Search

We present a substantial extension of our Human-Aware Task Planning framework, tailored for scenarios with intermittent shared execution experiences and significant belief divergence between humans and robots, particularly due to the uncontrollable nature of humans. Our objective is to build a robot policy that accounts for uncontrollable human behaviors, thus enabling the anticipation of possible advancements achieved by the robot when the execution is not shared, e.g. when humans are briefly absent from the shared environment to complete a subtask. But, this anticipation is considered from the perspective of humans who have access to an estimated model for the robot. To this end, we propose a novel planning framework and build a solver based on AND-OR search, which integrates knowledge reasoning, including situation assessment by perspective taking. Our approach dynamically models and manages the expansion and contraction of potential advances while precisely keeping track of when (and when not) agents share the task execution experience. The planner systematically assesses the situation and ignores worlds that it has reason to think are impossible for humans. Overall, our new solver can estimate the distinct beliefs of the human and the robot along potential courses of action, enabling the synthesis of plans where the robot selects the right moment for communication, i.e. informing, or replying to an inquiry, or defers ontic actions until the execution experiences can be shared. Preliminary experiments in two domains, one novel and one adapted, demonstrate the effectiveness of the framework., Comment: 15 pages, 4 figures, 1 table

This work studies the product and ratio statistics of independent and non-identically distributed (i.n.i.d) $ \alpha-\kappa - \mu $ shadowed random variables. We derive the series expression for the probability density function (PDF), cumulative distribution function (CDF), and moment generating function (MGF) of the product and ratio of i.n.i.d $ \alpha - \kappa - \mu $ shadowed random variables. We then give the single integral representation for the derived PDF expressions. Further, as application examples, 1) outage probability has been derived for cascaded wireless systems, and 2) physical-layer security metrics like secrecy outage probability and strictly positive secrecy capacity are derived for the classic three-node model with $\alpha-\kappa-\mu$ shadowed fading. Next, we discuss an intelligent reflecting surface-assisted communication system over $\alpha-\kappa-\mu$ shadowed fading., Comment: arXiv admin note: text overlap with arXiv:2203.15760

We explore a discrete-time, coined quantum walk on a quantum network where the coherent superposition of walker-moves originates from the unitary interaction of the walker-coin with the qubit degrees of freedom in the quantum network. The walk dynamics leads to a growth of entanglement between the walker and the network on one hand, and on the other, between the network-qubits among themselves. The initial entanglement among the network qubits plays a crucial role in determining the asymptotic values of these entanglement measures and the quantum walk statistics. Specifically, the entanglement entropy of the walker-network state and the negativity of the quantum network-qubit state saturate to values increasing with the initial network-entanglement. The asymptotic time-averaged walker-position probability distribution shows increasing localization around the initial walker-position with higher initial network entanglement. A potential application of these results as a characterisation tool for quantum network properties is suggested., Comment: Comments welcome

Cellular actin dynamics result from collective action of hundreds of regulatory proteins, majority of which target actin filaments at their barbed ends. Three key actin binding proteins - profilin, cofilin and twinfilin individually depolymerize filament barbed ends. Notwithstanding recent leaps in our understanding of their individual action, how they collectively regulate filament dynamics remains an open question. In absence of direct and simultaneous visualization of these proteins at barbed ends, gaining mechanistic insights has been challenging. We have here investigated multicomponent dynamics of profilin, cofilin and twinfilin using a hybrid approach that combines high throughput single filament experiments with theory. We discovered that while twinfilin competes with profilin, it promotes binding of cofilin to filament sides. Interestingly, contrary to previous expectations, we found that profilin and cofilin can simultaneously bind the same filament barbed end resulting in its accelerated depolymerization. Our study reveals that pair-wise interactions can effectively capture depolymerization dynamics in simultaneous presence of all three proteins. We thus believe that our approach of employing a theory-experiment dialog can potentially help decipher multicomponent regulation of actin dynamics., Comment: Primary research paper

Counterfactual explanations (CFE) are methods that explain a machine learning model by giving an alternate class prediction of a data point with some minimal changes in its features. It helps the users to identify their data attributes that caused an undesirable prediction like a loan or credit card rejection. We describe an efficient and an actionable counterfactual (CF) generation method based on particle swarm optimization (PSO). We propose a simple objective function for the optimization of the instance-centric CF generation problem. The PSO brings in a lot of flexibility in terms of carrying out multi-objective optimization in large dimensions, capability for multiple CF generation, and setting box constraints or immutability of data attributes. An algorithm is proposed that incorporates these features and it enables greater control over the proximity and sparsity properties over the generated CFs. The proposed algorithm is evaluated with a set of action-ability metrics in real-world datasets, and the results were superior compared to that of the state-of-the-arts., Comment: Submitted in IEEE CSDE 2023

Synthetic image datasets offer unmatched advantages for designing and evaluating deep neural networks: they make it possible to (i) render as many data samples as needed, (ii) precisely control each scene and yield granular ground truth labels (and captions), (iii) precisely control distribution shifts between training and testing to isolate variables of interest for sound experimentation. Despite such promise, the use of synthetic image data is still limited -- and often played down -- mainly due to their lack of realism. Most works therefore rely on datasets of real images, which have often been scraped from public images on the internet, and may have issues with regards to privacy, bias, and copyright, while offering little control over how objects precisely appear. In this work, we present a path to democratize the use of photorealistic synthetic data: we develop a new generation of interactive environments for representation learning research, that offer both controllability and realism. We use the Unreal Engine, a powerful game engine well known in the entertainment industry, to produce PUG (Photorealistic Unreal Graphics) environments and datasets for representation learning. In this paper, we demonstrate the potential of PUG to enable more rigorous evaluations of vision models.

The successful analysis of argumentative techniques from user-generated text is central to many downstream tasks such as political and market analysis. Recent argument mining tools use state-of-the-art deep learning methods to extract and annotate argumentative techniques from various online text corpora, however each task is treated as separate and different bespoke models are fine-tuned for each dataset. We show that different argument mining tasks share common semantic and logical structure by implementing a multi-task approach to argument mining that achieves better performance than state-of-the-art methods for the same problems. Our model builds a shared representation of the input text that is common to all tasks and exploits similarities between tasks in order to further boost performance via parameter-sharing. Our results are important for argument mining as they show that different tasks share substantial similarities and suggest a holistic approach to the extraction of argumentative techniques from text.

Joint-embedding based learning (e.g., SimCLR, MoCo, DINO) and reconstruction-based learning (e.g., BEiT, SimMIM, MAE) are the two leading paradigms for self-supervised learning of vision transformers, but they differ substantially in their transfer performance. Here, we aim to explain these differences by analyzing the impact of these objectives on the structure and transferability of the learned representations. Our analysis reveals that reconstruction-based learning features are significantly dissimilar to joint-embedding based learning features and that models trained with similar objectives learn similar features even across architectures. These differences arise early in the network and are primarily driven by attention and normalization layers. We find that joint-embedding features yield better linear probe transfer for classification because the different objectives drive different distributions of information and invariances in the learned representation. These differences explain opposite trends in transfer performance for downstream tasks that require spatial specificity in features. Finally, we address how fine-tuning changes reconstructive representations to enable better transfer, showing that fine-tuning re-organizes the information to be more similar to pre-trained joint embedding models.

Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art with a high barrier to entry. While many components are familiar, successfully training a SSL method involves a dizzying set of choices from the pretext tasks to training hyper-parameters. Our goal is to lower the barrier to entry into SSL research by laying the foundations and latest SSL recipes in the style of a cookbook. We hope to empower the curious researcher to navigate the terrain of methods, understand the role of the various knobs, and gain the know-how required to explore how delicious SSL can be.

Biomedical image segmentation is one of the fastest growing fields which has seen extensive automation through the use of Artificial Intelligence. This has enabled widespread adoption of accurate techniques to expedite the screening and diagnostic processes which would otherwise take several days to finalize. In this paper, we present an end-to-end pipeline to segment lungs from chest X-ray images, training the neural network model on the Japanese Society of Radiological Technology (JSRT) dataset, using UNet to enable faster processing of initial screening for various lung disorders. The pipeline developed can be readily used by medical centers with just the provision of X-Ray images as input. The model will perform the preprocessing, and provide a segmented image as the final output. It is expected that this will drastically reduce the manual effort involved and lead to greater accessibility in resource-constrained locations., Comment: 6 Pages

We design the phase shifts of an intelligent reflecting surface (IRS)-assisted single-input-multiple-output communication system to minimize the outage probability (OP) and to maximize the ergodic rate. Our phase shifts design uses only statistical channel state information since these depend only on the large-scale fading coefficients; the obtained phase shift design remains valid for a longer time frame. We further assume that one has access to only quantized phase values. The closed-form expressions for OP and ergodic rate are derived for the considered system. Next, two optimization problems are formulated to choose the phase shifts of IRS such that (i) OP is minimized and (ii) the ergodic rate is maximized. We used the multi-valued particle swarm optimization (MPSO) and particle swarm optimization (PSO) algorithms to solve the optimization problems. Numerical simulations are performed to study the impact of various parameters on the OP and ergodic rate. We also discuss signaling overhead between BS and IRS controller. It is shown that the overhead can be reduced up to $99.69 \%$ by using statistical CSI for phase shift design and $5$ bits to represent the phase shifts without significantly compromising on the performance.

We consider the human-aware task planning problem where a human-robot team is given a shared task with a known objective to achieve. Recent approaches tackle it by modeling it as a team of independent, rational agents, where the robot plans for both agents' (shared) tasks. However, the robot knows that humans cannot be administered like artificial agents, so it emulates and predicts the human's decisions, actions, and reactions. Based on earlier approaches, we describe a novel approach to solve such problems, which models and uses execution-time observability conventions. Abstractly, this modeling is based on situation assessment, which helps our approach capture the evolution of individual agents' beliefs and anticipate belief divergences that arise in practice. It decides if and when belief alignment is needed and achieves it with communication. These changes improve the solver's performance: (a) communication is effectively used, and (b) robust for more realistic and challenging problems., Comment: 10 pages, 2 figures, 1 table, AI-HRI AAAI 2022 Fall Symposium Series

Recent deep learning approaches in table detection achieved outstanding performance and proved to be effective in identifying document layouts. Currently, available table detection benchmarks have many limitations, including the lack of samples diversity, simple table structure, the lack of training cases, and samples quality. In this paper, we introduce a diverse large-scale dataset for table detection with more than seven thousand samples containing a wide variety of table structures collected from many diverse sources. In addition to that, we also present baseline results using a convolutional neural network-based method to detect table structure in documents. Experimental results show the superiority of applying convolutional deep learning methods over classical computer vision-based methods. The introduction of this diverse table detection dataset will enable the community to develop high throughput deep learning methods for understanding document layout and tabular data processing., Comment: Open source Table detection dataset and baseline results

In this work, we characterize the outage probability (OP) of an intelligent reflecting surface (IRS) assisted multi-user multiple-input-single-output (MU-MISO) communication system. Using a two-step approximation method, we approximate the signal-to-interference-plus-noise ratio (SINR) for any downlink user by a Log-Normal random variable. The impact of various system parameters is studied using the closed-form expression of OP. It is concluded that the position of IRS has a critical role, but an appropriate increase in the number of IRS elements would help to compensate for the loss in performance if the position of IRS is suboptimal.

This paper addresses the challenges of delivering fine-grained Quality of Service (QoS) and communication determinism over 5G wireless networks for real-time and autonomous needs of Industrial Internet of Things (IIoT) applications while effectively sharing network resources. Specifically, this work presents DANSM, a software-defined, dynamic and autonomous network slice management middleware for 5G-based IIoT use cases, such as adaptive robotic repair. Empirical studies evaluating DANSM on our testbed comprising a Free5GC-based core and UERANSIM-based simulations reveal that the software-defined DANSM solution can efficiently balance the traffic load in the data plane thereby reducing the end-to-end response time and improve the service performance by completing 34% more subtasks than a Modified Greedy Algorithm (MGA), 64% more subtasks than First Fit Descending (FFD) and 22% more subtasks than Best Fit Descending (BFD) approaches all while minimizing operational costs., Comment: 8 pages, 8 figures, conference

Widely observed neural scaling laws, in which error falls off as a power of the training set size, model size, or both, have driven substantial performance improvements in deep learning. However, these improvements through scaling alone require considerable costs in compute and energy. Here we focus on the scaling of error with dataset size and show how in theory we can break beyond power law scaling and potentially even reduce it to exponential scaling instead if we have access to a high-quality data pruning metric that ranks the order in which training examples should be discarded to achieve any pruned dataset size. We then test this improved scaling prediction with pruned dataset size empirically, and indeed observe better than power law scaling in practice on ResNets trained on CIFAR-10, SVHN, and ImageNet. Next, given the importance of finding high-quality pruning metrics, we perform the first large-scale benchmarking study of ten different data pruning metrics on ImageNet. We find most existing high performing metrics scale poorly to ImageNet, while the best are computationally intensive and require labels for every image. We therefore developed a new simple, cheap and scalable self-supervised pruning metric that demonstrates comparable performance to the best supervised metrics. Overall, our work suggests that the discovery of good data-pruning metrics may provide a viable path forward to substantially improved neural scaling laws, thereby reducing the resource costs of modern deep learning., Comment: Outstanding Paper Award @ NeurIPS 2022. Added github link to metric scores

In this work, the product of two independent and non-identically distributed (i.n.i.d) $\kappa - \mu $ shadowed random variables is studied. We derive the series expression for the probability density function (PDF), cumulative distribution function (CDF), and moment generating function (MGF) of the product of two (i.n.i.d) $\kappa - \mu $ shadowed random variables. The derived formulation in this work is quite general as they incorporate most of the typically used fading channels. As an application example, outage probability (OP) has been derived for cascaded wireless systems and relay-assisted communications with a variable gain relay. Extensive Monte-Carlo simulations have also been carried out.

In this paper, we present a passive method to detect face presentation attack a.k.a face liveness detection using an ensemble deep learning technique. Face liveness detection is one of the key steps involved in user identity verification of customers during the online onboarding/transaction processes. During identity verification, an unauthenticated user tries to bypass the verification system by several means, for example, they can capture a user photo from social media and do an imposter attack using printouts of users faces or using a digital photo from a mobile device and even create a more sophisticated attack like video replay attack. We have tried to understand the different methods of attack and created an in-house large-scale dataset covering all the kinds of attacks to train a robust deep learning model. We propose an ensemble method where multiple features of the face and background regions are learned to predict whether the user is a bonafide or an attacker., Comment: Accepted and presented at MLDM 2022. To be published in Lattice journal

Most of the machine learning models have associated hyper-parameters along with their parameters. While the algorithm gives the solution for parameters, its utility for model performance is highly dependent on the choice of hyperparameters. For a robust performance of a model, it is necessary to find out the right hyper-parameter combination. Hyper-parameter optimization (HPO) is a systematic process that helps in finding the right values for them. The conventional methods for this purpose are grid search and random search and both methods create issues in industrial-scale applications. Hence a set of strategies have been recently proposed based on Bayesian optimization and evolutionary algorithm principles that help in runtime issues in a production environment and robust performance. In this paper, we compare the performance of four python libraries, namely Optuna, Hyper-opt, Optunity, and sequential model-based algorithm configuration (SMAC) that has been proposed for hyper-parameter optimization. The performance of these tools is tested using two benchmarks. The first one is to solve a combined algorithm selection and hyper-parameter optimization (CASH) problem The second one is the NeurIPS black-box optimization challenge in which a multilayer perception (MLP) architecture has to be chosen from a set of related architecture constraints and hyper-parameters. The benchmarking is done with six real-world datasets. From the experiments, we found that Optuna has better performance for CASH problem and HyperOpt for MLP problem., Comment: Selected and presented at IEEE CSDE 2021. To be published in Proceedings of IEEE CSDE 2021

In this paper, we propose a scheme for the joint optimization of the user transmit power and the antenna selection at the access points (AP)s of a user-centric cell-free massive multiple-input-multiple-output (UC CF-mMIMO) system. We derive an approximate expression for the achievable uplink rate of the users in a UC CF-mMIMO system in the presence of a mixed analog-to-digital converter (ADC) resolution profile at the APs. Using the derived approximation, we propose to maximize the uplink sum rate of UC CF-mMIMO systems subject to energy constraints at the APs. An alternating-optimization solution is proposed using binary particle swarm optimization (BPSO) and successive convex approximation (SCA). We also study the impact of various system parameters on the performance of the system.

Virtual topologies in peer-to-peer networks can reduce the traffic consumed by altering the logical connectivity of peers without altering the underlying network. However, such sparsely connected virtual topologies do not focus on the needs for smart grid applications, which is information dissemination throughout the network, and in turn degrade the performance of distributed control algorithms running on peer-to-peer networks. This paper provides a flexible solution for application developers to prototype and deploy different virtual topologies that balances these trade-offs. First, it introduces a configurable virtual communication topology framework, TopLinkMgr, which enables users to specify any chosen connectivity configuration and deploy peer-to-peer applications using it. Second, it proposes a novel fault-tolerant self-adaptive virtual topology management algorithm, Bounded Path Dissemination, that can ensure the dissemination of information to all peers within a specified threshold. Experiments show that the algorithm improves on convergence speed and accuracy over state-of-the-art methods and is also robust against node failures while consuming significantly less communication bandwidth., Comment: 10 pages, 6 figures