October 19, 2019

3358 words 16 mins read

Paper Group ANR 280

Precision Medicine as an Accelerator for Next Generation Cognitive Supercomputing. A Data Analytics Framework for Aggregate Data Analysis. Adding New Tasks to a Single Network with Weight Transformations using Binary Masks. Randomized ICA and LDA Dimensionality Reduction Methods for Hyperspectral Image Classification. Evaluation of Momentum Diverse …

Precision Medicine as an Accelerator for Next Generation Cognitive Supercomputing


Title	Precision Medicine as an Accelerator for Next Generation Cognitive Supercomputing
Authors	Edmon Begoli, Jim Brase, Bambi DeLaRosa, Penelope Jones, Dimitri Kusnezov, Jason Paragas, Rick Stevens, Fred Streitz, Georgia Tourassi
Abstract	In the past several years, we have taken advantage of a number of opportunities to advance the intersection of next generation high-performance computing AI and big data technologies through partnerships in precision medicine. Today we are in the throes of piecing together what is likely the most unique convergence of medical data and computer technologies. But more deeply, we observe that the traditional paradigm of computer simulation and prediction needs fundamental revision. This is the time for a number of reasons. We will review what the drivers are, why now, how this has been approached over the past several years, and where we are heading.
Tasks
Published	2018-04-29
URL	http://arxiv.org/abs/1804.11002v1
PDF	http://arxiv.org/pdf/1804.11002v1.pdf
PWC	https://paperswithcode.com/paper/precision-medicine-as-an-accelerator-for-next
Repo
Framework

A Data Analytics Framework for Aggregate Data Analysis


Title	A Data Analytics Framework for Aggregate Data Analysis
Authors	Sanket Tavarageri, Nag Mani, Anand Ramasubramanian, Jaskiran Kalsi
Abstract	In many contexts, we have access to aggregate data, but individual level data is unavailable. For example, medical studies sometimes report only aggregate statistics about disease prevalence because of privacy concerns. Even so, many a time it is desirable, and in fact could be necessary to infer individual level characteristics from aggregate data. For instance, other researchers who want to perform more detailed analysis of disease characteristics would require individual level data. Similar challenges arise in other fields too including politics, and marketing. In this paper, we present an end-to-end pipeline for processing of aggregate data to derive individual level statistics, and then using the inferred data to train machine learning models to answer questions of interest. We describe a novel algorithm for reconstructing fine-grained data from summary statistics. This step will create multiple candidate datasets which will form the input to the machine learning models. The advantage of the highly parallel architecture we propose is that uncertainty in the generated fine-grained data will be compensated by the use of multiple candidate fine-grained datasets. Consequently, the answers derived from the machine learning models will be more valid and usable. We validate our approach using data from a challenging medical problem called Acute Traumatic Coagulopathy.
Tasks
Published	2018-09-16
URL	http://arxiv.org/abs/1809.05877v1
PDF	http://arxiv.org/pdf/1809.05877v1.pdf
PWC	https://paperswithcode.com/paper/a-data-analytics-framework-for-aggregate-data
Repo
Framework

Adding New Tasks to a Single Network with Weight Transformations using Binary Masks


Title	Adding New Tasks to a Single Network with Weight Transformations using Binary Masks
Authors	Massimiliano Mancini, Elisa Ricci, Barbara Caputo, Samuel Rota Bulò
Abstract	Visual recognition algorithms are required today to exhibit adaptive abilities. Given a deep model trained on a specific, given task, it would be highly desirable to be able to adapt incrementally to new tasks, preserving scalability as the number of new tasks increases, while at the same time avoiding catastrophic forgetting issues. Recent work has shown that masking the internal weights of a given original conv-net through learned binary variables is a promising strategy. We build upon this intuition and take into account more elaborated affine transformations of the convolutional weights that include learned binary masks. We show that with our generalization it is possible to achieve significantly higher levels of adaptation to new tasks, enabling the approach to compete with fine tuning strategies by requiring slightly more than 1 bit per network parameter per additional task. Experiments on two popular benchmarks showcase the power of our approach, that achieves the new state of the art on the Visual Decathlon Challenge.
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1805.11119v2
PDF	http://arxiv.org/pdf/1805.11119v2.pdf
PWC	https://paperswithcode.com/paper/adding-new-tasks-to-a-single-network-with
Repo
Framework

Randomized ICA and LDA Dimensionality Reduction Methods for Hyperspectral Image Classification


Title	Randomized ICA and LDA Dimensionality Reduction Methods for Hyperspectral Image Classification
Authors	Chippy Jayaprakash, Bharath Bhushan Damodaran, Sowmya V, K P Soman
Abstract	Dimensionality reduction is an important step in processing the hyperspectral images (HSI) to overcome the curse of dimensionality problem. Linear dimensionality reduction methods such as Independent component analysis (ICA) and Linear discriminant analysis (LDA) are commonly employed to reduce the dimensionality of HSI. These methods fail to capture non-linear dependency in the HSI data, as data lies in the nonlinear manifold. To handle this, nonlinear transformation techniques based on kernel methods were introduced for dimensionality reduction of HSI. However, the kernel methods involve cubic computational complexity while computing the kernel matrix, and thus its potential cannot be explored when the number of pixels (samples) are large. In literature a fewer number of pixels are randomly selected to partial to overcome this issue, however this sub-optimal strategy might neglect important information in the HSI. In this paper, we propose randomized solutions to the ICA and LDA dimensionality reduction methods using Random Fourier features, and we label them as RFFICA and RFFLDA. Our proposed method overcomes the scalability issue and to handle the non-linearities present in the data more efficiently. Experiments conducted with two real-world hyperspectral datasets demonstrates that our proposed randomized methods outperform the conventional kernel ICA and kernel LDA in terms overall, per-class accuracies and computational time.
Tasks	Dimensionality Reduction, Hyperspectral Image Classification, Image Classification
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07347v1
PDF	http://arxiv.org/pdf/1804.07347v1.pdf
PWC	https://paperswithcode.com/paper/randomized-ica-and-lda-dimensionality
Repo
Framework

Evaluation of Momentum Diverse Input Iterative Fast Gradient Sign Method (M-DI2-FGSM) Based Attack Method on MCS 2018 Adversarial Attacks on Black Box Face Recognition System


Title	Evaluation of Momentum Diverse Input Iterative Fast Gradient Sign Method (M-DI2-FGSM) Based Attack Method on MCS 2018 Adversarial Attacks on Black Box Face Recognition System
Authors	Md Ashraful Alam Milton
Abstract	The convolutional neural network is the crucial tool for the recent success of deep learning based methods on various computer vision tasks like classification, segmentation, and detection. Convolutional neural networks achieved state-of-the-art performance in these tasks and every day pushing the limit of computer vision and AI. However, adversarial attack on computer vision systems is threatening their application in the real life and in safety-critical applications. Necessarily, Finding adversarial examples are important to detect susceptible models to attack and take safeguard measures to overcome the adversarial attacks. In this regard, MCS 2018 Adversarial Attacks on Black Box Face Recognition challenge aims to facilitate the research of finding new adversarial attack techniques and their effectiveness in generating adversarial examples. In this challenge, the attack"s nature is targeted-attack on the black-box neural network where we have no knowledge about black-block"s inner structure. The attacker must modify a set of five images of a single person so that the neural network miss-classify them as target image which is a set of five images of another person. In this competition, we applied Momentum Diverse Input Iterative Fast Gradient Sign Method (M-DI2-FGSM) to make an adversarial attack on black-box face recognition system. We tested our method on MCS 2018 Adversarial Attacks on Black Box Face Recognition challenge and found competitive result. Our solution got validation score 1.404 which better than baseline score 1.407 and stood 14 place among 132 teams in the leader-board. Further improvement can be achieved by finding improved feature extraction from source image, carefully chosen hyper-parameters, finding improved substitute model of the black-box and better optimization method.
Tasks	Adversarial Attack, Face Recognition
Published	2018-06-23
URL	http://arxiv.org/abs/1806.08970v1
PDF	http://arxiv.org/pdf/1806.08970v1.pdf
PWC	https://paperswithcode.com/paper/evaluation-of-momentum-diverse-input
Repo
Framework

Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles


Title	Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles
Authors	Vahid Behzadan, Arslan Munir
Abstract	With the rapidly growing interest in autonomous navigation, the body of research on motion planning and collision avoidance techniques has enjoyed an accelerating rate of novel proposals and developments. However, the complexity of new techniques and their safety requirements render the bulk of current benchmarking frameworks inadequate, thus leaving the need for efficient comparison techniques unanswered. This work proposes a novel framework based on deep reinforcement learning for benchmarking the behavior of collision avoidance mechanisms under the worst-case scenario of dealing with an optimal adversarial agent, trained to drive the system into unsafe states. We describe the architecture and flow of this framework as a benchmarking solution, and demonstrate its efficacy via a practical case study of comparing the reliability of two collision avoidance mechanisms in response to intentional collision attempts.
Tasks	Autonomous Navigation, Autonomous Vehicles, Motion Planning
Published	2018-06-04
URL	http://arxiv.org/abs/1806.01368v1
PDF	http://arxiv.org/pdf/1806.01368v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-reinforcement-learning-framework
Repo
Framework

A computational perspective of the role of Thalamus in cognition


Title	A computational perspective of the role of Thalamus in cognition
Authors	Nima Dehghani, Ralf D. Wimmer
Abstract	Thalamus has traditionally been considered as only a relay source of cortical inputs, with hierarchically organized cortical circuits serially transforming thalamic signals to cognitively-relevant representations. Given the absence of local excitatory connections within the thalamus, the notion of thalamic `relay’ seemed like a reasonable description over the last several decades. Recent advances in experimental approaches and theory provide a broader perspective on the role of the thalamus in cognitively-relevant cortical computations, and suggest that only a subset of thalamic circuit motifs fit the relay description. Here, we discuss this perspective and highlight the potential role for the thalamus – and specifically mediodorsal (MD) nucleus – in dynamic selection of cortical representations through a combination of intrinsic thalamic computations and output signals that change cortical network functional parameters. We suggest that through the contextual modulation of cortical computation, thalamus and cortex jointly optimize the information/cost tradeoff in an emergent fashion. We emphasize that coordinated experimental and theoretical efforts will provide a path to understanding the role of the thalamus in cognition, along with an understanding to augment cognitive capacity in health and disease. \|
Tasks
Published	2018-03-02
URL	http://arxiv.org/abs/1803.00997v3
PDF	http://arxiv.org/pdf/1803.00997v3.pdf
PWC	https://paperswithcode.com/paper/a-computational-perspective-of-the-role-of
Repo
Framework

Water Disaggregation via Shape Features based Bayesian Discriminative Sparse Coding


Title	Water Disaggregation via Shape Features based Bayesian Discriminative Sparse Coding
Authors	Bingsheng Wang, Xuchao Zhang, Chang-Tien Lu, Feng Chen
Abstract	As the issue of freshwater shortage is increasing daily, it is critical to take effective measures for water conservation. According to previous studies, device level consumption could lead to significant freshwater conservation. Existing water disaggregation methods focus on learning the signatures for appliances; however, they are lack of the mechanism to accurately discriminate parallel appliances’ consumption. In this paper, we propose a Bayesian Discriminative Sparse Coding model using Laplace Prior (BDSC-LP) to extensively enhance the disaggregation performance. To derive discriminative basis functions, shape features are presented to describe the low-sampling-rate water consumption patterns. A Gibbs sampling based inference method is designed to extend the discriminative capability of the disaggregation dictionaries. Extensive experiments were performed to validate the effectiveness of the proposed model using both real-world and synthetic datasets.
Tasks
Published	2018-08-26
URL	http://arxiv.org/abs/1808.08951v1
PDF	http://arxiv.org/pdf/1808.08951v1.pdf
PWC	https://paperswithcode.com/paper/water-disaggregation-via-shape-features-based
Repo
Framework

Deep Neural Networks for Swept Volume Prediction Between Configurations


Title	Deep Neural Networks for Swept Volume Prediction Between Configurations
Authors	Hao-Tien Lewis Chiang, Aleksandra Faust, Lydia Tapia
Abstract	Swept Volume (SV), the volume displaced by an object when it is moving along a trajectory, is considered a useful metric for motion planning. First, SV has been used to identify collisions along a trajectory, because it directly measures the amount of space required for an object to move. Second, in sampling-based motion planning, SV is an ideal distance metric, because it correlates to the likelihood of success of the expensive local planning step between two sampled configurations. However, in both of these applications, traditional SV algorithms are too computationally expensive for efficient motion planning. In this work, we train Deep Neural Networks (DNNs) to learn the size of SV for specific robot geometries. Results for two robots, a 6 degree of freedom (DOF) rigid body and a 7 DOF fixed-based manipulator, indicate that the network estimations are very close to the true size of SV and is more than 1500 times faster than a state of the art SV estimation algorithm.
Tasks	Motion Planning
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11597v1
PDF	http://arxiv.org/pdf/1805.11597v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-networks-for-swept-volume
Repo
Framework

Hierarchical Bipartite Graph Convolution Networks


Title	Hierarchical Bipartite Graph Convolution Networks
Authors	Marcel Nassar
Abstract	Recently, graph neural networks have been adopted in a wide variety of applications ranging from relational representations to modeling irregular data domains such as point clouds and social graphs. However, the space of graph neural network architectures remains highly fragmented impeding the development of optimized implementations similar to what is available for convolutional neural networks. In this work, we present BiGraphNet, a graph neural network architecture that generalizes many popular graph neural network models and enables new efficient operations similar to those supported by ConvNets. By explicitly separating the input and output nodes, BiGraphNet: (i) generalizes the graph convolution to support new efficient operations such as coarsened graph convolutions (similar to strided convolution in convnets), multiple input graphs convolution and graph expansions (unpooling) which can be used to implement various graph architectures such as graph autoencoders, and graph residual nets; and (ii) accelerates and scales the computations and memory requirements in hierarchical networks by performing computations only at specified output nodes.
Tasks
Published	2018-11-17
URL	http://arxiv.org/abs/1812.03813v2
PDF	http://arxiv.org/pdf/1812.03813v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-bipartite-graph-convolution
Repo
Framework

Distance formulas capable of unifying Euclidian space and probability space


Title	Distance formulas capable of unifying Euclidian space and probability space
Authors	Zecang Gu, Ling Dong
Abstract	For pattern recognition like image recognition, it has become clear that each machine-learning dictionary data actually became data in probability space belonging to Euclidean space. However, the distances in the Euclidean space and the distances in the probability space are separated and ununified when machine learning is introduced in the pattern recognition. There is still a problem that it is impossible to directly calculate an accurate matching relation between the sampling data of the read image and the learned dictionary data. In this research, we focused on the reason why the distance is changed and the extent of change when passing through the probability space from the original Euclidean distance among data belonging to multiple probability spaces containing Euclidean space. By finding the reason of the cause of the distance error and finding the formula expressing the error quantitatively, a possible distance formula to unify Euclidean space and probability space is found. Based on the results of this research, the relationship between machine-learning dictionary data and sampling data was clearly understood for pattern recognition. As a result, the calculation of collation among data and machine-learning to compete mutually between data are cleared, and complicated calculations became unnecessary. Finally, using actual pattern recognition data, experimental demonstration of a possible distance formula to unify Euclidean space and probability space discovered by this research was carried out, and the effectiveness of the result was confirmed.
Tasks
Published	2018-01-06
URL	http://arxiv.org/abs/1801.01972v1
PDF	http://arxiv.org/pdf/1801.01972v1.pdf
PWC	https://paperswithcode.com/paper/distance-formulas-capable-of-unifying
Repo
Framework

Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems


Title	Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems
Authors	Florian Kreyssig, Inigo Casanueva, Pawel Budzianowski, Milica Gasic
Abstract	User Simulators are one of the major tools that enable offline training of task-oriented dialogue systems. For this task the Agenda-Based User Simulator (ABUS) is often used. The ABUS is based on hand-crafted rules and its output is in semantic form. Issues arise from both properties such as limited diversity and the inability to interface a text-level belief tracker. This paper introduces the Neural User Simulator (NUS) whose behaviour is learned from a corpus and which generates natural language, hence needing a less labelled dataset than simulators generating a semantic output. In comparison to much of the past work on this topic, which evaluates user simulators on corpus-based metrics, we use the NUS to train the policy of a reinforcement learning based Spoken Dialogue System. The NUS is compared to the ABUS by evaluating the policies that were trained using the simulators. Cross-model evaluation is performed i.e. training on one simulator and testing on the other. Furthermore, the trained policies are tested on real users. In both evaluation tasks the NUS outperformed the ABUS.
Tasks	Spoken Dialogue Systems, Task-Oriented Dialogue Systems
Published	2018-05-17
URL	http://arxiv.org/abs/1805.06966v1
PDF	http://arxiv.org/pdf/1805.06966v1.pdf
PWC	https://paperswithcode.com/paper/neural-user-simulation-for-corpus-based-1
Repo
Framework

A Data-Driven Approach for Autonomous Motion Planning and Control in Off-Road Driving Scenarios


Title	A Data-Driven Approach for Autonomous Motion Planning and Control in Off-Road Driving Scenarios
Authors	Hossein Rastgoftar, Bingxin Zhang, Ella M. Atkins
Abstract	This paper presents a novel data-driven approach to vehicle motion planning and control in off-road driving scenarios. For autonomous off-road driving, environmental conditions impact terrain traversability as a function of weather, surface composition, and slope. Geographical information system (GIS) and National Centers for Environmental Information datasets are processed to provide this information for interactive planning and control system elements. A top-level global route planner (GRP) defines optimal waypoints using dynamic programming (DP). A local path planner (LPP) computes a desired trajectory between waypoints such that infeasible control states and collisions with obstacles are avoided. The LPP also updates the GRP with real-time sensing and control data. A low-level feedback controller applies feedback linearization to asymptotically track the specified LPP trajectory. Autonomous driving simulation results are presented for traversal of terrains in Oregon and Indiana case studies.
Tasks	Autonomous Driving, Motion Planning
Published	2018-05-25
URL	http://arxiv.org/abs/1805.09951v1
PDF	http://arxiv.org/pdf/1805.09951v1.pdf
PWC	https://paperswithcode.com/paper/a-data-driven-approach-for-autonomous-motion
Repo
Framework

Revisiting Character-Based Neural Machine Translation with Capacity and Compression


Title	Revisiting Character-Based Neural Machine Translation with Capacity and Compression
Authors	Colin Cherry, George Foster, Ankur Bapna, Orhan Firat, Wolfgang Macherey
Abstract	Translating characters instead of words or word-fragments has the potential to simplify the processing pipeline for neural machine translation (NMT), and improve results by eliminating hyper-parameters and manual feature engineering. However, it results in longer sequences in which each symbol contains less information, creating both modeling and computational challenges. In this paper, we show that the modeling problem can be solved by standard sequence-to-sequence architectures of sufficient depth, and that deep models operating at the character level outperform identical models operating over word fragments. This result implies that alternative architectures for handling character input are better viewed as methods for reducing computation time than as improved ways of modeling longer sequences. From this perspective, we evaluate several techniques for character-level NMT, verify that they do not match the performance of our deep character baseline model, and evaluate the performance versus computation time tradeoffs they offer. Within this framework, we also perform the first evaluation for NMT of conditional computation over time, in which the model learns which timesteps can be skipped, rather than having them be dictated by a fixed schedule specified before training begins.
Tasks	Feature Engineering, Machine Translation
Published	2018-08-29
URL	http://arxiv.org/abs/1808.09943v1
PDF	http://arxiv.org/pdf/1808.09943v1.pdf
PWC	https://paperswithcode.com/paper/revisiting-character-based-neural-machine
Repo
Framework

PCA of high dimensional random walks with comparison to neural network training


Title	PCA of high dimensional random walks with comparison to neural network training
Authors	Joseph M. Antognini, Jascha Sohl-Dickstein
Abstract	One technique to visualize the training of neural networks is to perform PCA on the parameters over the course of training and to project to the subspace spanned by the first few PCA components. In this paper we compare this technique to the PCA of a high dimensional random walk. We compute the eigenvalues and eigenvectors of the covariance of the trajectory and prove that in the long trajectory and high dimensional limit most of the variance is in the first few PCA components, and that the projection of the trajectory onto any subspace spanned by PCA components is a Lissajous curve. We generalize these results to a random walk with momentum and to an Ornstein-Uhlenbeck processes (i.e., a random walk in a quadratic potential) and show that in high dimensions the walk is not mean reverting, but will instead be trapped at a fixed distance from the minimum. We finally compare the distribution of PCA variances and the PCA projected training trajectories of a linear model trained on CIFAR-10 and ResNet-50-v2 trained on Imagenet and find that the distribution of PCA variances resembles a random walk with drift.
Tasks
Published	2018-06-22
URL	http://arxiv.org/abs/1806.08805v1
PDF	http://arxiv.org/pdf/1806.08805v1.pdf
PWC	https://paperswithcode.com/paper/pca-of-high-dimensional-random-walks-with
Repo
Framework