This study addresses the problem of off-policy evaluation (OPE) from dependent samples obtained via the bandit algorithm. The goal of OPE is to evaluate a new policy using historical data obtained from behavior policies generated by the bandit algorithm. Because the bandit algorithm updates the policy based on past observations, the samples are not independent and identically distributed (i.i.d.). However, several existing methods for OPE do not take this issue into account and are based on the assumption that samples are i.i.d. In this study, we address this problem by constructing an estimator from a standardized martingale difference sequence. To standardize the sequence, we consider using evaluation data or sample splitting with a two-step estimation. This technique produces an estimator with asymptotic normality without restricting a class of behavior policies. In an experiment, the proposed estimator performs better than existing methods, which assume that the behavior policy converges to a time-invariant policy.
Time is deeply woven into how people perceive, and communicate about the world. Almost unconsciously, we provide our language utterances with temporal cues, like verb tenses, and we can hardly produce sentences without such cues. Extracting temporal cues from text, and constructing a global temporal view about the order of described events is a major challenge of automatic natural language understanding. Temporal reasoning, the process of combining different temporal cues into a coherent temporal view, plays a central role in temporal information extraction. This article presents a comprehensive survey of the research from the past decades on temporal reasoning for automatic temporal information extraction from text, providing a case study on the integration of symbolic reasoning with machine learning-based information extraction systems.
Analyzing and interpreting time-dependent stochastic data requires accurate and robust density estimation. In this paper we extend the concept of normalizing flows to so-called temporal Normalizing Flows (tNFs) to estimate time dependent distributions, leveraging the full spatio-temporal information present in the dataset. Our approach is unsupervised, does not require an a-priori characteristic scale and can accurately estimate multi-scale distributions of vastly different length scales. We illustrate tNFs on sparse datasets of Brownian and chemotactic walkers, showing that the inclusion of temporal information enhances density estimation. Finally, we speculate how tNFs can be applied to fit and discover the continuous PDE underlying a stochastic process.
Action recognition via 3D skeleton data is an emerging important topic in these years. Most existing methods either extract hand-crafted descriptors or learn action representations by supervised learning paradigms that require massive labeled data. In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL that can leverage different augmentations of unlabeled skeleton data to learn action representations in an unsupervised manner. Specifically, we first propose to contrast similarity between augmented instances (query and key) of the input skeleton sequence, which are transformed by multiple novel augmentation strategies, to learn inherent action patterns ("pattern-invariance") of different skeleton transformations. Second, to encourage learning the pattern-invariance with more consistent action representations, we propose a momentum LSTM, which is implemented as the momentum-based moving average of LSTM based query encoder, to encode long-term action dynamics of the key sequence. Third, we introduce a queue to store the encoded keys, which allows our model to flexibly reuse proceeding keys and build a more consistent dictionary to improve contrastive learning. Last, by temporally averaging the hidden states of action learned by the query encoder, a novel representation named Contrastive Action Encoding (CAE) is proposed to represent human's action effectively. Extensive experiments show that our approach typically improves existing hand-crafted methods by 10-50% top-1 accuracy, and it can achieve comparable or even superior performance to numerous supervised learning methods.
Manipulation tasks in daily life, such as pouring water, unfold intentionally under specialized manipulation contexts. Being able to process contextual knowledge in these Activities of Daily Living (ADLs) over time can help us understand manipulation intentions, which are essential for an intelligent robot to transition smoothly between various manipulation actions. In this paper, to model the intended concepts of manipulation, we present a vision dataset under a strictly constrained knowledge domain for both robot and human manipulations, where manipulation concepts and relations are stored by an ontology system in a taxonomic manner. Furthermore, we propose a scheme to generate a combination of visual attentions and an evolving knowledge graph filled with commonsense knowledge. Our scheme works with real-world camera streams and fuses an attention-based Vision-Language model with the ontology system. The experimental results demonstrate that the proposed scheme can successfully represent the evolution of an intended object manipulation procedure for both robots and humans. The proposed scheme allows the robot to mimic human-like intentional behaviors by watching real-time videos. We aim to develop this scheme further for real-world robot intelligence in Human-Robot Interaction.
Modularity is a central principle throughout the design process for cyber-physical systems. Modularity reduces complexity and increases reuse of behavior. In this paper we pose and answer the following question: how can we identify independent `modules' within the structure of reactive control architectures? To this end, we propose a graph-structured control architecture we call a decision structure, and show how it generalises some reactive control architectures which are popular in Artificial Intelligence (AI) and robotics, specifically Teleo-Reactive programs (TRs), Decision Trees (DTs), Behavior Trees (BTs) and Generalised Behavior Trees ($k$-BTs). Inspired by the definition of a module in graph theory, we define modules in decision structures and show how each decision structure possesses a canonical decomposition into its modules. We can naturally characterise each of the BTs, $k$-BTs, DTs and TRs by properties of their module decomposition. This allows us to recognise which decision structures are equivalent to each of these architectures in quadratic time. Our proposed concept of modules extends to formal verification, under any verification scheme capable of verifying a decision structure. Namely, we prove that a modification to a module within a decision structure has no greater flow-on effects than a modification to an individual action within that structure. This enables verification on modules to be done locally and hierarchically, where structures can be verified and then repeatedly locally modified, with modules replaced by modules while preserving correctness. To illustrate the findings, we present an example of a solar-powered drone controlled by a decision structure. We use a Linear Temporal Logic-based verification scheme to verify the correctness of this structure, and then show how one can modify modules while preserving its correctness.
One of the tasks of law enforcement agencies is to find evidence of criminal activity in the Darknet. However, visiting thousands of domains to locate visual information containing illegal acts manually requires a considerable amount of time and resources. Furthermore, the background of the images can pose a challenge when performing classification. To solve this problem, in this paper, we explore the automatic classification Tor Darknet images using Semantic Attention Keypoint Filtering, a strategy that filters non-significant features at a pixel level that do not belong to the object of interest, by combining saliency maps with Bag of Visual Words (BoVW). We evaluated SAKF on a custom Tor image dataset against CNN features: MobileNet v1 and Resnet50, and BoVW using dense SIFT descriptors, achieving a result of 87.98% accuracy and outperforming all other approaches.
Purpose: This work proposes a novel approach to efficiently generate MR fingerprints for MR fingerprinting (MRF) problems based on the unsupervised deep learning model generative adversarial networks (GAN). Methods: The GAN model is adopted and modified for better convergence and performance, resulting in an MRF specific model named GAN-MRF. The GAN-MRF model is trained, validated, and tested using different MRF fingerprints simulated from the Bloch equations with certain MRF sequence. The performance and robustness of the model are further tested by using in vivo data collected on a 3 Tesla scanner from a healthy volunteer together with MRF dictionaries with different sizes. T1, T2 maps are generated and compared quantitatively. Results: The validation and testing curves for the GAN-MRF model show no evidence of high bias or high variance problems. The sample MRF fingerprints generated from the trained GAN-MRF model agree well with the benchmark fingerprints simulated from the Bloch equations. The in vivo T1, T2 maps generated from the GAN-MRF fingerprints are in good agreement with those generated from the Bloch simulated fingerprints, showing good performance and robustness of the proposed GAN-MRF model. Moreover, the MRF dictionary generation time is reduced from hours to sub-second for the testing dictionary. Conclusion: The GAN-MRF model enables a fast and accurate generation of the MRF fingerprints. It significantly reduces the MRF dictionary generation process and opens the door for real-time applications and sequence optimization problems.
This paper addresses the problem of discovering the objects present in a collection of images without any supervision. We build on the optimization approach of Vo {\em et al.}~\cite{Vo2019UnsupOptim} with several key novelties: (1) We propose a novel saliency-based region proposal algorithm that achieves significantly higher overlap with ground-truth objects than other competitive methods. This procedure leverages off-the-shelf CNN features trained on classification tasks without any bounding box information, but is otherwise unsupervised. (2) We exploit the inherent hierarchical structure of proposals as an effective regularizer for the approach to object discovery of~\cite{Vo2019UnsupOptim}, boosting its performance to significantly improve over the state of the art on several standard benchmarks. (3) We adopt a two-stage strategy to select promising proposals using small random sets of images before using the whole image collection to discover the objects it depicts, allowing us to tackle, for the first time (to the best of our knowledge), the discovery of multiple objects in each one of the pictures making up datasets with up to 20,000 images, an over five-fold increase compared to existing methods, and a first step toward true large-scale unsupervised image interpretation.
There has been increased interest in missing sensor data imputation, which is ubiquitous in the field of structural health monitoring (SHM) due to discontinuous sensing caused by sensor malfunction. To address this fundamental issue, this paper presents an incremental Bayesian tensor learning method for reconstruction of spatiotemporal missing data in SHM and forecasting of structural response. In particular, a spatiotemporal tensor is first constructed followed by Bayesian tensor factorization that extracts latent features for missing data imputation. To enable structural response forecasting based on incomplete sensing data, the tensor decomposition is further integrated with vector autoregression in an incremental learning scheme. The performance of the proposed approach is validated on continuous field-sensing data (including strain and temperature records) of a concrete bridge, based on the assumption that strain time histories are highly correlated to temperature recordings. The results indicate that the proposed probabilistic tensor learning approach is accurate and robust even in the presence of large rates of random missing, structured missing and their combination. The effect of rank selection on the imputation and prediction performance is also investigated. The results show that a better estimation accuracy can be achieved with a higher rank for random missing whereas a lower rank for structured missing.