A Unified Neural Network Approach for Estimating Travel Time and Distance for a Taxi Trip

In building intelligent transportation systems such as taxi or rideshare services, accurate prediction of travel time and distance is crucial for customer experience and resource management. Using the NYC taxi dataset, which contains taxi trips data collected from GPS-enabled taxis [23], this paper investigates the use of deep neural networks to jointly predict taxi trip time and distance. We propose a model, called ST-NN (Spatio-Temporal Neural Network), which first predicts the travel distance between an origin and a destination GPS coordinate, then combines this prediction with the time of day to predict the travel time. The beauty of ST-NN is that it uses only the raw trips data without requiring further feature engineering and provides a joint estimate of travel time and distance. We compare the performance of ST-NN to that of state-of-the-art travel time estimation methods, and we observe that the proposed approach generalizes better than state-of-the-art methods. We show that ST-NN approach significantly reduces the mean absolute error for both predicted travel time and distance, about 17% for travel time prediction. We also observe that the proposed approach is more robust to outliers present in the dataset by testing the performance of ST-NN on the datasets with and without outliers.

Open-World Learning Without Labels

Open-world learning is a problem where an autonomous agent detects things that it does not know and learns them over time from a non-stationary and never-ending stream of data; in an open-world environment, the training data and objective criteria are never available at once. The agent should grasp new knowledge from learning without forgetting acquired prior knowledge. Researchers proposed a few open-world learning agents for image classification tasks that operate in complex scenarios. However, all prior work on open-world learning has all labeled data to learn the new classes from the stream of images. In scenarios where autonomous agents should respond in near real-time or work in areas with limited communication infrastructure, human labeling of data is not possible. Therefore, supervised open-world learning agents are not scalable solutions for such applications. Herein, we propose a new framework that enables agents to learn new classes from a stream of unlabeled data in an unsupervised manner. Also, we study the robustness and learning speed of such agents with supervised and unsupervised feature representation. We also introduce a new metric for open-world learning without labels. We anticipate our theories and method to be a starting point for developing autonomous true open-world never-ending learning agents.

Adaptive Lidar Scan Frame Integration: Tracking Known MAVs in 3D Point Clouds

Micro-aerial vehicles (MAVs) are becoming ubiquitous across multiple industries and application domains. Lightweight MAVs with only an onboard flight controller and a minimal sensor suite (e.g., IMU, vision, and vertical ranging sensors) have potential as mobile and easily deployable sensing platforms. When deployed from a ground robot, a key parameter is a relative localization between the ground robot and the MAV. This paper proposes a novel method for tracking MAVs in lidar point clouds. In lidar point clouds, we consider the speed and distance of the MAV to actively adapt the lidar's frame integration time and, in essence, the density and size of the point cloud to be processed. We show that this method enables more persistent and robust tracking when the speed of the MAV or its distance to the tracking sensor changes. In addition, we propose a multi-modal tracking method that relies on high-frequency scans for accurate state estimation, lower-frequency scans for robust and persistent tracking, and sub-Hz processing for trajectory and object identification. These three integration and processing modalities allow for an overall accurate and robust MAV tracking while ensuring the object being tracked meets shape and size constraints.

Real-time Scene Text Detection with Differentiable Binarization

Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text. However, the post-processing of binarization is essential for segmentation-based detection, which converts probability maps produced by a segmentation method into bounding boxes/regions of text. In this paper, we propose a module named Differentiable Binarization (DB), which can perform the binarization process in a segmentation network. Optimized along with a DB module, a segmentation network can adaptively set the thresholds for binarization, which not only simplifies the post-processing but also enhances the performance of text detection. Based on a simple segmentation network, we validate the performance improvements of DB on five benchmark datasets, which consistently achieves state-of-the-art results, in terms of both detection accuracy and speed. In particular, with a light-weight backbone, the performance improvements by DB are significant so that we can look for an ideal tradeoff between detection accuracy and efficiency. Specifically, with a backbone of ResNet-18, our detector achieves an F-measure of 82.8, running at 62 FPS, on the MSRA-TD500 dataset. Code is available at: https://github.com/MhLiao/DB

Transient Information Adaptation of Artificial Intelligence: Towards Sustainable Data Processes in Complex Projects

Large scale projects increasingly operate in complicated settings whilst drawing on an array of complex data-points, which require precise analysis for accurate control and interventions to mitigate possible project failure. Coupled with a growing tendency to rely on new information systems and processes in change projects, 90% of megaprojects globally fail to achieve their planned objectives. Renewed interest in the concept of Artificial Intelligence (AI) against a backdrop of disruptive technological innovations, seeks to enhance project managers cognitive capacity through the project lifecycle and enhance project excellence. However, despite growing interest there remains limited empirical insights on project managers ability to leverage AI for cognitive load enhancement in complex settings. As such this research adopts an exploratory sequential linear mixed methods approach to address unresolved empirical issues on transient adaptations of AI in complex projects, and the impact on cognitive load enhancement. Initial thematic findings from semi-structured interviews with domain experts, suggest that in order to leverage AI technologies and processes for sustainable cognitive load enhancement with complex data over time, project managers require improved knowledge and access to relevant technologies that mediate data processes in complex projects, but equally reflect application across different project phases. These initial findings support further hypothesis testing through a larger quantitative study incorporating structural equation modelling to examine the relationship between artificial intelligence and project managers cognitive load with project data in complex contexts.

Generalized Approach to Matched Filtering using Neural Networks

Gravitational wave science is a pioneering field with rapidly evolving data analysis methodology currently assimilating and inventing deep learning techniques. The bulk of the sophisticated flagship searches of the field rely on the time-tested matched filtering principle within their core. In this paper, we make a key observation on the relationship between the emerging deep learning and the traditional techniques: matched filtering is formally equivalent to a particular neural network. This means that a neural network can be constructed analytically to exactly implement matched filtering, and can be further trained on data or boosted with additional complexity for improved performance. This fundamental equivalence allows us to define a "complexity standard candle" allowing us to characterize the relative complexity of the different approaches to gravitational wave signals in a common framework. Additionally it also provides a glimpse of an intriguing symmetry that could provide clues on how neural networks approach the problem of finding signals in overwhelming noise. Moreover, we show that the proposed neural network architecture can outperform matched filtering, both with or without knowledge of a prior on the parameter distribution. When a prior is given, the proposed neural network can approach the statistically optimal performance. We also propose and investigate two different neural network architectures MNet-Shallow and MNet-Deep, both of which implement matched filtering at initialization and can be trained on data. MNet-Shallow has simpler structure, while MNet-Deep is more flexible and can deal with a wider range of distributions. Our theoretical findings are corroborated by experiments using real LIGO data and synthetic injections. Finally, our results suggest new perspectives on the role of deep learning in gravitational wave detection.

IBRNet: Learning Multi-View Image-Based Rendering

We present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. The core of our method is a network architecture that includes a multilayer perceptron and a ray transformer that estimates radiance and volume density at continuous 5D locations (3D spatial locations and 2D viewing directions), drawing appearance information on the fly from multiple source views. By drawing on source views at render time, our method hearkens back to classic work on image-based rendering (IBR), and allows us to render high-resolution imagery. Unlike neural scene representation work that optimizes per-scene functions for rendering, we learn a generic view interpolation function that generalizes to novel scenes. We render images using classic volume rendering, which is fully differentiable and allows us to train using only multi-view posed images as supervision. Experiments show that our method outperforms recent novel view synthesis methods that also seek to generalize to novel scenes. Further, if fine-tuned on each scene, our method is competitive with state-of-the-art single-scene neural rendering methods.

Dynamic Knowledge Graphs as Semantic Memory Model for Industrial Robots

In this paper, we present a model for semantic memory that allows machines to collect information and experiences to become more proficient with time. After a semantic analysis of the data, information is stored in a knowledge graph which is used to comprehend instructions, expressed in natural language, and execute the required tasks in a deterministic manner. This imparts industrial robots cognitive behavior and an intuitive user interface, which is most appreciated in an era, when collaborative robots are to work alongside humans. The paper outlines the architecture of the system together with a practical implementation of the proposal.

BR-NS: an Archive-less Approach to Novelty Search

As open-ended learning based on divergent search algorithms such as Novelty Search (NS) draws more and more attention from the research community, it is natural to expect that its application to increasingly complex real-world problems will require the exploration to operate in higher dimensional Behavior Spaces which will not necessarily be Euclidean. Novelty Search traditionally relies on k-nearest neighbours search and an archive of previously visited behavior descriptors which are assumed to live in a Euclidean space. This is problematic because of a number of issues. On one hand, Euclidean distance and Nearest-neighbour search are known to behave differently and become less meaningful in high dimensional spaces. On the other hand, the archive has to be bounded since, memory considerations aside, the computational complexity of finding nearest neighbours in that archive grows linearithmically with its size. A sub-optimal bound can result in "cycling" in the behavior space, which inhibits the progress of the exploration. Furthermore, the performance of NS depends on a number of algorithmic choices and hyperparameters, such as the strategies to add or remove elements to the archive and the number of neighbours to use in k-nn search. In this paper, we discuss an alternative approach to novelty estimation, dubbed Behavior Recognition based Novelty Search (BR-NS), which does not require an archive, makes no assumption on the metrics that can be defined in the behavior space and does not rely on nearest neighbours search. We conduct experiments to gain insight into its feasibility and dynamics as well as potential advantages over archive-based NS in terms of time complexity.

OGGN: A Novel Generalized Oracle Guided Generative Architecture for Modelling Inverse Function of Artificial Neural Networks

This paper presents a novel Generative Neural Network Architecture for modelling the inverse function of an Artificial Neural Network (ANN) either completely or partially. Modelling the complete inverse function of an ANN involves generating the values of all features that corresponds to a desired output. On the other hand, partially modelling the inverse function means generating the values of a subset of features and fixing the remaining feature values. The feature set generation is a critical step for artificial neural networks, useful in several practical applications in engineering and science. The proposed Oracle Guided Generative Neural Network, dubbed as OGGN, is flexible to handle a variety of feature generation problems. In general, an ANN is able to predict the target values based on given feature vectors. The OGGN architecture enables to generate feature vectors given the predetermined target values of an ANN. When generated feature vectors are fed to the forward ANN, the target value predicted by ANN will be close to the predetermined target values. Therefore, the OGGN architecture is able to map, inverse function of the function represented by forward ANN. Besides, there is another important contribution of this work. This paper also introduces a new class of functions, defined as constraint functions. The constraint functions enable a neural network to investigate a given local space for a longer period of time. Thus, enabling to find a local optimum of the loss function apart from just being able to find the global optimum. OGGN can also be adapted to solve a system of polynomial equations in many variables. The experiments on synthetic datasets validate the effectiveness of OGGN on various use cases.