Paper Group ANR 340
The Efficiency of Human Cognition Reflects Planned Information Processing. Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network. SummerTime: Variable-length Time SeriesSummarization with Applications to PhysicalActivity Analysis. Controlled time series generation for automotive software-in-the-loop testing …
The Efficiency of Human Cognition Reflects Planned Information Processing
| Title | The Efficiency of Human Cognition Reflects Planned Information Processing |
| Authors | Mark K. Ho, David Abel, Jonathan D. Cohen, Michael L. Littman, Thomas L. Griffiths |
| Abstract | Planning is useful. It lets people take actions that have desirable long-term consequences. But, planning is hard. It requires thinking about consequences, which consumes limited computational and cognitive resources. Thus, people should plan their actions, but they should also be smart about how they deploy resources used for planning their actions. Put another way, people should also “plan their plans”. Here, we formulate this aspect of planning as a meta-reasoning problem and formalize it in terms of a recursive Bellman objective that incorporates both task rewards and information-theoretic planning costs. Our account makes quantitative predictions about how people should plan and meta-plan as a function of the overall structure of a task, which we test in two experiments with human participants. We find that people’s reaction times reflect a planned use of information processing, consistent with our account. This formulation of planning to plan provides new insight into the function of hierarchical planning, state abstraction, and cognitive control in both humans and machines. |
| Tasks | |
| Published | 2020-02-13 |
| URL | https://arxiv.org/abs/2002.05769v1 |
| https://arxiv.org/pdf/2002.05769v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-efficiency-of-human-cognition-reflects |
| Repo | |
| Framework | |
Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network
| Title | Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network |
| Authors | Weiqi Ji, Sili Deng |
| Abstract | The inference of chemical reaction networks is an important task in understanding the chemical processes in life sciences and environment. Yet, only a few reaction systems are well-understood due to a large number of important reaction pathways involved but still unknown. Revealing unknown reaction pathways is an important task for scientific discovery that takes decades and requires lots of expert knowledge. This work presents a neural network approach for discovering unknown reaction pathways from concentration time series data. The neural network denoted as Chemical Reaction Neural Network (CRNN), is designed to be equivalent to chemical reaction networks by following the fundamental physics laws of the Law of Mass Action and Arrhenius Law. The CRNN is physically interpretable, and its weights correspond to the reaction pathways and rate constants of the chemical reaction network. Then, inferencing the reaction pathways and the rate constants are accomplished by training the equivalent CRNN via stochastic gradient descent. The approach precludes the need for expert knowledge in proposing candidate reactions, such that the inference is autonomous and applicable to new systems for which there is no existing empirical knowledge to propose reaction pathways. The physical interpretability also makes the CRNN not only capable of fitting the data for a given system but also developing knowledge of unknown pathways that could be generalized to similar chemical systems. Finally, the approach is applied to several chemical systems in chemical engineering and biochemistry to demonstrate its robustness and generality. |
| Tasks | Time Series |
| Published | 2020-02-20 |
| URL | https://arxiv.org/abs/2002.09062v1 |
| https://arxiv.org/pdf/2002.09062v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-discovery-of-unknown-reaction |
| Repo | |
| Framework | |
SummerTime: Variable-length Time SeriesSummarization with Applications to PhysicalActivity Analysis
| Title | SummerTime: Variable-length Time SeriesSummarization with Applications to PhysicalActivity Analysis |
| Authors | Kevin M. Amaral, Zihan Li, Wei Ding, Scott Crouter, Ping Chen |
| Abstract | \textit{SummerTime} seeks to summarize globally time series signals and provides a fixed-length, robust summarization of the variable-length time series. Many classical machine learning methods for classification and regression depend on data instances with a fixed number of features. As a result, those methods cannot be directly applied to variable-length time series data. One common approach is to perform classification over a sliding window on the data and aggregate the decisions made at local sections of the time series in some way, through majority voting for classification or averaging for regression. The downside to this approach is that minority local information is lost in the voting process and averaging assumes that each time series measurement is equal in significance. Also, since time series can be of varying length, the quality of votes and averages could vary greatly in cases where there is a close voting tie or bimodal distribution of regression domain. Summarization conducted by the \textit{SummerTime} method will be a fixed-length feature vector which can be used in-place of the time series dataset for use with classical machine learning methods. We use Gaussian Mixture models (GMM) over small same-length disjoint windows in the time series to group local data into clusters. The time series’ rate of membership for each cluster will be a feature in the summarization. The model is naturally capable of converging to an appropriate cluster count. We compare our results to state-of-the-art studies in physical activity classification and show high-quality improvement by classifying with only the summarization. Finally, we show that regression using the summarization can augment energy expenditure estimation, producing more robust and precise results. |
| Tasks | Time Series |
| Published | 2020-02-20 |
| URL | https://arxiv.org/abs/2002.09000v1 |
| https://arxiv.org/pdf/2002.09000v1.pdf | |
| PWC | https://paperswithcode.com/paper/summertime-variable-length-time |
| Repo | |
| Framework | |
Controlled time series generation for automotive software-in-the-loop testing using GANs
| Title | Controlled time series generation for automotive software-in-the-loop testing using GANs |
| Authors | Dhasarathy Parthasarathy, Karl Bäckström, Jens Henriksson, Sólrún Einarsdóttir |
| Abstract | Testing automotive mechatronic systems partly uses the software-in-the-loop approach, where systematically covering inputs of the system-under-test remains a major challenge. In current practice, there are two major techniques of input stimulation. One approach is to craft input sequences which eases control and feedback of the test process but falls short of exposing the system to realistic scenarios. The other is to replay sequences recorded from field operations which accounts for reality but requires collecting a well-labeled dataset of sufficient capacity for widespread use, which is expensive. This work applies the well-known unsupervised learning framework of Generative Adversarial Networks (GAN) to learn an unlabeled dataset of recorded in-vehicle signals and uses it for generation of synthetic input stimuli. Additionally, a metric-based linear interpolation algorithm is demonstrated, which guarantees that generated stimuli follow a customizable similarity relationship with specified references. This combination of techniques enables controlled generation of a rich range of meaningful and realistic input patterns, improving virtual test coverage and reducing the need for expensive field tests. |
| Tasks | Time Series |
| Published | 2020-02-16 |
| URL | https://arxiv.org/abs/2002.06611v2 |
| https://arxiv.org/pdf/2002.06611v2.pdf | |
| PWC | https://paperswithcode.com/paper/controlled-time-series-generation-for |
| Repo | |
| Framework | |
Generalized Product Quantization Network for Semi-supervised Image Retrieval
| Title | Generalized Product Quantization Network for Semi-supervised Image Retrieval |
| Authors | Young Kyun Jang, Nam Ik Cho |
| Abstract | Image retrieval methods that employ hashing or vector quantization have achieved great success by taking advantage of deep learning. However, these approaches do not meet expectations unless expensive label information is sufficient. To resolve this issue, we propose the first quantization-based semi-supervised image retrieval scheme: Generalized Product Quantization (GPQ) network. We design a novel metric learning strategy that preserves semantic similarity between labeled data, and employ entropy regularization term to fully exploit inherent potentials of unlabeled data. Our solution increases the generalization capacity of the quantization network, which allows overcoming previous limitations in the retrieval community. Extensive experimental results demonstrate that GPQ yields state-of-the-art performance on large-scale real image benchmark datasets. |
| Tasks | Image Retrieval, Metric Learning, Quantization, Semantic Similarity, Semantic Textual Similarity |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11281v2 |
| https://arxiv.org/pdf/2002.11281v2.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-product-quantization-network-for |
| Repo | |
| Framework | |
Variational Conditional-Dependence Hidden Markov Models for Human Action Recognition
| Title | Variational Conditional-Dependence Hidden Markov Models for Human Action Recognition |
| Authors | Konstantinos P. Panousis, Sotirios Chatzis, Sergios Theodoridis |
| Abstract | Hidden Markov Models (HMMs) are a powerful generative approach for modeling sequential data and time-series in general. However, the commonly employed assumption of the dependence of the current time frame to a single or multiple immediately preceding frames is unrealistic; more complicated dynamics potentially exist in real world scenarios. Human Action Recognition constitutes such a scenario, and has attracted increased attention with the advent of low-cost 3D sensors. The naturally arising variations and complex temporal dependencies have established this task as a challenging problem in the community. This paper revisits conventional sequential modeling approaches, aiming to address the problem of capturing time-varying temporal dependency patterns. To this end, we propose a different formulation of HMMs, whereby the dependence on past frames is dynamically inferred from the data. Specifically, we introduce a hierarchical extension by postulating an additional latent variable layer; therein, the (time-varying) temporal dependence patterns are treated as latent variables over which inference is performed. We leverage solid arguments from the Variational Bayes framework and derive a tractable inference algorithm based on the forward-backward algorithm. As we experimentally show using benchmark datasets, our approach yields competitive recognition accuracy and can effectively handle data with missing values. |
| Tasks | Temporal Action Localization, Time Series |
| Published | 2020-02-13 |
| URL | https://arxiv.org/abs/2002.05809v1 |
| https://arxiv.org/pdf/2002.05809v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-conditional-dependence-hidden |
| Repo | |
| Framework | |
Online Learning of the Kalman Filter with Logarithmic Regret
| Title | Online Learning of the Kalman Filter with Logarithmic Regret |
| Authors | Anastasios Tsiamis, George Pappas |
| Abstract | In this paper, we consider the problem of predicting observations generated online by an unknown, partially observed linear system, which is driven by stochastic noise. For such systems the optimal predictor in the mean square sense is the celebrated Kalman filter, which can be explicitly computed when the system model is known. When the system model is unknown, we have to learn how to predict observations online based on finite data, suffering possibly a non-zero regret with respect to the Kalman filter’s prediction. We show that it is possible to achieve a regret of the order of $\mathrm{poly}\log(N)$ with high probability, where $N$ is the number of observations collected. Our work is the first to provide logarithmic regret guarantees for the widely used Kalman filter. This is achieved using an online least-squares algorithm, which exploits the approximately linear relation between future observations and past observations. The regret analysis is based on the stability properties of the Kalman filter, recent statistical tools for finite sample analysis of system identification, and classical results for the analysis of least-squares algorithms for time series. Our regret analysis can also be applied for state prediction of the hidden state, in the case of unknown noise statistics but known state-space basis. A fundamental technical contribution is that our bounds hold even for the class of non-explosive systems, which includes the class of marginally stable systems, which was an open problem for the case of online prediction under stochastic noise. |
| Tasks | Time Series |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.05141v1 |
| https://arxiv.org/pdf/2002.05141v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-learning-of-the-kalman-filter-with |
| Repo | |
| Framework | |
Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer
| Title | Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer |
| Authors | Ori Press, Tomer Galanti, Sagie Benaim, Lior Wolf |
| Abstract | We study the problem of learning to map, in an unsupervised way, between domains A and B, such that the samples b in B contain all the information that exists in samples a in A and some additional information. For example, ignoring occlusions, B can be people with glasses, A people without, and the glasses, would be the added information. When mapping a sample a from the first domain to the other domain, the missing information is replicated from an independent reference sample b in B. Thus, in the above example, we can create, for every person without glasses a version with the glasses observed in any face image. Our solution employs a single two-pathway encoder and a single decoder for both domains. The common part of the two domains and the separate part are encoded as two vectors, and the separate part is fixed at zero for domain A. The loss terms are minimal and involve reconstruction losses for the two domains and a domain confusion term. Our analysis shows that under mild assumptions, this architecture, which is much simpler than the literature guided-translation methods, is enough to ensure disentanglement between the two domains. We present convincing results in a few visual domains, such as no-glasses to glasses, adding facial hair based on a reference image, etc. |
| Tasks | |
| Published | 2020-01-14 |
| URL | https://arxiv.org/abs/2001.05017v1 |
| https://arxiv.org/pdf/2001.05017v1.pdf | |
| PWC | https://paperswithcode.com/paper/emerging-disentanglement-in-auto-encoder-1 |
| Repo | |
| Framework | |
Machine Learning for Predicting Epileptic Seizures Using EEG Signals: A Review
| Title | Machine Learning for Predicting Epileptic Seizures Using EEG Signals: A Review |
| Authors | Khansa Rasheed, Adnan Qayyum, Junaid Qadir, Shobi Sivathamboo, Patrick Kwan, Levin Kuhlmann, Terence O’Brien, Adeel Razi |
| Abstract | With the advancement in artificial intelligence (AI) and machine learning (ML) techniques, researchers are striving towards employing these techniques for advancing clinical practice. One of the key objectives in healthcare is the early detection and prediction of disease to timely provide preventive interventions. This is especially the case for epilepsy, which is characterized by recurrent and unpredictable seizures. Patients can be relieved from the adverse consequences of epileptic seizures if it could somehow be predicted in advance. Despite decades of research, seizure prediction remains an unsolved problem. This is likely to remain at least partly because of the inadequate amount of data to resolve the problem. There have been exciting new developments in ML-based algorithms that have the potential to deliver a paradigm shift in the early and accurate prediction of epileptic seizures. Here we provide a comprehensive review of state-of-the-art ML techniques in early prediction of seizures using EEG signals. We will identify the gaps, challenges, and pitfalls in the current research and recommend future directions. |
| Tasks | EEG, Seizure prediction |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01925v1 |
| https://arxiv.org/pdf/2002.01925v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-predicting-epileptic |
| Repo | |
| Framework | |
End-to-End Velocity Estimation For Autonomous Racing
| Title | End-to-End Velocity Estimation For Autonomous Racing |
| Authors | Sirish Srinivasan, Inkyu Sa, Alex Zyner, Victor Reijgwart, Miguel I. Valls, Roland Siegwart |
| Abstract | Velocity estimation plays a central role in driverless vehicles, but standard and affordable methods struggle to cope with extreme scenarios like aggressive maneuvers due to the presence of high sideslip. To solve this, autonomous race cars are usually equipped with expensive external velocity sensors. In this paper, we present an end-to-end recurrent neural network that takes available raw sensors as input (IMU, wheel odometry, and motor currents) and outputs velocity estimates. The results are compared to two state-of-the-art Kalman filters, which respectively include and exclude expensive velocity sensors. All methods have been extensively tested on a formula student driverless race car with very high sideslip (10{\deg} at the rear axle) and slip ratio (~20%), operating close to the limits of handling. The proposed network is able to estimate lateral velocity up to 15x better than the Kalman filter with the equivalent sensor input and matches (0.06 m/s RMSE) the Kalman filter with the expensive velocity sensor setup. |
| Tasks | |
| Published | 2020-03-15 |
| URL | https://arxiv.org/abs/2003.06917v1 |
| https://arxiv.org/pdf/2003.06917v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-velocity-estimation-for-autonomous |
| Repo | |
| Framework | |
Fully convolutional networks for structural health monitoring through multivariate time series classification
| Title | Fully convolutional networks for structural health monitoring through multivariate time series classification |
| Authors | Luca Rosafalco, Andrea Manzoni, Stefano Mariani, Alberto Corigliano |
| Abstract | We propose a novel approach to Structural Health Monitoring (SHM), aiming at the automatic identification of damage-sensitive features from data acquired through pervasive sensor systems. Damage detection and localization are formulated as classification problems, and tackled through Fully Convolutional Networks (FCNs). A supervised training of the proposed network architecture is performed on data extracted from numerical simulations of a physics-based model (playing the role of digital twin of the structure to be monitored) accounting for different damage scenarios. By relying on this simplified model of the structure, several load conditions are considered during the training phase of the FCN, whose architecture has been designed to deal with time series of different length. The training of the neural network is done before the monitoring system starts operating, thus enabling a real time damage classification. The numerical performances of the proposed strategy are assessed on a numerical benchmark case consisting of an eight-story shear building subjected to two load types, one of which modeling random vibrations due to low-energy seismicity. Measurement noise has been added to the responses of the structure to mimic the outputs of a real monitoring system. Extremely good classification capacities are shown: among the nine possible alternatives (represented by the healthy state and by a damage at any floor), damage is correctly classified in up to 95% of cases, thus showing the strong potential of the proposed approach in view of the application to real-life cases. |
| Tasks | Time Series, Time Series Classification |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.07032v1 |
| https://arxiv.org/pdf/2002.07032v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-convolutional-networks-for-structural |
| Repo | |
| Framework | |
Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery
| Title | Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery |
| Authors | Jingwei Song, Jun Wang, Liang Zhao, Shoudong Huang, Gamini Dissanayake |
| Abstract | In minimal invasive surgery, it is important to rebuild and visualize the latest deformed shape of soft-tissue surfaces to mitigate tissue damages. This paper proposes an innovative Simultaneous Localization and Mapping (SLAM) algorithm for deformable dense reconstruction of surfaces using a sequence of images from a stereoscope. We introduce a warping field based on the Embedded Deformation (ED) nodes with 3D shapes recovered from consecutive pairs of stereo images. The warping field is estimated by deforming the last updated model to the current live model. Our SLAM system can: (1) Incrementally build a live model by progressively fusing new observations with vivid accurate texture. (2) Estimate the deformed shape of unobserved region with the principle As-Rigid-As-Possible. (3) Show the consecutive shape of models. (4) Estimate the current relative pose between the soft-tissue and the scope. In-vivo experiments with publicly available datasets demonstrate that the 3D models can be incrementally built for different soft-tissues with different deformations from sequences of stereo images obtained by laparoscopes. Results show the potential clinical application of our SLAM system for providing surgeon useful shape and texture information in minimal invasive surgery. |
| Tasks | Simultaneous Localization and Mapping |
| Published | 2020-03-22 |
| URL | https://arxiv.org/abs/2003.10867v1 |
| https://arxiv.org/pdf/2003.10867v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-reconstruction-of-deformable-soft |
| Repo | |
| Framework | |
Syntactically Look-Ahead Attention Network for Sentence Compression
| Title | Syntactically Look-Ahead Attention Network for Sentence Compression |
| Authors | Hidetaka Kamigaito, Manabu Okumura |
| Abstract | Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words. In sequence-to-sequence (Seq2Seq) based models, the decoder unidirectionally decides to retain or delete words. Thus, it cannot usually explicitly capture the relationships between decoded words and unseen words that will be decoded in the future time steps. Therefore, to avoid generating ungrammatical sentences, the decoder sometimes drops important words in compressing sentences. To solve this problem, we propose a novel Seq2Seq model, syntactically look-ahead attention network (SLAHAN), that can generate informative summaries by explicitly tracking both dependency parent and child words during decoding and capturing important words that will be decoded in the future. The results of the automatic evaluation on the Google sentence compression dataset showed that SLAHAN achieved the best kept-token-based-F1, ROUGE-1, ROUGE-2 and ROUGE-L scores of 85.5, 79.3, 71.3 and 79.1, respectively. SLAHAN also improved the summarization performance on longer sentences. Furthermore, in the human evaluation, SLAHAN improved informativeness without losing readability. |
| Tasks | Sentence Compression |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01145v1 |
| https://arxiv.org/pdf/2002.01145v1.pdf | |
| PWC | https://paperswithcode.com/paper/syntactically-look-ahead-attention-network |
| Repo | |
| Framework | |
Human Perception of Intrinsically Motivated Autonomy in Human-Robot Interaction
| Title | Human Perception of Intrinsically Motivated Autonomy in Human-Robot Interaction |
| Authors | Marcus M. Scheunemann, Christoph Salge, Daniel Polani, Kerstin Dautenhahn |
| Abstract | A challenge in using fully autonomous robots in human-robot interaction (HRI) is to design behavior that is engaging enough to encourage voluntary, long-term interaction, yet robust to the perturbations induced by human interaction. Here we evaluate if an intrinsically motivated, physical robot can address this challenge. We use predictive information maximization as an intrinsic motivation, as simulated experiments showed that this leads to playful, exploratory behavior that is robust to changes in the robot’s morphology and environment. To the authors’ knowledge there are no previous HRI studies that evaluate the effect of intrinsically motivated behavior in robots on the human perception of those robots. We present a game-like study design, which allows us to focus on the interplay between the robot and the human participant. In contrast to a study design where participants order or control a robot to do a specific task, the robot and the human participants in our study design explore their behaviors without knowledge about any specific goals. We conducted a within-subjects study (N=24) were participants interacted with a fully autonomous Sphero BB8 robot with different behavioral regimes: one realizing an adaptive, intrinsically motivated behavior and the other being reactive, but not adaptive. A quantitative analysis of post-interaction questionnaires showed a significantly higher perception (r=.555, p=.007) of the dimension “Warmth” compared to the baseline behavior. Warmth is considered a primary dimension for social attitude formation in human cognition. A human perceived as warm (i.e. friendly and trustworthy) experiences more positive social interactions. If future work demonstrates that this transfers to human-robot social cognition, then the generic methods presented here could be used to imbue robots with behavior leading to positive perception by humans. |
| Tasks | |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2002.05936v1 |
| https://arxiv.org/pdf/2002.05936v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-perception-of-intrinsically-motivated |
| Repo | |
| Framework | |
Residual Bootstrap Exploration for Bandit Algorithms
| Title | Residual Bootstrap Exploration for Bandit Algorithms |
| Authors | Chi-Hua Wang, Yang Yu, Botao Hao, Guang Cheng |
| Abstract | In this paper, we propose a novel perturbation-based exploration method in bandit algorithms with bounded or unbounded rewards, called residual bootstrap exploration (\texttt{ReBoot}). The \texttt{ReBoot} enforces exploration by injecting data-driven randomness through a residual-based perturbation mechanism. This novel mechanism captures the underlying distributional properties of fitting errors, and more importantly boosts exploration to escape from suboptimal solutions (for small sample sizes) by inflating variance level in an \textit{unconventional} way. In theory, with appropriate variance inflation level, \texttt{ReBoot} provably secures instance-dependent logarithmic regret in Gaussian multi-armed bandits. We evaluate the \texttt{ReBoot} in different synthetic multi-armed bandits problems and observe that the \texttt{ReBoot} performs better for unbounded rewards and more robustly than \texttt{Giro} \cite{kveton2018garbage} and \texttt{PHE} \cite{kveton2019perturbed}, with comparable computational efficiency to the Thompson sampling method. |
| Tasks | Multi-Armed Bandits |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.08436v1 |
| https://arxiv.org/pdf/2002.08436v1.pdf | |
| PWC | https://paperswithcode.com/paper/residual-bootstrap-exploration-for-bandit |
| Repo | |
| Framework | |
