Paper Group ANR 336
Sparse Deep Neural Network Exact Solutions. Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation. Diverse Exploration for Fast and Safe Policy Improvement. Automatic Classification of Object Code Using Machine Learning. A Proof of the Front-Door Adjustment Formula. Goal-oriented Dialogue Policy Learning …
Sparse Deep Neural Network Exact Solutions
| Title | Sparse Deep Neural Network Exact Solutions |
| Authors | Jeremy Kepner, Vijay Gadepally, Hayden Jananthan, Lauren Milechin, Sid Samsi |
| Abstract | Deep neural networks (DNNs) have emerged as key enablers of machine learning. Applying larger DNNs to more diverse applications is an important challenge. The computations performed during DNN training and inference are dominated by operations on the weight matrices describing the DNN. As DNNs incorporate more layers and more neurons per layers, these weight matrices may be required to be sparse because of memory limitations. Sparse DNNs are one possible approach, but the underlying theory is in the early stages of development and presents a number of challenges, including determining the accuracy of inference and selecting nonzero weights for training. Associative array algebra has been developed by the big data community to combine and extend database, matrix, and graph/network concepts for use in large, sparse data problems. Applying this mathematics to DNNs simplifies the formulation of DNN mathematics and reveals that DNNs are linear over oscillating semirings. This work uses associative array DNNs to construct exact solutions and corresponding perturbation models to the rectified linear unit (ReLU) DNN equations that can be used to construct test vectors for sparse DNN implementations over various precisions. These solutions can be used for DNN verification, theoretical explorations of DNN properties, and a starting point for the challenge of sparse training. |
| Tasks | |
| Published | 2018-07-06 |
| URL | http://arxiv.org/abs/1807.03165v1 |
| http://arxiv.org/pdf/1807.03165v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-deep-neural-network-exact-solutions |
| Repo | |
| Framework | |
Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation
| Title | Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation |
| Authors | Stefan Hoermann, Philipp Henzler, Martin Bach, Klaus Dietmayer |
| Abstract | We tackle the problem of object detection and pose estimation in a shared space downtown environment. For perception multiple laser scanners with 360{\deg} coverage were fused in a dynamic occupancy grid map (DOGMa). A single-stage deep convolutional neural network is trained to provide object hypotheses comprising of shape, position, orientation and an existence score from a single input DOGMa. Furthermore, an algorithm for offline object extraction was developed to automatically label several hours of training data. The algorithm is based on a two-pass trajectory extraction, forward and backward in time. Typical for engineered algorithms, the automatic label generation suffers from misdetections, which makes hard negative mining impractical. Therefore, we propose a loss function counteracting the high imbalance between mostly static background and extremely rare dynamic grid cells. Experiments indicate, that the trained network has good generalization capabilities since it detects objects occasionally lost by the label algorithm. Evaluation reaches an average precision (AP) of 75.9% |
| Tasks | Object Detection, Pose Estimation |
| Published | 2018-01-30 |
| URL | http://arxiv.org/abs/1802.02202v1 |
| http://arxiv.org/pdf/1802.02202v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-detection-on-dynamic-occupancy-grid |
| Repo | |
| Framework | |
Diverse Exploration for Fast and Safe Policy Improvement
| Title | Diverse Exploration for Fast and Safe Policy Improvement |
| Authors | Andrew Cohen, Lei Yu, Robert Wright |
| Abstract | We study an important yet under-addressed problem of quickly and safely improving policies in online reinforcement learning domains. As its solution, we propose a novel exploration strategy - diverse exploration (DE), which learns and deploys a diverse set of safe policies to explore the environment. We provide DE theory explaining why diversity in behavior policies enables effective exploration without sacrificing exploitation. Our empirical study shows that an online policy improvement algorithm framework implementing the DE strategy can achieve both fast policy improvement and safe online performance. |
| Tasks | |
| Published | 2018-02-22 |
| URL | http://arxiv.org/abs/1802.08331v1 |
| http://arxiv.org/pdf/1802.08331v1.pdf | |
| PWC | https://paperswithcode.com/paper/diverse-exploration-for-fast-and-safe-policy |
| Repo | |
| Framework | |
Automatic Classification of Object Code Using Machine Learning
| Title | Automatic Classification of Object Code Using Machine Learning |
| Authors | John Clemens |
| Abstract | Recent research has repeatedly shown that machine learning techniques can be applied to either whole files or file fragments to classify them for analysis. We build upon these techniques to show that for samples of un-labeled compiled computer object code, one can apply the same type of analysis to classify important aspects of the code, such as its target architecture and endianess. We show that using simple byte-value histograms we retain enough information about the opcodes within a sample to classify the target architecture with high accuracy, and then discuss heuristic-based features that exploit information within the operands to determine endianess. We introduce a dataset with over 16000 code samples from 20 architectures and experimentally show that by using our features, classifiers can achieve very high accuracy with relatively small sample sizes. |
| Tasks | |
| Published | 2018-05-06 |
| URL | http://arxiv.org/abs/1805.02146v1 |
| http://arxiv.org/pdf/1805.02146v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-classification-of-object-code-using |
| Repo | |
| Framework | |
A Proof of the Front-Door Adjustment Formula
| Title | A Proof of the Front-Door Adjustment Formula |
| Authors | Mohammad Ali Javidian, Marco Valtorta |
| Abstract | We provide a proof of the the Front-Door adjustment formula using the do-calculus. |
| Tasks | |
| Published | 2018-06-25 |
| URL | http://arxiv.org/abs/1806.10449v1 |
| http://arxiv.org/pdf/1806.10449v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-proof-of-the-front-door-adjustment-formula |
| Repo | |
| Framework | |
Goal-oriented Dialogue Policy Learning from Failures
| Title | Goal-oriented Dialogue Policy Learning from Failures |
| Authors | Keting Lu, Shiqi Zhang, Xiaoping Chen |
| Abstract | Reinforcement learning methods have been used for learning dialogue policies. However, learning an effective dialogue policy frequently requires prohibitively many conversations. This is partly because of the sparse rewards in dialogues, and the very few successful dialogues in early learning phase. Hindsight experience replay (HER) enables learning from failures, but the vanilla HER is inapplicable to dialogue learning due to the implicit goals. In this work, we develop two complex HER methods providing different trade-offs between complexity and performance, and, for the first time, enabled HER-based dialogue policy learning. Experiments using a realistic user simulator show that our HER methods perform better than existing experience replay methods (as applied to deep Q-networks) in learning rate. |
| Tasks | |
| Published | 2018-08-20 |
| URL | http://arxiv.org/abs/1808.06497v2 |
| http://arxiv.org/pdf/1808.06497v2.pdf | |
| PWC | https://paperswithcode.com/paper/goal-oriented-dialogue-policy-learning-from |
| Repo | |
| Framework | |
Geographical Hidden Markov Tree for Flood Extent Mapping (With Proof Appendix)
| Title | Geographical Hidden Markov Tree for Flood Extent Mapping (With Proof Appendix) |
| Authors | Miao Xie, Zhe Jiang, Arpan Man Sainju |
| Abstract | Flood extent mapping plays a crucial role in disaster management and national water forecasting. Unfortunately, traditional classification methods are often hampered by the existence of noise, obstacles and heterogeneity in spectral features as well as implicit anisotropic spatial dependency across class labels. In this paper, we propose geographical hidden Markov tree, a probabilistic graphical model that generalizes the common hidden Markov model from a one dimensional sequence to a two dimensional map. Anisotropic spatial dependency is incorporated in the hidden class layer with a reverse tree structure. We also investigate computational algorithms for reverse tree construction, model parameter learning and class inference. Extensive evaluations on both synthetic and real world datasets show that proposed model outperforms multiple baselines in flood mapping, and our algorithms are scalable on large data sizes. |
| Tasks | |
| Published | 2018-05-24 |
| URL | http://arxiv.org/abs/1805.09757v1 |
| http://arxiv.org/pdf/1805.09757v1.pdf | |
| PWC | https://paperswithcode.com/paper/geographical-hidden-markov-tree-for-flood |
| Repo | |
| Framework | |
Distributed Computation of Wasserstein Barycenters over Networks
| Title | Distributed Computation of Wasserstein Barycenters over Networks |
| Authors | César A. Uribe, Darina Dvinskikh, Pavel Dvurechensky, Alexander Gasnikov, Angelia Nedić |
| Abstract | We propose a new \cu{class-optimal} algorithm for the distributed computation of Wasserstein Barycenters over networks. Assuming that each node in a graph has a probability distribution, we prove that every node can reach the barycenter of all distributions held in the network by using local interactions compliant with the topology of the graph. We provide an estimate for the minimum number of communication rounds required for the proposed method to achieve arbitrary relative precision both in the optimality of the solution and the consensus among all agents for undirected fixed networks. |
| Tasks | |
| Published | 2018-03-08 |
| URL | http://arxiv.org/abs/1803.02933v2 |
| http://arxiv.org/pdf/1803.02933v2.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-computation-of-wasserstein |
| Repo | |
| Framework | |
Apple Flower Detection using Deep Convolutional Networks
| Title | Apple Flower Detection using Deep Convolutional Networks |
| Authors | Philipe A. Dias, Amy Tabb, Henry Medeiros |
| Abstract | To optimize fruit production, a portion of the flowers and fruitlets of apple trees must be removed early in the growing season. The proportion to be removed is determined by the bloom intensity, i.e., the number of flowers present in the orchard. Several automated computer vision systems have been proposed to estimate bloom intensity, but their overall performance is still far from satisfactory even in relatively controlled environments. With the goal of devising a technique for flower identification which is robust to clutter and to changes in illumination, this paper presents a method in which a pre-trained convolutional neural network is fine-tuned to become specially sensitive to flowers. Experimental results on a challenging dataset demonstrate that our method significantly outperforms three approaches that represent the state of the art in flower detection, with recall and precision rates higher than $90%$. Moreover, a performance assessment on three additional datasets previously unseen by the network, which consist of different flower species and were acquired under different conditions, reveals that the proposed method highly surpasses baseline approaches in terms of generalization capability. |
| Tasks | |
| Published | 2018-09-17 |
| URL | http://arxiv.org/abs/1809.06357v1 |
| http://arxiv.org/pdf/1809.06357v1.pdf | |
| PWC | https://paperswithcode.com/paper/apple-flower-detection-using-deep |
| Repo | |
| Framework | |
Towards a classification of Lindenmayer systems
| Title | Towards a classification of Lindenmayer systems |
| Authors | Diego Krivochen, Douglas Saddy |
| Abstract | In this paper we will attempt to classify Lindenmayer systems based on properties of sets of rules and the kind of strings those rules generate. This classification will be referred to as a parametrization of the L-space: the L-space is the phase space in which all possible L-developments are represented. This space is infinite, because there is no halting algorithm for L-grammars; but it is also subjected to hard conditions, because there are grammars and developments which are not possible states of an L-system: a very well-known example is the space of normal grammars. Just as the space of normal grammars is parametrized into Regular, Context-Free, Context-Sensitive, and Unrestricted (with proper containment relations holding among them; see Chomsky, 1959: Theorem 1), we contend here that the L-space is a very rich landscape of grammars which cluster into kinds that are not mutually translatable. |
| Tasks | |
| Published | 2018-09-27 |
| URL | http://arxiv.org/abs/1809.10542v1 |
| http://arxiv.org/pdf/1809.10542v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-classification-of-lindenmayer |
| Repo | |
| Framework | |
GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
| Title | GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning |
| Authors | Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann |
| Abstract | A key problem in deep multi-attribute learning is to effectively discover the inter-attribute correlation structures. Typically, the conventional deep multi-attribute learning approaches follow the pipeline of manually designing the network architectures based on task-specific expertise prior knowledge and careful network tunings, leading to the inflexibility for various complicated scenarios in practice. Motivated by addressing this problem, we propose an efficient greedy neural architecture search approach (GNAS) to automatically discover the optimal tree-like deep architecture for multi-attribute learning. In a greedy manner, GNAS divides the optimization of global architecture into the optimizations of individual connections step by step. By iteratively updating the local architectures, the global tree-like architecture gets converged where the bottom layers are shared across relevant attributes and the branches in top layers more encode attribute-specific features. Experiments on three benchmark multi-attribute datasets show the effectiveness and compactness of neural architectures derived by GNAS, and also demonstrate the efficiency of GNAS in searching neural architectures. |
| Tasks | Neural Architecture Search |
| Published | 2018-04-19 |
| URL | http://arxiv.org/abs/1804.06964v2 |
| http://arxiv.org/pdf/1804.06964v2.pdf | |
| PWC | https://paperswithcode.com/paper/gnas-a-greedy-neural-architecture-search |
| Repo | |
| Framework | |
Residuum-Condition Diagram and Reduction of Over-Complete Endmember-Sets
| Title | Residuum-Condition Diagram and Reduction of Over-Complete Endmember-Sets |
| Authors | Christoph Schikora, Markus Plack, Andreas Kolb |
| Abstract | Extracting reference spectra, or endmembers (EMs) from a given multi- or hyperspectral image, as well as estimating the size of the EM set, plays an important role in multispectral image processing. In this paper, we present condition-residuum-diagrams. By plotting the residuum resulting from the unmixing and reconstruction and the condition number of various EM sets, the resulting diagram provides insight into the behavior of the spectral unmixing under a varying amount of endmembers (EMs). Furthermore, we utilize condition-residuum-diagrams to realize an EM reduction algorithm that starts with an initially extracted, over-complete EM set. An over-complete EM set commonly exhibits a good unmixing result, i.e. a lower reconstruction residuum, but due to its partial redundancy, the unmixing gets numerically unstable, i.e. the unmixed abundances values are less reliable. Our greedy reduction scheme improves the EM set by reducing the condition number, i.e. enhancing the set’s stability, while keeping the reconstruction error as low as possible. The resulting set sequence gives hint to the optimal EM set and its size. We demonstrate the benefit of our condition-residuum-diagram and reduction scheme on well-studied datasets with known reference EM set sizes for several well-known EE algorithms. |
| Tasks | |
| Published | 2018-09-26 |
| URL | http://arxiv.org/abs/1809.10089v1 |
| http://arxiv.org/pdf/1809.10089v1.pdf | |
| PWC | https://paperswithcode.com/paper/residuum-condition-diagram-and-reduction-of |
| Repo | |
| Framework | |
Unsupervised Learning of Sequence Representations by Autoencoders
| Title | Unsupervised Learning of Sequence Representations by Autoencoders |
| Authors | Wenjie Pei, David M. J. Tax |
| Abstract | Sequence data is challenging for machine learning approaches, because the lengths of the sequences may vary between samples. In this paper, we present an unsupervised learning model for sequence data, called the Integrated Sequence Autoencoder (ISA), to learn a fixed-length vectorial representation by minimizing the reconstruction error. Specifically, we propose to integrate two classical mechanisms for sequence reconstruction which takes into account both the global silhouette information and the local temporal dependencies. Furthermore, we propose a stop feature that serves as a temporal stamp to guide the reconstruction process, which results in a higher-quality representation. The learned representation is able to effectively summarize not only the apparent features, but also the underlying and high-level style information. Take for example a speech sequence sample: our ISA model can not only recognize the spoken text (apparent feature), but can also discriminate the speaker who utters the audio (more high-level style). One promising application of the ISA model is that it can be readily used in the semi-supervised learning scenario, in which a large amount of unlabeled data is leveraged to extract high-quality sequence representations and thus to improve the performance of the subsequent supervised learning tasks on limited labeled data. |
| Tasks | |
| Published | 2018-04-03 |
| URL | http://arxiv.org/abs/1804.00946v2 |
| http://arxiv.org/pdf/1804.00946v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-of-sequence |
| Repo | |
| Framework | |
MaxHedge: Maximising a Maximum Online
| Title | MaxHedge: Maximising a Maximum Online |
| Authors | Stephen Pasteris, Fabio Vitale, Kevin Chan, Shiqiang Wang, Mark Herbster |
| Abstract | We introduce a new online learning framework where, at each trial, the learner is required to select a subset of actions from a given known action set. Each action is associated with an energy value, a reward and a cost. The sum of the energies of the actions selected cannot exceed a given energy budget. The goal is to maximise the cumulative profit, where the profit obtained on a single trial is defined as the difference between the maximum reward among the selected actions and the sum of their costs. Action energy values and the budget are known and fixed. All rewards and costs associated with each action change over time and are revealed at each trial only after the learner’s selection of actions. Our framework encompasses several online learning problems where the environment changes over time; and the solution trades-off between minimising the costs and maximising the maximum reward of the selected subset of actions, while being constrained to an action energy budget. The algorithm that we propose is efficient and general in that it may be specialised to multiple natural online combinatorial problems. |
| Tasks | |
| Published | 2018-10-28 |
| URL | https://arxiv.org/abs/1810.11843v2 |
| https://arxiv.org/pdf/1810.11843v2.pdf | |
| PWC | https://paperswithcode.com/paper/maxhedge-maximising-a-maximum-online-with |
| Repo | |
| Framework | |
A Computational Theory for Life-Long Learning of Semantics
| Title | A Computational Theory for Life-Long Learning of Semantics |
| Authors | Peter Sutor Jr., Douglas Summers-Stay, Yiannis Aloimonos |
| Abstract | Semantic vectors are learned from data to express semantic relationships between elements of information, for the purpose of solving and informing downstream tasks. Other models exist that learn to map and classify supervised data. However, the two worlds of learning rarely interact to inform one another dynamically, whether across types of data or levels of semantics, in order to form a unified model. We explore the research problem of learning these vectors and propose a framework for learning the semantics of knowledge incrementally and online, across multiple mediums of data, via binary vectors. We discuss the aspects of this framework to spur future research on this approach and problem. |
| Tasks | |
| Published | 2018-06-28 |
| URL | http://arxiv.org/abs/1806.10755v2 |
| http://arxiv.org/pdf/1806.10755v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-computational-theory-for-life-long-learning |
| Repo | |
| Framework | |
