January 28, 2020

3100 words 15 mins read

Paper Group ANR 812

Deep Learning with Persistent Homology for Orbital Angular Momentum (OAM) Decoding. Deep Structured Implicit Functions. Multiway clustering via tensor block models. Big Bidirectional Insertion Representations for Documents. Neural Collision Clearance Estimator for Fast Robot Motion Planning. Control of nonlinear, complex and black-boxed greenhouse …

Deep Learning with Persistent Homology for Orbital Angular Momentum (OAM) Decoding


Title	Deep Learning with Persistent Homology for Orbital Angular Momentum (OAM) Decoding
Authors	Soheil Rostami, Walid Saad, Choong Seon Hong
Abstract	Orbital angular momentum (OAM)-encoding has recently emerged as an effective approach for increasing the channel capacity of free-space optical communications. In this paper, OAM-based decoding is formulated as a supervised classification problem. To maintain lower error rate in presence of severe atmospheric turbulence, a new approach that combines effective machine learning tools from persistent homology and convolutional neural networks (CNNs) is proposed to decode the OAM modes. A Gaussian kernel with learnable parameters is proposed in order to connect persistent homology to CNN, allowing the system to extract and distinguish robust and unique topological features for the OAM modes. Simulation results show that the proposed approach achieves up to 20% gains in classification accuracy rate over state-of-the-art of method based on only CNNs. These results essentially show that geometric and topological features play a pivotal role in the OAM mode classification problem.
Tasks
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06858v1
PDF	https://arxiv.org/pdf/1911.06858v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-with-persistent-homology-for
Repo
Framework

Deep Structured Implicit Functions


Title	Deep Structured Implicit Functions
Authors	Kyle Genova, Forrester Cole, Avneesh Sud, Aaron Sarna, Thomas Funkhouser
Abstract	The goal of this project is to learn a 3D shape representation that enables accurate surface reconstruction, compact storage, efficient computation, consistency for similar shapes, generalization across diverse shape categories, and inference from depth camera observations. Towards this end, we introduce Deep Structured Implicit Functions (DSIF), a 3D shape representation that decomposes space into a structured set of local deep implicit functions. We provide networks that infer the space decomposition and local deep implicit functions from a 3D mesh or posed depth image. During experiments, we find that it provides 10.3 points higher surface reconstruction accuracy (F-Score) than the state-of-the-art (OccNet), while requiring fewer than 1 percent of the network parameters. Experiments on posed depth image completion and generalization to unseen classes show 15.8 and 17.8 point improvements over the state-of-the-art, while producing a structured 3D representation for each input with consistency across diverse shape collections. Please see our video at https://youtu.be/HCBtG0-EZ2s
Tasks	3D Shape Representation
Published	2019-12-12
URL	https://arxiv.org/abs/1912.06126v1
PDF	https://arxiv.org/pdf/1912.06126v1.pdf
PWC	https://paperswithcode.com/paper/deep-structured-implicit-functions
Repo
Framework

Multiway clustering via tensor block models


Title	Multiway clustering via tensor block models
Authors	Miaoyan Wang, Yuchen Zeng
Abstract	We consider the problem of identifying multiway block structure from a large noisy tensor. Such problems arise frequently in applications such as genomics, recommendation system, topic modeling, and sensor network localization. We propose a tensor block model, develop a unified least-square estimation, and obtain the theoretical accuracy guarantees for multiway clustering. The statistical convergence of the estimator is established, and we show that the associated clustering procedure achieves partition consistency. A sparse regularization is further developed for identifying important blocks with elevated means. The proposal handles a broad range of data types, including binary, continuous, and hybrid observations. Through simulation and application to two real datasets, we demonstrate the outperformance of our approach over previous methods.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03807v3
PDF	https://arxiv.org/pdf/1906.03807v3.pdf
PWC	https://paperswithcode.com/paper/multiway-clustering-via-tensor-block-models
Repo
Framework

Big Bidirectional Insertion Representations for Documents


Title	Big Bidirectional Insertion Representations for Documents
Authors	Lala Li, William Chan
Abstract	The Insertion Transformer is well suited for long form text generation due to its parallel generation capabilities, requiring $O(\log_2 n)$ generation steps to generate $n$ tokens. However, modeling long sequences is difficult, as there is more ambiguity captured in the attention mechanism. This work proposes the Big Bidirectional Insertion Representations for Documents (Big BIRD), an insertion-based model for document-level translation tasks. We scale up the insertion-based models to long form documents. Our key contribution is introducing sentence alignment via sentence-positional embeddings between the source and target document. We show an improvement of +4.3 BLEU on the WMT’19 English$\rightarrow$German document-level translation task compared with the Insertion Transformer baseline.
Tasks	Text Generation
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13034v1
PDF	https://arxiv.org/pdf/1910.13034v1.pdf
PWC	https://paperswithcode.com/paper/big-bidirectional-insertion-representations
Repo
Framework

Neural Collision Clearance Estimator for Fast Robot Motion Planning


Title	Neural Collision Clearance Estimator for Fast Robot Motion Planning
Authors	J. Chase Kew, Brian Ichter, Maryam Bandari, Tsang-Wei Edward Lee, Aleksandra Faust
Abstract	Collision checking is a well known bottleneck in sampling-based motion planning due to its computational expense and the large number of checks required. To alleviate this bottleneck, we present a fast neural network collision checking heuristic, ClearanceNet, and incorporate it within a planning algorithm, ClearanceNet-RRT (CN-RRT). ClearanceNet takes as input a robot pose and the location of all obstacles in the workspace and learns to predict the clearance, i.e., distance to nearest obstacle. CN-RRT then efficiently computes a motion plan by leveraging three key features of ClearanceNet. First, as neural network inference is massively parallel, CN-RRT explores the space via a parallel RRT, which expands nodes in parallel, allowing for thousands of collision checks at once. Second, CN-RRT adaptively relaxes its clearance threshold for more difficult problems. Third, to repair errors, CN-RRT shifts states towards higher clearance through a gradient-based approach that uses the analytic gradient of ClearanceNet. Once a path is found, any errors are repaired via RRT over the misclassified sections, thus maintaining the theoretical guarantees of sampling-based motion planning. We evaluate the collision checking speed, planning speed, and motion plan efficiency in configuration spaces with up to 30 degrees of freedom. The collision checking achieves speedups of more than two orders of magnitude over traditional collision detection methods. Sampling-based planning over multiple robotic arms in new environment configurations achieves speedups of up to 51% over a baseline, with paths up to 25% more efficient. Experiments on a physical Fetch robot reaching into shelves in a cluttered environment confirm the feasibility of this method on real robots.
Tasks	Motion Planning
Published	2019-10-14
URL	https://arxiv.org/abs/1910.05917v1
PDF	https://arxiv.org/pdf/1910.05917v1.pdf
PWC	https://paperswithcode.com/paper/neural-collision-clearance-estimator-for-fast
Repo
Framework

Control of nonlinear, complex and black-boxed greenhouse system with reinforcement learning


Title	Control of nonlinear, complex and black-boxed greenhouse system with reinforcement learning
Authors	Byunghyun Ban, Soobin Kim
Abstract	Modern control theories such as systems engineering approaches try to solve nonlinear system problems by revelation of causal relationship or co-relationship among the components; most of those approaches focus on control of sophisticatedly modeled white-boxed systems. We suggest an application of actor-critic reinforcement learning approach to control a nonlinear, complex and black-boxed system. We demonstrated this approach on artificial green-house environment simulator all of whose control inputs have several side effects so human cannot figure out how to control this system easily. Our approach succeeded to maintain the circumstance at least 20 times longer than PID and Deep Q Learning.
Tasks	Q-Learning
Published	2019-07-30
URL	https://arxiv.org/abs/1907.12690v1
PDF	https://arxiv.org/pdf/1907.12690v1.pdf
PWC	https://paperswithcode.com/paper/control-of-nonlinear-complex-and-black-boxed
Repo
Framework

An Object Detection by using Adaptive Structural Learning of Deep Belief Network


Title	An Object Detection by using Adaptive Structural Learning of Deep Belief Network
Authors	Shin Kamada, Takumi Ichimura
Abstract	Deep learning forms a hierarchical network structure for representation of multiple input features. The adaptive structural learning method of Deep Belief Network (DBN) can realize a high classification capability while searching the optimal network structure during the training. The method can find the optimal number of hidden neurons for given input data in a Restricted Boltzmann Machine (RBM) by neuron generation-annihilation algorithm. Moreover, it can generate a new hidden layer in DBN by the layer generation algorithm to actualize a deep data representation. The proposed method showed higher classification accuracy for image benchmark data sets than several deep learning methods including well-known CNN methods. In this paper, a new object detection method for the DBN architecture is proposed for localization and category of objects. The method is a task for finding semantic objects in images as Bounding Box (B-Box). To investigate the effectiveness of the proposed method, the adaptive structural learning of DBN and the object detection were evaluated on the Chest X-ray image benchmark data set (CXR8), which is one of the most commonly accessible radio-logical examination for many lung diseases. The proposed method showed higher performance for both classification (more than 94.5% classification for test data) and localization (more than 90.4% detection for test data) than the other CNN methods.
Tasks	Object Detection
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13465v1
PDF	https://arxiv.org/pdf/1909.13465v1.pdf
PWC	https://paperswithcode.com/paper/an-object-detection-by-using-adaptive
Repo
Framework

The role of artificial intelligence in achieving the Sustainable Development Goals


Title	The role of artificial intelligence in achieving the Sustainable Development Goals
Authors	Ricardo Vinuesa, Hossein Azizpour, Iolanda Leite, Madeline Balaam, Virginia Dignum, Sami Domisch, Anna Felländer, Simone Langhans, Max Tegmark, Francesco Fuso Nerini
Abstract	The emergence of artificial intelligence (AI) and its progressively wider impact on many sectors across the society requires an assessment of its effect on sustainable development. Here we analyze published evidence of positive or negative impacts of AI on the achievement of each of the 17 goals and 169 targets of the 2030 Agenda for Sustainable Development. We find that AI can support the achievement of 128 targets across all SDGs, but it may also inhibit 58 targets. Notably, AI enables new technologies that improve efficiency and productivity, but it may also lead to increased inequalities among and within countries, thus hindering the achievement of the 2030 Agenda. The fast development of AI needs to be supported by appropriate policy and regulation. Otherwise, it would lead to gaps in transparency, accountability, safety and ethical standards of AI-based technology, which could be detrimental towards the development and sustainable use of AI. Finally, there is a lack of research assessing the medium- and long-term impacts of AI. It is therefore essential to reinforce the global debate regarding the use of AI and to develop the necessary regulatory insight and oversight for AI-based technologies.
Tasks
Published	2019-04-30
URL	http://arxiv.org/abs/1905.00501v1
PDF	http://arxiv.org/pdf/1905.00501v1.pdf
PWC	https://paperswithcode.com/paper/the-role-of-artificial-intelligence-in
Repo
Framework

Graph Neural Networks for Modelling Traffic Participant Interaction


Title	Graph Neural Networks for Modelling Traffic Participant Interaction
Authors	Frederik Diehl, Thomas Brunner, Michael Truong Le, Alois Knoll
Abstract	By interpreting a traffic scene as a graph of interacting vehicles, we gain a flexible abstract representation which allows us to apply Graph Neural Network (GNN) models for traffic prediction. These naturally take interaction between traffic participants into account while being computationally efficient and providing large model capacity. We evaluate two state-of-the art GNN architectures and introduce several adaptations for our specific scenario. We show that prediction error in scenarios with much interaction decreases by 30% compared to a model that does not take interactions into account. This suggests that interaction is important, and shows that we can model it using graphs. This makes GNNs a worthwhile addition to traffic prediction systems.
Tasks	Traffic Prediction
Published	2019-03-04
URL	https://arxiv.org/abs/1903.01254v2
PDF	https://arxiv.org/pdf/1903.01254v2.pdf
PWC	https://paperswithcode.com/paper/graph-neural-networks-for-modelling-traffic
Repo
Framework

A Classifiers Voting Model for Exit Prediction of Privately Held Companies


Title	A Classifiers Voting Model for Exit Prediction of Privately Held Companies
Authors	Giuseppe Carlo Calafiore, Marisa Hillary Morales, Vittorio Tiozzo, Serge Marquie
Abstract	Predicting the exit (e.g. bankrupt, acquisition, etc.) of privately held companies is a current and relevant problem for investment firms. The difficulty of the problem stems from the lack of reliable, quantitative and publicly available data. In this paper, we contribute to this endeavour by constructing an exit predictor model based on qualitative data, which blends the outcomes of three classifiers, namely, a Logistic Regression model, a Random Forest model, and a Support Vector Machine model. The output of the combined model is selected on the basis of the majority of the output classes of the component models. The models are trained using data extracted from the Thomson Reuters Eikon repository of 54697 US and European companies over the 1996-2011 time span. Experiments have been conducted for predicting whether the company eventually either gets acquired or goes public (IPO), against the complementary event that it remains private or goes bankrupt, in the considered time window. Our model achieves a 63% predictive accuracy, which is quite a valuable figure for Private Equity investors, who typically expect very high returns from successful investments.
Tasks
Published	2019-10-30
URL	https://arxiv.org/abs/1910.13969v1
PDF	https://arxiv.org/pdf/1910.13969v1.pdf
PWC	https://paperswithcode.com/paper/a-classifiers-voting-model-for-exit
Repo
Framework

Parameter-Free Online Convex Optimization with Sub-Exponential Noise


Title	Parameter-Free Online Convex Optimization with Sub-Exponential Noise
Authors	Kwang-Sung Jun, Francesco Orabona
Abstract	We consider the problem of unconstrained online convex optimization (OCO) with sub-exponential noise, a strictly more general problem than the standard OCO. In this setting, the learner receives a subgradient of the loss functions corrupted by sub-exponential noise and strives to achieve optimal regret guarantee, without knowledge of the competitor norm, i.e., in a parameter-free way. Recently, Cutkosky and Boahen (COLT 2017) proved that, given unbounded subgradients, it is impossible to guarantee a sublinear regret due to an exponential penalty. This paper shows that it is possible to go around the lower bound by allowing the observed subgradients to be unbounded via stochastic noise. However, the presence of unbounded noise in unconstrained OCO is challenging; existing algorithms do not provide near-optimal regret bounds or fail to have a guarantee. So, we design a novel parameter-free OCO algorithm for Banach space, which we call BANCO, via a reduction to betting on noisy coins. We show that BANCO achieves the optimal regret rate in our problem. Finally, we show the application of our results to obtain a parameter-free locally private stochastic subgradient descent algorithm, and the connection to the law of iterated logarithms.
Tasks
Published	2019-02-05
URL	https://arxiv.org/abs/1902.01500v3
PDF	https://arxiv.org/pdf/1902.01500v3.pdf
PWC	https://paperswithcode.com/paper/parameter-free-online-convex-optimization
Repo
Framework

The option pricing model based on time values: an application of the universal approximation theory on unbounded domains


Title	The option pricing model based on time values: an application of the universal approximation theory on unbounded domains
Authors	Yang Qu, Ming-Xi Wang
Abstract	The mathematical theory of neural networks is ``meant to tell us what is possible and, sometimes equally importantly, what is not.” This paper contributes a case that fits into this principle. We propose that “option price or time value” is a natural hyperparameter in the design of neural network option models. Hutchinson, Lo and Poggio asked the question that if learning networks can learn the Black-Scholes formula, and they studied the network $(S_t/K, \tau) \to C_t/K$ where $S_t, K, \tau, C_t$ are the underlying price, strike, time to maturity and option price. In this paper we propose a novel decision function and study the network $(S_t/K, \tau) \to V_t/K$ where $V_t$ is the time value. Empirical experiments will be carried out to demonstrate that this new decision function significantly improves Hutchinson-Lo-Poggio’s model by faster learning and better generalization performance. We prove that a shallow neural network with the logistic activation is a universal approximator in $L^{2}(\mathbb{R} \times [0, 1])$. As a corollary $V_t/K$ but not $C_t/K$ can be approximated by superpositions of logistic functions on $\mathbb{R}^+ \times [0, 1]$. This justifies the benefit of time value oriented decision functions in option pricing models. \|
Tasks
Published	2019-10-02
URL	https://arxiv.org/abs/1910.01490v2
PDF	https://arxiv.org/pdf/1910.01490v2.pdf
PWC	https://paperswithcode.com/paper/the-option-pricing-model-based-on-time-values
Repo
Framework

Reinforcement Learning-Based Trajectory Design for the Aerial Base Stations


Title	Reinforcement Learning-Based Trajectory Design for the Aerial Base Stations
Authors	Behzad Khamidehi, Elvino S. Sousa
Abstract	In this paper, the trajectory optimization problem for a multi-aerial base station (ABS) communication network is investigated. The objective is to find the trajectory of the ABSs so that the sum-rate of the users served by each ABS is maximized. To reach this goal, along with the optimal trajectory design, optimal power and sub-channel allocation is also of great importance to support the users with the highest possible data rates. To solve this complicated problem, we divide it into two sub-problems: ABS trajectory optimization sub-problem, and joint power and sub-channel assignment sub-problem. Then, based on the Q-learning method, we develop a distributed algorithm which solves these sub-problems efficiently, and does not need significant amount of information exchange between the ABSs and the core network. Simulation results show that although Q-learning is a model-free reinforcement learning technique, it has a remarkable capability to train the ABSs to optimize their trajectories based on the received reward signals, which carry decent information from the topology of the network.
Tasks	Q-Learning
Published	2019-06-23
URL	https://arxiv.org/abs/1906.09550v2
PDF	https://arxiv.org/pdf/1906.09550v2.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-based-trajectory
Repo
Framework

Learned Critical Probabilistic Roadmaps for Robotic Motion Planning


Title	Learned Critical Probabilistic Roadmaps for Robotic Motion Planning
Authors	Brian Ichter, Edward Schmerling, Tsang-Wei Edward Lee, Aleksandra Faust
Abstract	Sampling-based motion planning techniques have emerged as an efficient algorithmic paradigm for solving complex motion planning problems. These approaches use a set of probing samples to construct an implicit graph representation of the robot’s state space, allowing arbitrarily accurate representations as the number of samples increases to infinity. In practice, however, solution trajectories only rely on a few critical states, often defined by structure in the state space (e.g., doorways). In this work we propose a general method to identify these critical states via graph-theoretic techniques (betweenness centrality) and learn to predict criticality from only local environment features. These states are then leveraged more heavily via global connections within a hierarchical graph, termed Critical Probabilistic Roadmaps. Critical PRMs are demonstrated to achieve up to three orders of magnitude improvement over uniform sampling, while preserving the guarantees and complexity of sampling-based motion planning. A video is available at https://youtu.be/AYoD-pGd9ms.
Tasks	Motion Planning
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03701v1
PDF	https://arxiv.org/pdf/1910.03701v1.pdf
PWC	https://paperswithcode.com/paper/learned-critical-probabilistic-roadmaps-for
Repo
Framework

DeepScaffold: a comprehensive tool for scaffold-based de novo drug discovery using deep learning


Title	DeepScaffold: a comprehensive tool for scaffold-based de novo drug discovery using deep learning
Authors	Yibo Li, Jianxing Hu, Yanxing Wang, Jielong Zhou, Liangren Zhang, Zhenming Liu
Abstract	The ultimate goal of drug design is to find novel compounds with desirable pharmacological properties. Designing molecules retaining particular scaffolds as the core structures of the molecules is one of the efficient ways to obtain potential drug candidates with desirable properties. We proposed a scaffold-based molecular generative model for scaffold-based drug discovery, which performs molecule generation based on a wide spectrum of scaffold definitions, including BM-scaffolds, cyclic skeletons, as well as scaffolds with specifications on side-chain properties. The model can generalize the learned chemical rules of adding atoms and bonds to a given scaffold. Furthermore, the generated compounds were evaluated by molecular docking in DRD2 targets and the results demonstrated that this approach can be effectively applied to solve several drug design problems, including the generation of compounds containing a given scaffold and de novo drug design of potential drug candidates with specific docking scores. Finally, a command line interface is created.
Tasks	Drug Discovery
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07209v4
PDF	https://arxiv.org/pdf/1908.07209v4.pdf
PWC	https://paperswithcode.com/paper/deepscaffold-a-comprehensive-tool-for
Repo
Framework