reduce the number of training samples required to train the NNs remarkably. I. INTRODUCTION A. Background The 5th Generation (5G) cellular networks are expected to support various emerging applications with diverse Quality-of-Service (QoS) requirements, such as enhanced mobile broadband services, massive This paper has been presented in part at the IEEE Global Communications Conference 2019 [1]. The authors are with the School of Electrical and Information Engineering, University of Sydney, Sydney, NSW 2006, Australia (email: {rui.dong, To guarantee the QoS requirements of different types of services, existing optimization algorithms for radio resource allocation are designed to maximize spectrum efficiency or energy efficiency by optimizing scarce radio resources, such as time-frequency resource blocks and transmit power, subject to QoS constraints [3-9]. There are two major challenges for implementing existing optimization algorithms in practical 5G networks. First, QoS constraints of some services, such as delay-sensitive and URLLC services, may not have closed-form expressions. To execute an optimization algorithm, the system needs to evaluate the QoS achieved by a certain policy via extensive simulations or experiments, and thus suffers from long processing delay [9, 10]. Second, even if the closed-form expressions of QoS constraints can be obtained in some scenarios, the optimization problems are non-convex in general [8,10,11].

This work presents ensemble forecasting of monthly electricity demand using pattern similarity-based forecasting methods (PSFMs). PSFMs applied in this study include $k$-nearest neighbor model, fuzzy neighborhood model, kernel regression model, and general regression neural network. An integral part of PSFMs is a time series representation using patterns of time series sequences. Pattern representation ensures the input and output data unification through filtering a trend and equalizing variance. Two types of ensembles are created: heterogeneous and homogeneous. The former consists of different type base models, while the latter consists of a single-type base model. Five strategies are used for controlling a diversity of members in a homogeneous approach. The diversity is generated using different subsets of training data, different subsets of features, randomly disrupted input and output variables, and randomly disrupted model parameters. An empirical illustration applies the ensemble models as well as individual PSFMs for comparison to the monthly electricity demand forecasting for 35 European countries.

This paper studies how to design abstractions of large-scale combinatorial optimization problems that can leverage existing state-of-the-art solvers in general purpose ways, and that are amenable to data-driven design. The goal is to arrive at new approaches that can reliably outperform existing solvers in wall-clock time. We focus on solving integer programs, and ground our approach in the large neighborhood search (LNS) paradigm, which iteratively chooses a subset of variables to optimize while leaving the remainder fixed. The appeal of LNS is that it can easily use any existing solver as a subroutine, and thus can inherit the benefits of carefully engineered heuristic approaches and their software implementations. We also show that one can learn a good neighborhood selector from training data. Through an extensive empirical validation, we demonstrate that our LNS framework can significantly outperform, in wall-clock time, compared to state-of-the-art commercial solvers such as Gurobi.

In this paper, we aim to look into the feasibility of constructing alphabets using gestures. The main idea is to construct gestures, that are easy to remember, not cumbersome to reproduce and easily identifiable. We construct gestures for the entire English alphabet and provide an algorithm to identify the gestures, even when they are constructed continuously. We tackle the problem statistically, taking into account the problem of randomness in the hand movement gestures of users, and achieve an average accuracy of 97.33% with the entire English alphabet.