Search for: All records

As a decisive part in the success of Mobility-as-a-Service (MaaS), spatio-temporal dynamics modeling on mobility networks is a challenging task particularly considering scenarios where open-world events drive mobility behavior deviated from the routines. While tremendous progress has been made to model high-level spatio-temporal regularities with deep learning, most, if not all of the existing methods are neither aware of the dynamic interactions among multiple transport modes on mobility networks, nor adaptive to unprecedented volatility brought by potential open-world events. In this paper, we are therefore motivated to improve the canonical spatio-temporal network (ST-Net) from two perspectives: (1) design a heterogeneous mobility information network (HMIN) to explicitly represent intermodality in multimodal mobility; (2) propose a memory-augmented dynamic filter generator (MDFG) to generate sequence-specific parameters in an on-the-fly fashion for various scenarios. The enhanced event-aware spatio-temporal network, namely EAST-Net, is evaluated on several real-world datasets with a wide variety and coverage of open-world events. Both quantitative and qualitative experimental results verify the superiority of our approach compared with the state-of-the-art baselines. What is more, experiments show generalization ability of EAST-Net to perform zero-shot inference over different open-world events that have not been seen. 

Recombinant adeno‐associated virus (rAAV) is among the most commonly used in vivo gene delivery vehicles and has seen a number of successes in clinical application. Current manufacturing processes of rAAV employ multiple plasmid transfection or rely on virus infection and face challenges in scale‐up. A synthetic biology approach was taken to generate stable cell lines with integrated genetic modules, which produced rAAV upon induction albeit at a low productivity. To identify potential factors that restrained the productivity, we systematically characterized virus production kinetics through targeted quantitative proteomics and various physical assays of viral components. We demonstrated that reducing the excessive expression of gene of interest by its conditional expression greatly increased the productivity of these synthetic cell lines. Further enhancement was gained by optimizing induction profiles and alleviating proteasomal degradation of viral capsid protein by the addition of proteasome inhibitors. Altogether, these enhancements brought the productivity close to traditional multiple plasmid transfection. The rAAV produced had comparable full particle contents as those produced by conventional transient plasmid transfection. The present work exemplified the versatility of our synthetic biology‐based viral vector production platform and its potential for plasmid‐ and virus‐free rAAV manufacturing.

 

An extensively studied phenomenon of the past few years in training deep networks is the implicit bias of gradient descent towards parsimonious solutions. In this work, we further investigate this phenomenon by narrowing our focus to deep matrix factorization, where we reveal surprising low-dimensional structures in the learning dynamics when the target matrix is low-rank. Specifically, we show that the evolution of gradient descent starting from arbitrary orthogonal initialization only affects a minimal portion of singular vector spaces across all weight matrices. In other words, the learning process happens only within a small invariant subspace of each weight matrix, despite the fact that all parameters are updated throughout training. From this, we provide rigorous justification for low-rank training in a specific, yet practical setting. In particular, we demonstrate that we can construct compressed factorizations that are equivalent to full-width, deep factorizations throughout training for solving low-rank matrix completion problems efficiently. 

Today a tremendous amount of geospatial knowledge is hidden in massive volumes of text data. To facilitate flexible and powerful geospatial analysis and applications, we introduce a new architecture: geospatial knowledge hypercube, a multi-scale, multidimensional knowledge structure that integrates information from geospatial dimensions, thematic themes and diverse application semantics, extracted and computed from spatial-related text data. To construct such a knowledge hypercube, weakly supervised language models are leveraged for automatic, dynamic and incremental extraction of heterogeneous geospatial data, thematic themes, latent connections and relationships, and application semantics, through combining a variety of information from unstructured text, structured tables, and maps. The hypercube lays a foundation for many knowledge discovery and in-depth spatial analysis, and other advanced applications. We have deployed a prototype web application of proposed geospatial knowledge hypercube for public access at: https://hcwebapp.cigi.illinois.edu/. 

Abstract In robotics, simulation has the potential to reduce design time and costs, and lead to a more robust engineered solution and a safer development process. However, the use of simulators is predicated on the availability of good models. This contribution is concerned with improving the quality of these models via calibration, which is cast herein in a Bayesian framework. First, we discuss the Bayesian machinery involved in model calibration. Then, we demonstrate it in one example: calibration of a vehicle dynamics model that has low degree-of-freedom (DOF) count and can be used for state estimation, model predictive control, or path planning. A high fidelity simulator is used to emulate the “experiments” and generate the data for the calibration. The merit of this work is not tied to a new Bayesian methodology for calibration, but to the demonstration of how the Bayesian machinery can establish connections among models in computational dynamics, even when the data in use is noisy. The software used to generate the results reported herein is available in a public repository for unfettered use and distribution.