Paper Group ANR 218
Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning. Gunrock: A Social Bot for Complex and Engaging Long Conversations. Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition. Some Developments in Clustering Analysis on Stochastic Processes. Differentiable Learning-to-Group Channels via Groupable Convo …
Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning
| Title | Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning |
| Authors | Dexter R. R. Scobee, S. Shankar Sastry |
| Abstract | While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent’s policy or demonstrated behavior on a control task, it is often the case that such behavior is more succinctly described by a simple reward combined with a set of hard constraints. In this setting, the agent is attempting to maximize cumulative rewards subject to these given constraints on their behavior. We reformulate the problem of IRL on Markov Decision Processes (MDPs) such that, given a nominal model of the environment and a nominal reward function, we seek to estimate state, action, and feature constraints in the environment that motivate an agent’s behavior. Our approach is based on the Maximum Entropy IRL framework, which allows us to reason about the likelihood of an expert agent’s demonstrations given our knowledge of an MDP. Using our method, we can infer which constraints can be added to the MDP to most increase the likelihood of observing these demonstrations. We present an algorithm which iteratively infers the Maximum Likelihood Constraint to best explain observed behavior, and we evaluate its efficacy using both simulated behavior and recorded data of humans navigating around an obstacle. |
| Tasks | |
| Published | 2019-09-12 |
| URL | https://arxiv.org/abs/1909.05477v1 |
| https://arxiv.org/pdf/1909.05477v1.pdf | |
| PWC | https://paperswithcode.com/paper/maximum-likelihood-constraint-inference-for |
| Repo | |
| Framework | |
Gunrock: A Social Bot for Complex and Engaging Long Conversations
| Title | Gunrock: A Social Bot for Complex and Engaging Long Conversations |
| Authors | Dian Yu, Michelle Cohn, Yi Mang Yang, Chun-Yen Chen, Weiming Wen, Jiaping Zhang, Mingyang Zhou, Kevin Jesse, Austin Chau, Antara Bhowmick, Shreenath Iyer, Giritheja Sreenivasulu, Sam Davidson, Ashwin Bhandare, Zhou Yu |
| Abstract | Gunrock is the winner of the 2018 Amazon Alexa Prize, as evaluated by coherence and engagement from both real users and Amazon-selected expert conversationalists. We focus on understanding complex sentences and having in-depth conversations in open domains. In this paper, we introduce some innovative system designs and related validation analysis. Overall, we found that users produce longer sentences to Gunrock, which are directly related to users’ engagement (e.g., ratings, number of turns). Additionally, users’ backstory queries about Gunrock are positively correlated to user satisfaction. Finally, we found dialog flows that interleave facts and personal opinions and stories lead to better user satisfaction. |
| Tasks | |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.03042v1 |
| https://arxiv.org/pdf/1910.03042v1.pdf | |
| PWC | https://paperswithcode.com/paper/gunrock-a-social-bot-for-complex-and-engaging |
| Repo | |
| Framework | |
Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition
| Title | Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition |
| Authors | Jibin Wu, Emre Yilmaz, Malu Zhang, Haizhou Li, Kay Chen Tan |
| Abstract | Artificial neural networks (ANN) have become the mainstream acoustic modeling technique for large vocabulary automatic speech recognition (ASR). A conventional ANN features a multi-layer architecture that requires massive amounts of computation. The brain-inspired spiking neural networks (SNN) closely mimic the biological neural networks and can operate on low-power neuromorphic hardware with spike-based computation. Motivated by their unprecedented energyefficiency and rapid information processing capability, we explore the use of SNNs for speech recognition. In this work, we use SNNs for acoustic modeling and evaluate their performance on several large vocabulary recognition scenarios. The experimental results demonstrate competitive ASR accuracies to their ANN counterparts, while require significantly reduced computational cost and inference time. Integrating the algorithmic power of deep SNNs with energy-efficient neuromorphic hardware, therefore, offer an attractive solution for ASR applications running locally on mobile and embedded devices. |
| Tasks | Speech Recognition |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08373v1 |
| https://arxiv.org/pdf/1911.08373v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-spiking-neural-networks-for-large |
| Repo | |
| Framework | |
Some Developments in Clustering Analysis on Stochastic Processes
| Title | Some Developments in Clustering Analysis on Stochastic Processes |
| Authors | Qidi Peng, Nan Rao, Ran Zhao |
| Abstract | We review some developments on clustering stochastic processes and come with the conclusion that asymptotically consistent clustering algorithms can be obtained when the processes are ergodic and the dissimilarity measure satisfies the triangle inequality. Examples are provided when the processes are distribution ergodic, covariance ergodic and locally asymptotically self-similar, respectively. |
| Tasks | |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1908.01794v1 |
| https://arxiv.org/pdf/1908.01794v1.pdf | |
| PWC | https://paperswithcode.com/paper/some-developments-in-clustering-analysis-on |
| Repo | |
| Framework | |
Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks
| Title | Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks |
| Authors | Zhaoyang Zhang, Jingyu Li, Wenqi Shao, Zhanglin Peng, Ruimao Zhang, Xiaogang Wang, Ping Luo |
| Abstract | Group convolution, which divides the channels of ConvNets into groups, has achieved impressive improvement over the regular convolution operation. However, existing models, eg. ResNeXt, still suffers from the sub-optimal performance due to manually defining the number of groups as a constant over all of the layers. Toward addressing this issue, we present Groupable ConvNet (GroupNet) built by using a novel dynamic grouping convolution (DGConv) operation, which is able to learn the number of groups in an end-to-end manner. The proposed approach has several appealing benefits. (1) DGConv provides a unified convolution representation and covers many existing convolution operations such as regular dense convolution, group convolution, and depthwise convolution. (2) DGConv is a differentiable and flexible operation which learns to perform various convolutions from training data. (3) GroupNet trained with DGConv learns different number of groups for different convolution layers. Extensive experiments demonstrate that GroupNet outperforms its counterparts such as ResNet and ResNeXt in terms of accuracy and computational complexity. We also present introspection and reproducibility study, for the first time, showing the learning dynamics of training group numbers. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.05867v2 |
| https://arxiv.org/pdf/1908.05867v2.pdf | |
| PWC | https://paperswithcode.com/paper/differentiable-learning-to-group-channels |
| Repo | |
| Framework | |
Finding Social Media Trolls: Dynamic Keyword Selection Methods for Rapidly-Evolving Online Debates
| Title | Finding Social Media Trolls: Dynamic Keyword Selection Methods for Rapidly-Evolving Online Debates |
| Authors | Anqi Liu, Maya Srikanth, Nicholas Adams-Cohen, R. Michael Alvarez, Anima Anandkumar |
| Abstract | Online harassment is a significant social problem. Prevention of online harassment requires rapid detection of harassing, offensive, and negative social media posts. In this paper, we propose the use of word embedding models to identify offensive and harassing social media messages in two aspects: detecting fast-changing topics for more effective data collection and representing word semantics in different domains. We demonstrate with preliminary results that using the GloVe (Global Vectors for Word Representation) model facilitates the discovery of new and relevant keywords to use for data collection and trolling detection. Our paper concludes with a discussion of a research agenda to further develop and test word embedding models for identification of social media harassment and trolling. |
| Tasks | |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.05332v2 |
| https://arxiv.org/pdf/1911.05332v2.pdf | |
| PWC | https://paperswithcode.com/paper/finding-social-media-trolls-dynamic-keyword |
| Repo | |
| Framework | |
Query Complexity of Bayesian Private Learning
| Title | Query Complexity of Bayesian Private Learning |
| Authors | Kuang Xu |
| Abstract | We study the query complexity of Bayesian Private Learning: a learner wishes to locate a random target within an interval by submitting queries, in the presence of an adversary who observes all of her queries but not the responses. How many queries are necessary and sufficient in order for the learner to accurately estimate the target, while simultaneously concealing the target from the adversary? Our main result is a query complexity lower bound that is tight up to the first order. We show that if the learner wants to estimate the target within an error of $\varepsilon$, while ensuring that no adversary estimator can achieve a constant additive error with probability greater than $1/L$, then the query complexity is on the order of $L\log(1/\varepsilon)$, as $\varepsilon \to 0$. Our result demonstrates that increased privacy, as captured by $L$, comes at the expense of a {multiplicative} increase in query complexity. Our proof method builds on Fano’s inequality and a family of proportional-sampling estimators. As an illustration of the method’s wider applicability, we generalize the complexity lower bound to settings involving high-dimensional linear query learning and partial adversary observation. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06903v1 |
| https://arxiv.org/pdf/1911.06903v1.pdf | |
| PWC | https://paperswithcode.com/paper/query-complexity-of-bayesian-private-learning-1 |
| Repo | |
| Framework | |
Mining Closed Episodes with Simultaneous Events
| Title | Mining Closed Episodes with Simultaneous Events |
| Authors | Nikolaj Tatti, Boris Cule |
| Abstract | Sequential pattern discovery is a well-studied field in data mining. Episodes are sequential patterns describing events that often occur in the vicinity of each other. Episodes can impose restrictions to the order of the events, which makes them a versatile technique for describing complex patterns in the sequence. Most of the research on episodes deals with special cases such as serial, parallel, and injective episodes, while discovering general episodes is understudied. In this paper we extend the definition of an episode in order to be able to represent cases where events often occur simultaneously. We present an efficient and novel miner for discovering frequent and closed general episodes. Such a task presents unique challenges. Firstly, we cannot define closure based on frequency. We solve this by computing a more conservative closure that we use to reduce the search space and discover the closed episodes as a postprocessing step. Secondly, episodes are traditionally presented as directed acyclic graphs. We argue that this representation has drawbacks leading to redundancy in the output. We solve these drawbacks by defining a subset relationship in such a way that allows us to remove the redundant episodes. We demonstrate the efficiency of our algorithm and the need for using closed episodes empirically on synthetic and real-world datasets. |
| Tasks | |
| Published | 2019-04-16 |
| URL | http://arxiv.org/abs/1904.08741v1 |
| http://arxiv.org/pdf/1904.08741v1.pdf | |
| PWC | https://paperswithcode.com/paper/mining-closed-episodes-with-simultaneous |
| Repo | |
| Framework | |
Learning spatiotemporal signals using a recurrent spiking network that discretizes time
| Title | Learning spatiotemporal signals using a recurrent spiking network that discretizes time |
| Authors | Amadeus Maes, Mauricio Barahona, Claudia Clopath |
| Abstract | Learning to produce spatiotemporal sequences is a common task that the brain has to solve. The same neural substrate may be used by the brain to produce different sequential behaviours. The way the brain learns and encodes such tasks remains unknown as current computational models do not typically use realistic biologically-plausible learning. Here, we propose a model where a spiking recurrent network of excitatory and inhibitory biophysical neurons drives a read-out layer: the dynamics of the driver recurrent network is trained to encode time which is then mapped through the read-out neurons to encode another dimension, such as space or a phase. Different spatiotemporal patterns can be learned and encoded through the synaptic weights to the read-out neurons that follow common Hebbian learning rules. We demonstrate that the model is able to learn spatiotemporal dynamics on time scales that are behaviourally relevant and we show that the learned sequences are robustly replayed during a regime of spontaneous activity. |
| Tasks | |
| Published | 2019-07-20 |
| URL | https://arxiv.org/abs/1907.08801v2 |
| https://arxiv.org/pdf/1907.08801v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-spatiotemporal-signals-using-a |
| Repo | |
| Framework | |
Unsupervised Domain Adaptation by Optical Flow Augmentation in Semantic Segmentation
| Title | Unsupervised Domain Adaptation by Optical Flow Augmentation in Semantic Segmentation |
| Authors | Oluwafemi Azeez |
| Abstract | It is expensive to generate real-life image labels and there is a domain gap between real-life and simulated images, hence a model trained on the latter cannot adapt to the former. Solving this can totally eliminate the need for labeling real-life datasets completely. Class balanced self-training is one of the existing techniques that attempt to reduce the domain gap. Moreover, augmenting RGB with flow maps has improved performance in simple semantic segmentation and geometry is preserved across domains. Hence, by augmenting images with dense optical flow map, domain adaptation in semantic segmentation can be improved. |
| Tasks | Domain Adaptation, Optical Flow Estimation, Semantic Segmentation, Unsupervised Domain Adaptation |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.09652v1 |
| https://arxiv.org/pdf/1911.09652v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-by-optical |
| Repo | |
| Framework | |
Spatially Constrained Spectral Clustering Algorithms for Region Delineation
| Title | Spatially Constrained Spectral Clustering Algorithms for Region Delineation |
| Authors | Shuai Yuan, Pang-Ning Tan, Kendra Spence Cheruvelil, Sarah M. Collins, Patricia A. Soranno |
| Abstract | Regionalization is the task of dividing up a landscape into homogeneous patches with similar properties. Although this task has a wide range of applications, it has two notable challenges. First, it is assumed that the resulting regions are both homogeneous and spatially contiguous. Second, it is well-recognized that landscapes are hierarchical such that fine-scale regions are nested wholly within broader-scale regions. To address these two challenges, first, we develop a spatially constrained spectral clustering framework for region delineation that incorporates the tradeoff between region homogeneity and spatial contiguity. The framework uses a flexible, truncated exponential kernel to represent the spatial contiguity constraints, which is integrated with the landscape feature similarity matrix for region delineation. To address the second challenge, we extend the framework to create fine-scale regions that are nested within broader-scaled regions using a greedy, recursive bisection approach. We present a case study of a terrestrial ecology data set in the United States that compares the proposed framework with several baseline methods for regionalization. Experimental results suggest that the proposed framework for regionalization outperforms the baseline methods, especially in terms of balancing region contiguity and homogeneity, as well as creating regions of more similar size, which is often a desired trait of regions. |
| Tasks | |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08451v1 |
| https://arxiv.org/pdf/1905.08451v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatially-constrained-spectral-clustering |
| Repo | |
| Framework | |
A Parametric Perceptual Deficit Modeling and Diagnostics Framework for Retina Damage using Mixed Reality
| Title | A Parametric Perceptual Deficit Modeling and Diagnostics Framework for Retina Damage using Mixed Reality |
| Authors | Prithul Aniruddha, Nasif Zaman, Alireza Tavakkoli, Stewart Zuckerbrod |
| Abstract | Age-related Macular Degeneration (AMD) is a progressive visual impairment affecting millions of individuals. Since there is no current treatment for the disease, the only means of improving the lives of individuals suffering from the disease is via assistive technologies. In this paper we propose a novel and effective methodology to accurately generate a parametric model for the perceptual deficit caused by the physiological deterioration of a patient’s retina due to AMD. Based on the parameters of the model, a mechanism is developed to simulate the patient’s perception as a result of the disease. This simulation can effectively deliver the perceptual impact and its progression to the patient’s eye doctor. In addition, we propose a mixed-reality apparatus and interface to allow the patient recover functional vision and to compensate for the perceptual loss caused by the physiological damage. The results obtained by the proposed approach show the superiority of our framework over the state-of-the-art low-vision systems. |
| Tasks | |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.07688v1 |
| https://arxiv.org/pdf/1910.07688v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-parametric-perceptual-deficit-modeling-and |
| Repo | |
| Framework | |
Neural Memory Plasticity for Anomaly Detection
| Title | Neural Memory Plasticity for Anomaly Detection |
| Authors | Tharindu Fernando, Simon Denman, David Ahmedt-Aristizabal, Sridha Sridharan, Kristin Laurens, Patrick Johnston, Clinton Fookes |
| Abstract | In the domain of machine learning, Neural Memory Networks (NMNs) have recently achieved impressive results in a variety of application areas including visual question answering, trajectory prediction, object tracking, and language modelling. However, we observe that the attention based knowledge retrieval mechanisms used in current NMNs restricts them from achieving their full potential as the attention process retrieves information based on a set of static connection weights. This is suboptimal in a setting where there are vast differences among samples in the data domain; such as anomaly detection where there is no consistent criteria for what constitutes an anomaly. In this paper, we propose a plastic neural memory access mechanism which exploits both static and dynamic connection weights in the memory read, write and output generation procedures. We demonstrate the effectiveness and flexibility of the proposed memory model in three challenging anomaly detection tasks in the medical domain: abnormal EEG identification, MRI tumour type classification and schizophrenia risk detection in children. In all settings, the proposed approach outperforms the current state-of-the-art. Furthermore, we perform an in-depth analysis demonstrating the utility of neural plasticity for the knowledge retrieval process and provide evidence on how the proposed memory model generates sparse yet informative memory outputs. |
| Tasks | Anomaly Detection, EEG, Language Modelling, Object Tracking, Question Answering, Trajectory Prediction, Visual Question Answering |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.05448v1 |
| https://arxiv.org/pdf/1910.05448v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-memory-plasticity-for-anomaly |
| Repo | |
| Framework | |
Convolutional Bipartite Attractor Networks
| Title | Convolutional Bipartite Attractor Networks |
| Authors | Michael Iuzzolino, Yoram Singer, Michael C. Mozer |
| Abstract | In human perception and cognition, a fundamental operation that brains perform is interpretation: constructing coherent neural states from noisy, incomplete, and intrinsically ambiguous evidence. The problem of interpretation is well matched to an early and often overlooked architecture, the attractor network—a recurrent neural net that performs constraint satisfaction, imputation of missing features, and clean up of noisy data via energy minimization dynamics. We revisit attractor nets in light of modern deep learning methods and propose a convolutional bipartite architecture with a novel training loss, activation function, and connectivity constraints. We tackle larger problems than have been previously explored with attractor nets and demonstrate their potential for image completion and super-resolution. We argue that this architecture is better motivated than ever-deeper feedforward models and is a viable alternative to more costly sampling-based generative methods on a range of supervised and unsupervised tasks. |
| Tasks | Denoising, Image Denoising, Imputation, Super-Resolution |
| Published | 2019-06-08 |
| URL | https://arxiv.org/abs/1906.03504v3 |
| https://arxiv.org/pdf/1906.03504v3.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-bipartite-attractor-networks |
| Repo | |
| Framework | |
Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning
| Title | Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning |
| Authors | Fuxun Yu, Di Wang, Yinpeng Chen, Nikolaos Karianakis, Pei Yu, Dimitrios Lymberopoulos, Xiang Chen |
| Abstract | Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new domains/environments without any expensive label cost. However, without ground truth labels, most prior works on UDA for object detection tasks can only perform coarse image-level and/or feature-level adaptation by using adversarial learning methods. In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the domain content distribution gap that is shown to be important for object detectors. To overcome this limitation, we propose the Cross-Domain Semi-Supervised Learning (CDSSL) framework by leveraging high-quality pseudo labels to learn better representations from the target domain directly. To enable SSL for cross-domain object detection, we propose fine-grained domain transfer, progressive-confidence-based label sharpening and imbalanced sampling strategy to address two challenges: (i) non-identical distribution between source and target domain data, (ii) error amplification/accumulation due to noisy pseudo labeling on the target domain. Experiment results show that our proposed approach consistently achieves new state-of-the-art performance (2.2% - 9.5% better than prior best work on mAP) under various domain gap scenarios. The code will be released. |
| Tasks | Domain Adaptation, Object Detection, Unsupervised Domain Adaptation |
| Published | 2019-11-17 |
| URL | https://arxiv.org/abs/1911.07158v2 |
| https://arxiv.org/pdf/1911.07158v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-for-object |
| Repo | |
| Framework | |
