Paper Group ANR 1033
Graph networks as learnable physics engines for inference and control. Development of formal models, algorithms, procedures, engineering and functioning of the software system “Instrumental complex for ontological engineering purpose”. Reasoning About Physical Interactions with Object-Oriented Prediction and Planning. DeepMood: Modeling Mobile Phon …
Graph networks as learnable physics engines for inference and control
| Title | Graph networks as learnable physics engines for inference and control |
| Authors | Alvaro Sanchez-Gonzalez, Nicolas Heess, Jost Tobias Springenberg, Josh Merel, Martin Riedmiller, Raia Hadsell, Peter Battaglia |
| Abstract | Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new class of learnable models–based on graph networks–which implement an inductive bias for object- and relation-centric representations of complex, dynamical systems. Our results show that as a forward model, our approach supports accurate predictions from real and simulated data, and surprisingly strong and efficient generalization, across eight distinct physical systems which we varied parametrically and structurally. We also found that our inference model can perform system identification. Our models are also differentiable, and support online planning via gradient-based trajectory optimization, as well as offline policy optimization. Our framework offers new opportunities for harnessing and exploiting rich knowledge about the world, and takes a key step toward building machines with more human-like representations of the world. |
| Tasks | |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01242v1 |
| http://arxiv.org/pdf/1806.01242v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-networks-as-learnable-physics-engines |
| Repo | |
| Framework | |
Development of formal models, algorithms, procedures, engineering and functioning of the software system “Instrumental complex for ontological engineering purpose”
| Title | Development of formal models, algorithms, procedures, engineering and functioning of the software system “Instrumental complex for ontological engineering purpose” |
| Authors | A. V. Palagin, N. G. Petrenko, V. Yu. Velychko, K. S. Malakhov |
| Abstract | The given paper considered a generalized model representation of the software system “Instrumental complex for ontological engineering purpose”. Represented complete software system development process. Developed relevant formal models of the software system “Instrumental complex for ontological engineering purpose”, represented as mathematical expressions, UML diagrams, and also described the three-tier architecture of the software system “Instrumental complex for ontological engineering purpose” in a client-server environment. |
| Tasks | |
| Published | 2018-03-24 |
| URL | http://arxiv.org/abs/1803.10684v1 |
| http://arxiv.org/pdf/1803.10684v1.pdf | |
| PWC | https://paperswithcode.com/paper/development-of-formal-models-algorithms |
| Repo | |
| Framework | |
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
| Title | Reasoning About Physical Interactions with Object-Oriented Prediction and Planning |
| Authors | Michael Janner, Sergey Levine, William T. Freeman, Joshua B. Tenenbaum, Chelsea Finn, Jiajun Wu |
| Abstract | Object-based factorizations provide a useful level of abstraction for interacting with the world. Building explicit object representations, however, often requires supervisory signals that are difficult to obtain in practice. We present a paradigm for learning object-centric representations for physical scene understanding without direct supervision of object properties. Our model, Object-Oriented Prediction and Planning (O2P2), jointly learns a perception function to map from image observations to object representations, a pairwise physics interaction function to predict the time evolution of a collection of objects, and a rendering function to map objects back to pixels. For evaluation, we consider not only the accuracy of the physical predictions of the model, but also its utility for downstream tasks that require an actionable representation of intuitive physics. After training our model on an image prediction task, we can use its learned representations to build block towers more complicated than those observed during training. |
| Tasks | Scene Understanding |
| Published | 2018-12-28 |
| URL | http://arxiv.org/abs/1812.10972v2 |
| http://arxiv.org/pdf/1812.10972v2.pdf | |
| PWC | https://paperswithcode.com/paper/reasoning-about-physical-interactions-with-1 |
| Repo | |
| Framework | |
DeepMood: Modeling Mobile Phone Typing Dynamics for Mood Detection
| Title | DeepMood: Modeling Mobile Phone Typing Dynamics for Mood Detection |
| Authors | Bokai Cao, Lei Zheng, Chenwei Zhang, Philip S. Yu, Andrea Piscitello, John Zulueta, Olu Ajilore, Kelly Ryan, Alex D. Leow |
| Abstract | The increasing use of electronic forms of communication presents new opportunities in the study of mental health, including the ability to investigate the manifestations of psychiatric diseases unobtrusively and in the setting of patients’ daily lives. A pilot study to explore the possible connections between bipolar affective disorder and mobile phone usage was conducted. In this study, participants were provided a mobile phone to use as their primary phone. This phone was loaded with a custom keyboard that collected metadata consisting of keypress entry time and accelerometer movement. Individual character data with the exceptions of the backspace key and space bar were not collected due to privacy concerns. We propose an end-to-end deep architecture based on late fusion, named DeepMood, to model the multi-view metadata for the prediction of mood scores. Experimental results show that 90.31% prediction accuracy on the depression score can be achieved based on session-level mobile phone typing dynamics which is typically less than one minute. It demonstrates the feasibility of using mobile phone metadata to infer mood disturbance and severity. |
| Tasks | |
| Published | 2018-03-23 |
| URL | http://arxiv.org/abs/1803.08986v1 |
| http://arxiv.org/pdf/1803.08986v1.pdf | |
| PWC | https://paperswithcode.com/paper/deepmood-modeling-mobile-phone-typing |
| Repo | |
| Framework | |
Question Answering by Reasoning Across Documents with Graph Convolutional Networks
| Title | Question Answering by Reasoning Across Documents with Graph Convolutional Networks |
| Authors | Nicola De Cao, Wilker Aziz, Ivan Titov |
| Abstract | Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and reasons relying on information spread within documents and across multiple documents. We frame it as an inference problem on a graph. Mentions of entities are nodes of this graph while edges encode relations between different mentions (e.g., within- and cross-document co-reference). Graph convolutional networks (GCNs) are applied to these graphs and trained to perform multi-step reasoning. Our Entity-GCN method is scalable and compact, and it achieves state-of-the-art results on a multi-document question answering dataset, WikiHop (Welbl et al., 2018). |
| Tasks | Question Answering, Reading Comprehension |
| Published | 2018-08-29 |
| URL | http://arxiv.org/abs/1808.09920v3 |
| http://arxiv.org/pdf/1808.09920v3.pdf | |
| PWC | https://paperswithcode.com/paper/question-answering-by-reasoning-across |
| Repo | |
| Framework | |
Large-Scale Neuromorphic Spiking Array Processors: A quest to mimic the brain
| Title | Large-Scale Neuromorphic Spiking Array Processors: A quest to mimic the brain |
| Authors | Chetan Singh Thakur, Jamal Molin, Gert Cauwenberghs, Giacomo Indiveri, Kundan Kumar, Ning Qiao, Johannes Schemmel, Runchun Wang, Elisabetta Chicca, Jennifer Olson Hasler, Jae-sun Seo, Shimeng Yu, Yu Cao, André van Schaik, Ralph Etienne-Cummings |
| Abstract | Neuromorphic engineering (NE) encompasses a diverse range of approaches to information processing that are inspired by neurobiological systems, and this feature distinguishes neuromorphic systems from conventional computing systems. The brain has evolved over billions of years to solve difficult engineering problems by using efficient, parallel, low-power computation. The goal of NE is to design systems capable of brain-like computation. Numerous large-scale neuromorphic projects have emerged recently. This interdisciplinary field was listed among the top 10 technology breakthroughs of 2014 by the MIT Technology Review and among the top 10 emerging technologies of 2015 by the World Economic Forum. NE has two-way goals: one, a scientific goal to understand the computational properties of biological neural systems by using models implemented in integrated circuits (ICs); second, an engineering goal to exploit the known properties of biological systems to design and implement efficient devices for engineering applications. Building hardware neural emulators can be extremely useful for simulating large-scale neural models to explain how intelligent behavior arises in the brain. The principle advantages of neuromorphic emulators are that they are highly energy efficient, parallel and distributed, and require a small silicon area. Thus, compared to conventional CPUs, these neuromorphic emulators are beneficial in many engineering applications such as for the porting of deep learning algorithms for various recognitions tasks. In this review article, we describe some of the most significant neuromorphic spiking emulators, compare the different architectures and approaches used by them, illustrate their advantages and drawbacks, and highlight the capabilities that each can deliver to neural modelers. |
| Tasks | |
| Published | 2018-05-23 |
| URL | http://arxiv.org/abs/1805.08932v1 |
| http://arxiv.org/pdf/1805.08932v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-neuromorphic-spiking-array |
| Repo | |
| Framework | |
Point cloud segmentation using hierarchical tree for architectural models
| Title | Point cloud segmentation using hierarchical tree for architectural models |
| Authors | Omair Hassaan, Abeera Shamail, Zain Butt, Murtaza Taj |
| Abstract | Recent developments in the 3D scanning technologies have made the generation of highly accurate 3D point clouds relatively easy but the segmentation of these point clouds remains a challenging area. A number of techniques have set precedent of either planar or primitive based segmentation in literature. In this work, we present a novel and an effective primitive based point cloud segmentation algorithm. The primary focus, i.e. the main technical contribution of our method is a hierarchical tree which iteratively divides the point cloud into segments. This tree uses an exclusive energy function and a 3D convolutional neural network, HollowNets to classify the segments. We test the efficacy of our proposed approach using both real and synthetic data obtaining an accuracy greater than 90% for domes and minarets. |
| Tasks | |
| Published | 2018-06-22 |
| URL | http://arxiv.org/abs/1806.08572v1 |
| http://arxiv.org/pdf/1806.08572v1.pdf | |
| PWC | https://paperswithcode.com/paper/point-cloud-segmentation-using-hierarchical |
| Repo | |
| Framework | |
Learning Convex Partitions and Computing Game-theoretic Equilibria from Best Response Queries
| Title | Learning Convex Partitions and Computing Game-theoretic Equilibria from Best Response Queries |
| Authors | Paul W. Goldberg, Francisco J. Marmolejo-Cossío |
| Abstract | Suppose that an $m$-simplex is partitioned into $n$ convex regions having disjoint interiors and distinct labels, and we may learn the label of any point by querying it. The learning objective is to know, for any point in the simplex, a label that occurs within some distance $\epsilon$ from that point. We present two algorithms for this task: Constant-Dimension Generalised Binary Search (CD-GBS), which for constant $m$ uses $poly(n, \log \left( \frac{1}{\epsilon} \right))$ queries, and Constant-Region Generalised Binary Search (CR-GBS), which uses CD-GBS as a subroutine and for constant $n$ uses $poly(m, \log \left( \frac{1}{\epsilon} \right))$ queries. We show via Kakutani’s fixed-point theorem that these algorithms provide bounds on the best-response query complexity of computing approximate well-supported equilibria of bimatrix games in which one of the players has a constant number of pure strategies. We also partially extend our results to games with multiple players, establishing further query complexity bounds for computing approximate well-supported equilibria in this setting. |
| Tasks | |
| Published | 2018-07-17 |
| URL | http://arxiv.org/abs/1807.06170v2 |
| http://arxiv.org/pdf/1807.06170v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-convex-partitions-and-computing-game |
| Repo | |
| Framework | |
Learning Shaping Strategies in Human-in-the-loop Interactive Reinforcement Learning
| Title | Learning Shaping Strategies in Human-in-the-loop Interactive Reinforcement Learning |
| Authors | Chao Yu, Tianpei Yang, Wenxuan Zhu, Dongxu wang, Guangliang Li |
| Abstract | Providing reinforcement learning agents with informationally rich human knowledge can dramatically improve various aspects of learning. Prior work has developed different kinds of shaping methods that enable agents to learn efficiently in complex environments. All these methods, however, tailor human guidance to agents in specialized shaping procedures, thus embodying various characteristics and advantages in different domains. In this paper, we investigate the interplay between different shaping methods for more robust learning performance. We propose an adaptive shaping algorithm which is capable of learning the most suitable shaping method in an on-line manner. Results in two classic domains verify its effectiveness from both simulated and real human studies, shedding some light on the role and impact of human factors in human-robot collaborative learning. |
| Tasks | |
| Published | 2018-11-10 |
| URL | http://arxiv.org/abs/1811.04272v1 |
| http://arxiv.org/pdf/1811.04272v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-shaping-strategies-in-human-in-the |
| Repo | |
| Framework | |
A Direct Sum Result for the Information Complexity of Learning
| Title | A Direct Sum Result for the Information Complexity of Learning |
| Authors | Ido Nachum, Jonathan Shafer, Amir Yehudayoff |
| Abstract | How many bits of information are required to PAC learn a class of hypotheses of VC dimension $d$? The mathematical setting we follow is that of Bassily et al. (2018), where the value of interest is the mutual information $\mathrm{I}(S;A(S))$ between the input sample $S$ and the hypothesis outputted by the learning algorithm $A$. We introduce a class of functions of VC dimension $d$ over the domain $\mathcal{X}$ with information complexity at least $\Omega\left(d\log \log \frac{\mathcal{X}}{d}\right)$ bits for any consistent and proper algorithm (deterministic or random). Bassily et al. proved a similar (but quantitatively weaker) result for the case $d=1$. The above result is in fact a special case of a more general phenomenon we explore. We define the notion of information complexity of a given class of functions $\mathcal{H}$. Intuitively, it is the minimum amount of information that an algorithm for $\mathcal{H}$ must retain about its input to ensure consistency and properness. We prove a direct sum result for information complexity in this context; roughly speaking, the information complexity sums when combining several classes. |
| Tasks | |
| Published | 2018-04-16 |
| URL | http://arxiv.org/abs/1804.05474v1 |
| http://arxiv.org/pdf/1804.05474v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-direct-sum-result-for-the-information |
| Repo | |
| Framework | |
Towards more Reliable Transfer Learning
| Title | Towards more Reliable Transfer Learning |
| Authors | Zirui Wang, Jaime Carbonell |
| Abstract | Multi-source transfer learning has been proven effective when within-target labeled data is scarce. Previous work focuses primarily on exploiting domain similarities and assumes that source domains are richly or at least comparably labeled. While this strong assumption is never true in practice, this paper relaxes it and addresses challenges related to sources with diverse labeling volume and diverse reliability. The first challenge is combining domain similarity and source reliability by proposing a new transfer learning method that utilizes both source-target similarities and inter-source relationships. The second challenge involves pool-based active learning where the oracle is only available in source domains, resulting in an integrated active transfer learning framework that incorporates distribution matching and uncertainty sampling. Extensive experiments on synthetic and two real-world datasets clearly demonstrate the superiority of our proposed methods over several baselines including state-of-the-art transfer learning methods. |
| Tasks | Active Learning, Transfer Learning |
| Published | 2018-07-06 |
| URL | http://arxiv.org/abs/1807.02235v1 |
| http://arxiv.org/pdf/1807.02235v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-more-reliable-transfer-learning |
| Repo | |
| Framework | |
A MapReduce based Big-data Framework for Object Extraction from Mosaic Satellite Images
| Title | A MapReduce based Big-data Framework for Object Extraction from Mosaic Satellite Images |
| Authors | Suleyman Eken, Ahmet Sayar |
| Abstract | We propose a framework stitching of vector representations of large scale raster mosaic images in distributed computing model. In this way, the negative effect of the lack of resources of the central system and scalability problem can be eliminated. The product obtained by this study can be used in applications requiring spatial and temporal analysis on big satellite map images. This study also shows that big data frameworks are not only used in applications of text-based data mining and machine learning algorithms, but also used in applications of algorithms in image processing. The effectiveness of the product realized with this project is also going to be proven by scalability and performance tests performed on real world LandSat-8 satellite images. |
| Tasks | |
| Published | 2018-08-26 |
| URL | http://arxiv.org/abs/1808.08528v1 |
| http://arxiv.org/pdf/1808.08528v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-mapreduce-based-big-data-framework-for |
| Repo | |
| Framework | |
Detection limits in the high-dimensional spiked rectangular model
| Title | Detection limits in the high-dimensional spiked rectangular model |
| Authors | Ahmed El Alaoui, Michael I. Jordan |
| Abstract | We study the problem of detecting the presence of a single unknown spike in a rectangular data matrix, in a high-dimensional regime where the spike has fixed strength and the aspect ratio of the matrix converges to a finite limit. This setup includes Johnstone’s spiked covariance model. We analyze the likelihood ratio of the spiked model against an “all noise” null model of reference, and show it has asymptotically Gaussian fluctuations in a region below—but in general not up to—the so-called BBP threshold from random matrix theory. Our result parallels earlier findings of Onatski et al.\ (2013) and Johnstone-Onatski (2015) for spherical spikes. We present a probabilistic approach capable of treating generic product priors. In particular, sparsity in the spike is allowed. Our approach is based on Talagrand’s interpretation of the cavity method from spin-glass theory. The question of the maximal parameter region where asymptotic normality is expected to hold is left open. This region is shaped by the prior in a non-trivial way. We conjecture that this is the entire paramagnetic phase of an associated spin-glass model, and is defined by the vanishing of the replica-symmetric solution of Lesieur et al.\ (2015). |
| Tasks | |
| Published | 2018-02-20 |
| URL | http://arxiv.org/abs/1802.07309v3 |
| http://arxiv.org/pdf/1802.07309v3.pdf | |
| PWC | https://paperswithcode.com/paper/detection-limits-in-the-high-dimensional |
| Repo | |
| Framework | |
SmartChoices: Hybridizing Programming and Machine Learning
| Title | SmartChoices: Hybridizing Programming and Machine Learning |
| Authors | Victor Carbune, Thierry Coppey, Alexander Daryin, Thomas Deselaers, Nikhil Sarda, Jay Yagnik |
| Abstract | We present SmartChoices, an approach to making machine learning (ML) a first class citizen in programming languages which we see as one way to lower the entrance cost to applying ML to problems in new domains. There is a growing divide in approaches to building systems: on the one hand, programming leverages human experts to define a system while on the other hand behavior is learned from data in machine learning. We propose to hybridize these two by providing a 3-call API which we expose through an object called SmartChoice. We describe the SmartChoices-interface, how it can be used in programming with minimal code changes, and demonstrate that it is an easy to use but still powerful tool by demonstrating improvements over not using ML at all on three algorithmic problems: binary search, QuickSort, and caches. In these three examples, we replace the commonly used heuristics with an ML model entirely encapsulated within a SmartChoice and thus requiring minimal code changes. As opposed to previous work applying ML to algorithmic problems, our proposed approach does not require to drop existing implementations but seamlessly integrates into the standard software development workflow and gives full control to the software developer over how ML methods are applied. Our implementation relies on standard Reinforcement Learning (RL) methods. To learn faster, we use the heuristic function, which they are replacing, as an initial function. We show how this initial function can be used to speed up and stabilize learning while providing a safety net that prevents performance to become substantially worse – allowing for a safe deployment in critical applications in real life. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://arxiv.org/abs/1810.00619v3 |
| https://arxiv.org/pdf/1810.00619v3.pdf | |
| PWC | https://paperswithcode.com/paper/smartchoices-hybridizing-programming-and |
| Repo | |
| Framework | |
A Bio-inspired Redundant Sensing Architecture
| Title | A Bio-inspired Redundant Sensing Architecture |
| Authors | Anh Tuan Nguyen, Jian Xu, Zhi Yang |
| Abstract | Sensing is the process of deriving signals from the environment that allows artificial systems to interact with the physical world. The Shannon theorem specifies the maximum rate at which information can be acquired. However, this upper bound is hard to achieve in many man-made systems. The biological visual systems, on the other hand, have highly efficient signal representation and processing mechanisms that allow precise sensing. In this work, we argue that redundancy is one of the critical characteristics for such superior performance. We show architectural advantages by utilizing redundant sensing, including correction of mismatch error and significant precision enhancement. For a proof-of-concept demonstration, we have designed a heuristic-based analog-to-digital converter - a zero-dimensional quantizer. Through Monte Carlo simulation with the error probabilistic distribution as a priori, the performance approaching the Shannon limit is feasible. In actual measurements without knowing the error distribution, we observe at least 2-bit extra precision. The results may also help explain biological processes including the dominance of binocular vision, the functional roles of the fixational eye movements, and the structural mechanisms allowing hyperacuity. |
| Tasks | |
| Published | 2018-02-15 |
| URL | http://arxiv.org/abs/1802.05686v1 |
| http://arxiv.org/pdf/1802.05686v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-bio-inspired-redundant-sensing-architecture |
| Repo | |
| Framework | |
