Paper Group ANR 174
MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics. Spectral Analysis Of Weighted Laplacians Arising In Data Clustering. Neural Network Based Explicit MPC for Chemical Reactor Control. Generative Adversarial Networks: recent developments. A Review of Stochastic Block Models and Ext …
MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics
| Title | MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics |
| Authors | Mohammadamin Barekatain, Ryo Yonetani, Masashi Hamaya |
| Abstract | Transfer reinforcement learning (RL) aims at improving learning efficiency of an agent by exploiting knowledge from other source agents trained on relevant tasks. However, it remains challenging to transfer knowledge between different environmental dynamics without having access to the source environments. In this work, we explore a new challenge in transfer RL, where only a set of source policies collected under unknown diverse dynamics is available for learning a target task efficiently. To address this problem, the proposed approach, MULTI-source POLicy AggRegation (MULTIPOLAR), comprises two key techniques. We learn to aggregate the actions provided by the source policies adaptively to maximize the target task performance. Meanwhile, we learn an auxiliary network that predicts residuals around the aggregated actions, which ensures the target policy’s expressiveness even when some of the source policies perform poorly. We demonstrated the effectiveness of MULTIPOLAR through an extensive experimental evaluation across six simulated environments ranging from classic control problems to challenging robotics simulations, under both continuous and discrete action spaces. |
| Tasks | Transfer Reinforcement Learning |
| Published | 2019-09-28 |
| URL | https://arxiv.org/abs/1909.13111v1 |
| https://arxiv.org/pdf/1909.13111v1.pdf | |
| PWC | https://paperswithcode.com/paper/multipolar-multi-source-policy-aggregation |
| Repo | |
| Framework | |
Spectral Analysis Of Weighted Laplacians Arising In Data Clustering
| Title | Spectral Analysis Of Weighted Laplacians Arising In Data Clustering |
| Authors | Franca Hoffmann, Bamdad Hosseini, Assad A. Oberai, Andrew M. Stuart |
| Abstract | Graph Laplacians computed from weighted adjacency matrices are widely used to identify geometric structure in data, and clusters in particular; their spectral properties play a central role in a number of unsupervised and semi-supervised learning algorithms. When suitably scaled, graph Laplacians approach limiting continuum operators in the large data limit. Studying these limiting operators, therefore, sheds light on learning algorithms. This paper is devoted to the study of a parameterized family of divergence form elliptic operators that arise as the large data limit of graph Laplacians. The link between a three-parameter family of graph Laplacians and a three-parameter family of differential operators is explained. The spectral properties of these differential perators are analyzed in the situation where the data comprises two nearly separated clusters, in a sense which is made precise. In particular, we investigate how the spectral gap depends on the three parameters entering the graph Laplacian and on a parameter measuring the size of the perturbation from the perfectly clustered case. Numerical results are presented which exemplify and extend the analysis; in particular the computations study situations with more than two clusters. The findings provide insight into parameter choices made in learning algorithms which are based on weighted adjacency matrices; they also provide the basis for analysis of the consistency of various unsupervised and semi-supervised learning algorithms, in the large data limit. |
| Tasks | |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06389v1 |
| https://arxiv.org/pdf/1909.06389v1.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-analysis-of-weighted-laplacians |
| Repo | |
| Framework | |
Neural Network Based Explicit MPC for Chemical Reactor Control
| Title | Neural Network Based Explicit MPC for Chemical Reactor Control |
| Authors | Karol Kiš, Martin Klaučo |
| Abstract | In this paper, we show the implementation of deep neural networks applied in process control. In our approach, we based the training of the neural network on model predictive control. Model predictive control is popular for its ability to be tuned by the weighting matrices and by the fact that it respects the constraints. We present the neural network that can approximate the behavior of the MPC in the way of mimicking the control input trajectory while the constraints on states and control input remain unimpaired of the value of the weighting matrices. This approach is demonstrated in a simulation case study involving a continuous stirred tank reactor, where multi-component chemical reaction takes place. |
| Tasks | |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04684v1 |
| https://arxiv.org/pdf/1912.04684v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-based-explicit-mpc-for |
| Repo | |
| Framework | |
Generative Adversarial Networks: recent developments
| Title | Generative Adversarial Networks: recent developments |
| Authors | Maciej Zamorski, Adrian Zdobylak, Maciej Zięba, Jerzy Świątek |
| Abstract | In traditional generative modeling, good data representation is very often a base for a good machine learning model. It can be linked to good representations encoding more explanatory factors that are hidden in the original data. With the invention of Generative Adversarial Networks (GANs), a subclass of generative models that are able to learn representations in an unsupervised and semi-supervised fashion, we are now able to adversarially learn good mappings from a simple prior distribution to a target data distribution. This paper presents an overview of recent developments in GANs with a focus on learning latent space representations. |
| Tasks | |
| Published | 2019-03-16 |
| URL | http://arxiv.org/abs/1903.12266v1 |
| http://arxiv.org/pdf/1903.12266v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-networks-recent |
| Repo | |
| Framework | |
A Review of Stochastic Block Models and Extensions for Graph Clustering
| Title | A Review of Stochastic Block Models and Extensions for Graph Clustering |
| Authors | Clement Lee, Darren J Wilkinson |
| Abstract | There have been rapid developments in model-based clustering of graphs, also known as block modelling, over the last ten years or so. We review different approaches and extensions proposed for different aspects in this area, such as the type of the graph, the clustering approach, the inference approach, and whether the number of groups is selected or estimated. We also review models that combine block modelling with topic modelling and/or longitudinal modelling, regarding how these models deal with multiple types of data. How different approaches cope with various issues will be summarised and compared, to facilitate the demand of practitioners for a concise overview of the current status of these areas of literature. |
| Tasks | Graph Clustering |
| Published | 2019-03-01 |
| URL | https://arxiv.org/abs/1903.00114v2 |
| https://arxiv.org/pdf/1903.00114v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-review-of-stochastic-block-models-and |
| Repo | |
| Framework | |
Understanding partition comparison indices based on counting object pairs
| Title | Understanding partition comparison indices based on counting object pairs |
| Authors | Matthijs J. Warrens, Hanneke van der Hoef |
| Abstract | In unsupervised machine learning, agreement between partitions is commonly assessed with so-called external validity indices. Researchers tend to use and report indices that quantify agreement between two partitions for all clusters simultaneously. Commonly used examples are the Rand index and the adjusted Rand index. Since these overall measures give a general notion of what is going on, their values are usually hard to interpret. Three families of indices based on counting object pairs are analyzed. It is shown that the overall indices can be decomposed into indices that reflect the degree of agreement on the level of individual clusters. The overall indices based on the pair-counting approach are sensitive to cluster size imbalance: they tend to reflect the degree of agreement on the large clusters and provide little to no information on smaller clusters. Furthermore, the value of Rand-like indices is determined to a large extent by the number of pairs of objects that are not joined in either of the partitions. |
| Tasks | |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.01777v1 |
| http://arxiv.org/pdf/1901.01777v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-partition-comparison-indices |
| Repo | |
| Framework | |
Utterance-level end-to-end language identification using attention-based CNN-BLSTM
| Title | Utterance-level end-to-end language identification using attention-based CNN-BLSTM |
| Authors | Weicheng Cai, Danwei Cai, Shen Huang, Ming Li |
| Abstract | In this paper, we present an end-to-end language identification framework, the attention-based Convolutional Neural Network-Bidirectional Long-short Term Memory (CNN-BLSTM). The model is performed on the utterance level, which means the utterance-level decision can be directly obtained from the output of the neural network. To handle speech utterances with entire arbitrary and potentially long duration, we combine CNN-BLSTM model with a self-attentive pooling layer together. The front-end CNN-BLSTM module plays a role as local pattern extractor for the variable-length inputs, and the following self-attentive pooling layer is built on top to get the fixed-dimensional utterance-level representation. We conducted experiments on NIST LRE07 closed-set task, and the results reveal that the proposed attention-based CNN-BLSTM model achieves comparable error reduction with other state-of-the-art utterance-level neural network approaches for all 3 seconds, 10 seconds, 30 seconds duration tasks. |
| Tasks | Language Identification |
| Published | 2019-02-20 |
| URL | http://arxiv.org/abs/1902.07374v1 |
| http://arxiv.org/pdf/1902.07374v1.pdf | |
| PWC | https://paperswithcode.com/paper/utterance-level-end-to-end-language |
| Repo | |
| Framework | |
Modern CNNs for IoT Based Farms
| Title | Modern CNNs for IoT Based Farms |
| Authors | Patrick Kinyua Gikunda |
| Abstract | Recent introduction of ICT in agriculture has brought a number of changes in the way farming is done. This means use of Internet of Things(IoT), Cloud Computing(CC), Big Data (BD) and automation to gain better control over the process of farming. As the use of these technologies in farms has grown exponentially with massive data production, there is need to develop and use state-of-the-art tools in order to gain more insight from the data within reasonable time. In this paper, we present an initial understanding of Convolutional Neural Network (CNN), the recent architectures of state-of-the-art CNN and their underlying complexities. Then we propose a classification taxonomy tailored for agricultural application of CNN. Finally, we present a comprehensive review of research dedicated to applications of state-of-the-art CNNs in agricultural production systems. Our contribution is in two-fold. First, for end users of agricultural deep learning tools, our benchmarking finding can serve as a guide to selecting appropriate architecture to use. Second, for agricultural software developers of deep learning tools, our in-depth analysis explains the state-of-the-art CNN complexities and points out possible future directions to further optimize the running performance. |
| Tasks | |
| Published | 2019-07-15 |
| URL | https://arxiv.org/abs/1907.07772v1 |
| https://arxiv.org/pdf/1907.07772v1.pdf | |
| PWC | https://paperswithcode.com/paper/modern-cnns-for-iot-based-farms |
| Repo | |
| Framework | |
Dynamic Graph Message Passing Networks
| Title | Dynamic Graph Message Passing Networks |
| Authors | Li Zhang, Dan Xu, Anurag Arnab, Philip H. S. Torr |
| Abstract | Modelling long-range dependencies is critical for complex scene understanding tasks such as semantic segmentation and object detection. Although CNNs have excelled in many computer vision tasks, they are still limited in capturing long-range structured relationships as they typically consist of layers of local kernels. A fully-connected graph is beneficial for such modelling, however, its computational overhead is prohibitive. We propose a dynamic graph message passing network, based on the message passing neural network framework, that significantly reduces the computational complexity compared to related works modelling a fully-connected graph. This is achieved by adaptively sampling nodes in the graph, conditioned on the input, for message passing. Based on the sampled nodes, we then dynamically predict node-dependent filter weights and the affinity matrix for propagating information between them. Using this model, we show significant improvements with respect to strong, state-of-the-art baselines on three different tasks and backbone architectures. Our approach also outperforms fully-connected graphs while using substantially fewer floating point operations and parameters. |
| Tasks | Object Detection, Scene Understanding, Semantic Segmentation |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06955v2 |
| https://arxiv.org/pdf/1908.06955v2.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-graph-message-passing-networks |
| Repo | |
| Framework | |
Depth map estimation methodology for detecting free-obstacle navigation areas
| Title | Depth map estimation methodology for detecting free-obstacle navigation areas |
| Authors | Sergio Trejo, Karla Martinez, Gerardo Flores |
| Abstract | This paper presents a vision-based methodology which makes use of a stereo camera rig and a one dimension LiDAR to estimate free obstacle areas for quadrotor navigation. The presented approach fuses information provided by a depth map from a stereo camera rig, and the sensing distance of the 1D-LiDAR. Once the depth map is filtered with a Weighted Least Squares filter (WLS), the information is fused through a Kalman filter algorithm. To determine if there is a free space large enough for the quadrotor to pass through, our approach marks an area inside the disparity map by using the Kalman Filter output information. The whole process is implemented in an embedded computer Jetson TX2 and coded in the Robotic Operating System (ROS). Experiments demonstrate the effectiveness of our approach. |
| Tasks | |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.05946v1 |
| https://arxiv.org/pdf/1905.05946v1.pdf | |
| PWC | https://paperswithcode.com/paper/depth-map-estimation-methodology-for |
| Repo | |
| Framework | |
Learning sound representations using trainable COPE feature extractors
| Title | Learning sound representations using trainable COPE feature extractors |
| Authors | Nicola Strisciuglio, Mario Vento, Nicolai Petkov |
| Abstract | Sound analysis research has mainly been focused on speech and music processing. The deployed methodologies are not suitable for analysis of sounds with varying background noise, in many cases with very low signal-to-noise ratio (SNR). In this paper, we present a method for the detection of patterns of interest in audio signals. We propose novel trainable feature extractors, which we call COPE (Combination of Peaks of Energy). The structure of a COPE feature extractor is determined using a single prototype sound pattern in an automatic configuration process, which is a type of representation learning. We construct a set of COPE feature extractors, configured on a number of training patterns. Then we take their responses to build feature vectors that we use in combination with a classifier to detect and classify patterns of interest in audio signals. We carried out experiments on four public data sets: MIVIA audio events, MIVIA road events, ESC-10 and TU Dortmund data sets. The results that we achieved (recognition rate equal to 91.71% on the MIVIA audio events, 94% on the MIVIA road events, 81.25% on the ESC-10 and 94.27% on the TU Dortmund) demonstrate the effectiveness of the proposed method and are higher than the ones obtained by other existing approaches. The COPE feature extractors have high robustness to variations of SNR. Real-time performance is achieved even when the value of a large number of features is computed. |
| Tasks | Representation Learning |
| Published | 2019-01-21 |
| URL | http://arxiv.org/abs/1901.06904v2 |
| http://arxiv.org/pdf/1901.06904v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-sound-representations-using |
| Repo | |
| Framework | |
Gradient Dynamics of Shallow Univariate ReLU Networks
| Title | Gradient Dynamics of Shallow Univariate ReLU Networks |
| Authors | Francis Williams, Matthew Trager, Claudio Silva, Daniele Panozzo, Denis Zorin, Joan Bruna |
| Abstract | We present a theoretical and empirical study of the gradient dynamics of overparameterized shallow ReLU networks with one-dimensional input, solving least-squares interpolation. We show that the gradient dynamics of such networks are determined by the gradient flow in a non-redundant parameterization of the network function. We examine the principal qualitative features of this gradient flow. In particular, we determine conditions for two learning regimes:kernel and adaptive, which depend both on the relative magnitude of initialization of weights in different layers and the asymptotic behavior of initialization coefficients in the limit of large network widths. We show that learning in the kernel regime yields smooth interpolants, minimizing curvature, and reduces to cubic splines for uniform initializations. Learning in the adaptive regime favors instead linear splines, where knots cluster adaptively at the sample points. |
| Tasks | |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07842v1 |
| https://arxiv.org/pdf/1906.07842v1.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-dynamics-of-shallow-univariate-relu |
| Repo | |
| Framework | |
Low-Rank Discriminative Least Squares Regression for Image Classification
| Title | Low-Rank Discriminative Least Squares Regression for Image Classification |
| Authors | Zhe Chen, Xiao-Jun Wu, Josef Kittler |
| Abstract | Latest least squares regression (LSR) methods mainly try to learn slack regression targets to replace strict zero-one labels. However, the difference of intra-class targets can also be highlighted when enlarging the distance between different classes, and roughly persuing relaxed targets may lead to the problem of overfitting. To solve above problems, we propose a low-rank discriminative least squares regression model (LRDLSR) for multi-class image classification. Specifically, LRDLSR class-wisely imposes low-rank constraint on the intra-class regression targets to encourage its compactness and similarity. Moreover, LRDLSR introduces an additional regularization term on the learned targets to avoid the problem of overfitting. These two improvements are helpful to learn a more discriminative projection for regression and thus achieving better classification performance. Experimental results over a range of image databases demonstrate the effectiveness of the proposed LRDLSR method. |
| Tasks | Image Classification |
| Published | 2019-03-19 |
| URL | https://arxiv.org/abs/1903.07832v4 |
| https://arxiv.org/pdf/1903.07832v4.pdf | |
| PWC | https://paperswithcode.com/paper/low-rank-discriminative-least-squares |
| Repo | |
| Framework | |
Deep Representation with ReLU Neural Networks
| Title | Deep Representation with ReLU Neural Networks |
| Authors | Andreas Heinecke, Wen-Liang Hwang |
| Abstract | We consider deep feedforward neural networks with rectified linear units from a signal processing perspective. In this view, such representations mark the transition from using a single (data-driven) linear representation to utilizing a large collection of affine linear representations tailored to particular regions of the signal space. This paper provides a precise description of the individual affine linear representations and corresponding domain regions that the (data-driven) neural network associates to each signal of the input space. In particular, we describe atomic decompositions of the representations and, based on estimating their Lipschitz regularity, suggest some conditions that can stabilize learning independent of the network depth. Such an analysis may promote further theoretical insight from both the signal processing and machine learning communities. |
| Tasks | |
| Published | 2019-03-29 |
| URL | http://arxiv.org/abs/1903.12384v1 |
| http://arxiv.org/pdf/1903.12384v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-representation-with-relu-neural-networks |
| Repo | |
| Framework | |
Performance Boundary Identification for the Evaluation of Automated Vehicles using Gaussian Process Classification
| Title | Performance Boundary Identification for the Evaluation of Automated Vehicles using Gaussian Process Classification |
| Authors | Felix Batsch, Alireza Daneshkhah, Madeline Cheah, Stratis Kanarachos, Anthony Baxendale |
| Abstract | Safety is an essential aspect in the facilitation of automated vehicle deployment. Current testing practices are not enough, and going beyond them leads to infeasible testing requirements, such as needing to drive billions of kilometres on public roads. Automated vehicles are exposed to an indefinite number of scenarios. Handling of the most challenging scenarios should be tested, which leads to the question of how such corner cases can be determined. We propose an approach to identify the performance boundary, where these corner cases are located, using Gaussian Process Classification. We also demonstrate the classification on an exemplary traffic jam approach scenario, showing that it is feasible and would lead to more efficient testing practices. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05364v1 |
| https://arxiv.org/pdf/1907.05364v1.pdf | |
| PWC | https://paperswithcode.com/paper/performance-boundary-identification-for-the |
| Repo | |
| Framework | |
