Despite substantial progress in deep learning approaches to time-series reconstruction, no existing methods are designed to uncover local activities with minute signal strength due to their negligible contribution to the optimization loss. Such local activities however can signify important abnormal events in physiological systems, such as an extra foci triggering an abnormal propagation of electrical waves in the heart. We discuss a novel technique for reconstructing such local activity that, while small in signal strength, is the cause of subsequent global activities that have larger signal strength. Our central innovation is to approach this by explicitly modeling and disentangling how the latent state of a system is influenced by potential hidden internal interventions. In a novel neural formulation of state-space models (SSMs), we first introduce causal-effect modeling of the latent dynamics via a system of interacting neural ODEs that separately describes 1) the continuous-time dynamics of the internal intervention, and 2) its effect on the trajectory of the system's native state. Because the intervention can not be directly observed but have to be disentangled from the observed subsequent effect, we integrate knowledge of the native intervention-free dynamics of a system, and infer the hidden intervention by assuming it to be responsible for differences observed between the actual and hypothetical intervention-free dynamics. We demonstrated a proof-of-concept of the presented framework on reconstructing ectopic foci disrupting the course of normal cardiac electrical propagation from remote observations.
One-bit compressed sensing (1bCS) is an extremely quantized signal acquisition method that has been proposed and studied rigorously in the past decade. In 1bCS, linear samples of a high dimensional signal are quantized to only one bit per sample (sign of the measurement). Assuming the original signal vector to be sparse, existing results in 1bCS either aim to find the support of the vector, or approximate the signal allowing a small error. The focus of this paper is support recovery, which often also computationally facilitate approximate signal recovery. A {\em universal} measurement matrix for 1bCS refers to one set of measurements that work for all sparse signals. With universality, it is known that $\tilde{\Theta}(k^2)$ 1bCS measurements are necessary and sufficient for support recovery (where $k$ denotes the sparsity). To improve the dependence on sparsity from quadratic to linear, in this work we propose approximate support recovery (allowing $\epsilon>0$ proportion of errors), and superset recovery (allowing $\epsilon$ proportion of false positives). We show that the first type of recovery is possible with $\tilde{O}(k/\epsilon)$ measurements, while the later type of recovery, more challenging, is possible with $\tilde{O}(\max\{k/\epsilon,k^{3/2}\})$ measurements. We also show that in both cases $\Omega(k/\epsilon)$ measurements would be necessary for universal recovery. Improved results are possible if we consider universal recovery within a restricted class of signals, such as rational signals, or signals with bounded dynamic range. In both cases superset recovery is possible with only $\tilde{O}(k/\epsilon)$ measurements. Other results on universal but approximate support recovery are also provided in this paper. All of our main recovery algorithms are simple and polynomial-time.
This 'research preview' paper introduces an adaptive path planning framework for robotic mission execution in assistive-care applications. The framework provides a graph-based environment modelling approach, with dynamic path finding performed using Dijkstra's algorithm. A predictive module that uses probabilistic model checking is applied to estimate the human's movement through the environment, allowing run-time re-planning of the robot's path. We illustrate the use of the framework for a simulated assistive-care case study in which a mobile robot navigates through the environment and monitors an end user with mild physical or cognitive impairments.
Referred to as the third rung of the causal inference ladder, counterfactual queries typically ask the "What if ?" question retrospectively. The standard approach to estimate counterfactuals resides in using a structural equation model that accurately reflects the underlying data generating process. However, such models are seldom available in practice and one usually wishes to infer them from observational data alone. Unfortunately, the correct structural equation model is in general not identifiable from the observed factual distribution. Nevertheless, in this work, we show that under the assumption that the main latent contributors to the treatment responses are categorical, the counterfactuals can be still reliably predicted. Building upon this assumption, we introduce CounterFactual Query Prediction (CFQP), a novel method to infer counterfactuals from continuous observations when the background variables are categorical. We show that our method significantly outperforms previously available deep-learning-based counterfactual methods, both theoretically and empirically on time series and image data. Our code is available at https://github.com/edebrouwer/cfqp.
Neural Architecture Search (NAS) algorithms aim at finding efficient Deep Neural Network (DNN) architectures for a given application under given system constraints. DNNs are computationally-complex as well as vulnerable to adversarial attacks. In order to address multiple design objectives, we propose RoHNAS, a novel NAS framework that jointly optimizes for adversarial-robustness and hardware-efficiency of DNNs executed on specialized hardware accelerators. Besides the traditional convolutional DNNs, RoHNAS additionally accounts for complex types of DNNs such as Capsule Networks. For reducing the exploration time, RoHNAS analyzes and selects appropriate values of adversarial perturbation for each dataset to employ in the NAS flow. Extensive evaluations on multi - Graphics Processing Unit (GPU) - High Performance Computing (HPC) nodes provide a set of Pareto-optimal solutions, leveraging the tradeoff between the above-discussed design objectives. For example, a Pareto-optimal DNN for the CIFAR-10 dataset exhibits 86.07% accuracy, while having an energy of 38.63 mJ, a memory footprint of 11.85 MiB, and a latency of 4.47 ms.
More tasks in Machine Reading Comprehension(MRC) require, in addition to answer prediction, the extraction of evidence sentences that support the answer. However, the annotation of supporting evidence sentences is usually time-consuming and labor-intensive. In this paper, to address this issue and considering that most of the existing extraction methods are semi-supervised, we propose an unsupervised evidence extraction method (U3E). U3E takes the changes after sentence-level feature erasure in the document as input, simulating the decline in problem-solving ability caused by human memory decline. In order to make selections on the basis of fully understanding the semantics of the original text, we also propose metrics to quickly select the optimal memory model for this input changes. To compare U3E with typical evidence extraction methods and investigate its effectiveness in evidence extraction, we conduct experiments on different datasets. Experimental results show that U3E is simple but effective, not only extracting evidence more accurately, but also significantly improving model performance.
Due to the unfamiliarity to particular words(or proper nouns) for ingredients, non-native English speakers can be extremely confused about the ordering process in restaurants like Subway. Thus, We developed a dialogue system, which supports Chinese(Mandarin)1 and English2 at the same time. In other words, users can switch arbitrarily between Chinese(Mandarin) and English as the conversation is being conducted. This system is specifically designed for Subway ordering3. In BilDOS, we designed a Discriminator module to tell the language is being used in inputted user utterance, a Translator module to translate used language into English if it is not English, and a Dialogue Manager module to detect the intention within inputted user utterances, handle outlier inputs by throwing clarification requests, map detected Intention and detailed Keyword4 into a particular intention class, locate the current ordering process, continue to give queries to finish the order, conclude the order details once the order is completed, activate the evaluation process when the conversation is done.
This paper aims to investigate representation learning for large scale visual place recognition, which consists of determining the location depicted in a query image by referring to a database of reference images. This is a challenging task due to the large-scale environmental changes that can occur over time (i.e., weather, illumination, season, traffic, occlusion). Progress is currently challenged by the lack of large databases with accurate ground truth. To address this challenge, we introduce GSV-Cities, a new image dataset providing the widest geographic coverage to date with highly accurate ground truth, covering more than 40 cities across all continents over a 14-year period. We subsequently explore the full potential of recent advances in deep metric learning to train networks specifically for place recognition, and evaluate how different loss functions influence performance. In addition, we show that performance of existing methods substantially improves when trained on GSV-Cities. Finally, we introduce a new fully convolutional aggregation layer that outperforms existing techniques, including GeM, NetVLAD and CosPlace, and establish a new state-of-the-art on large-scale benchmarks, such as Pittsburgh, Mapillary-SLS, SPED and Nordland. The dataset and code are available for research purposes at https://github.com/amaralibey/gsv-cities.
Therapeutic intervention in neurological disorders still relies heavily on pharmacological solutions, while the treatment of patients with drug resistance remains an open challenge. This is particularly true for patients with epilepsy, 30% of whom are refractory to medications. Implantable devices for chronic recording and electrical modulation of brain activity have proved a viable alternative in such cases. To operate, the device should detect the relevant electrographic biomarkers from Local Field Potentials (LFPs) and determine the right time for stimulation. To enable timely interventions, the ideal device should attain biomarker detection with low latency while operating under low power consumption to prolong the battery life. Neuromorphic networks have progressively gained reputation as low-latency low-power computing systems, which makes them a promising candidate as processing core of next-generation implantable neural interfaces. Here we introduce a fully-analog neuromorphic device implemented in CMOS technology for analyzing LFP signals in an in vitro model of acute ictogenesis. We show that the system can detect ictal and interictal events with ms-latency and with high precision, consuming on average 3.50 nW during the task. Our work paves the way to a new generation of brain implantable devices for personalized closed-loop stimulation for epilepsy treatment.
This paper investigates the performance of two-timescale transmission design for uplink reconfigurable intelligent surface (RIS)-aided cell-free massive multiple-input multiple-output (CF-mMIMO) systems. We consider the Rician channel model and design the passive beamforming of RISs based on the long-time statistical channel state information (CSI), while the maximum ratio combining (MRC) technique is utilized to design the active beamforming of base stations (BSs) based on the instantaneous overall channels, which are the superposition of the direct and RIS-reflected channels. Firstly, we derive the closed-form expressions of uplink achievable rate for arbitrary numbers of BS antennas and RIS reflecting elements. Relying on the derived expressions, we theoretically analyze the benefits of RIS-aided cell-free mMIMO systems and draw explicit insights. Then, based on closed-form expressions under statistical CSI, we maximize the sum user rate and the minimum user rate by optimizing the phase shifts of the RISs based on the genetic algorithm (GA). Finally, the numerical results demonstrate the feasibility and the benefits of deploying large-size RISs into conventional cell-free mMIMO systems. Besides, our results validate the effectiveness of the proposed two-timescale scheme in the RIS-aided cell-free mMIMO systems.