PyTorchKR Papers

최신 논문

총 3,383편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1810.09930

Machine Learning Accelerated Likelihood-Free Event Reconstruction in Dark Matter Direct Detection

Reconstructing the position of an interaction for any dual-phase time projection chamber (TPC) with the best precision is key to directly detecting Dark Matter. Using the likelihood-free framework, a new algorithm to reconstruct the 2-D (x; y) position and the size of the charge signal (e) of an interaction is presented. The algorithm uses the charge signal (S2) light distribution obtained by simulating events using a waveform generator. To deal with the computational effort required by the likelihood-free approach, we employ the Bayesian Optimization for Likelihood-Free Inference (BOLFI) algorithm. Together with BOLFI, prior distributions for the parameters of interest (x; y; e) and highly informative discrepancy measures to perform the analyses are introduced. We evaluate the quality of the proposed algorithm by a comparison against the currently existing alternative methods using a large-scale simulation study. BOLFI provides a natural probabilistic uncertainty measure for the reconstruction and it improved the accuracy of the reconstruction over the next best algorithm by up to 15% when focusing on events over a large radii (R > 30 cm, the outer 37% of the detector). In addition, BOLFI provides the smallest uncertainties among all the tested methods.

arXiv:1810.05475공식 코드 · Papers with Code

Quantifying the amount of visual information used by neural caption generators

This paper addresses the sensitivity of neural image caption generators to their visual input. A sensitivity analysis and omission analysis based on image foils is reported, showing that the extent to which image captioning architectures retain and are sensitive to visual information varies depending on the type of word being generated and the position in the caption as a whole. We motivate this work in the context of broader goals in the field to achieve more explainability in AI.

arXiv:1810.05597공식 코드 · Papers with Code

Learning Grid Cells as Vector Representation of Self-Position Coupled with Matrix Representation of Self-Motion

This paper proposes a representational model for grid cells. In this model, the 2D self-position of the agent is represented by a high-dimensional vector, and the 2D self-motion or displacement of the agent is represented by a matrix that transforms the vector. Each component of the vector is a unit or a cell. The model consists of the following three sub-models. (1) Vector-matrix multiplication. The movement from the current position to the next position is modeled by matrix-vector multiplication, i.e., the vector of the next position is obtained by multiplying the matrix of the motion to the vector of the current position. (2) Magnified local isometry. The angle between two nearby vectors equals the Euclidean distance between the two corresponding positions multiplied by a magnifying factor. (3) Global adjacency kernel. The inner product between two vectors measures the adjacency between the two corresponding positions, which is defined by a kernel function of the Euclidean distance between the two positions. Our representational model has explicit algebra and geometry. It can learn hexagon patterns of grid cells, and it is capable of error correction, path integral and path planning.

arXiv:1810.01866

Learning an internal representation of the end-effector configuration space

Current machine learning techniques proposed to automatically discover a robot kinematics usually rely on a priori information about the robot's structure, sensors properties or end-effector position. This paper proposes a method to estimate a certain aspect of the forward kinematics model with no such information. An internal representation of the end-effector configuration is generated from unstructured proprioceptive and exteroceptive data flow under very limited assumptions. A mapping from the proprioceptive space to this representational space can then be used to control the robot.

arXiv:1810.01616

Cascaded Pyramid Network for 3D Human Pose Estimation Challenge

Over the past decade, there has been a growing interest in human pose estimation. Although much work has been done on 2D pose estimation, 3D pose estimation has still been relatively studied less. In this paper, we propose a top-bottom based two-stage 3D estimation framework. GloabalNet and RefineNet in our 2D pose estimation process enable us to find occluded or invisible 2D joints while 2D-to-3D pose estimator composed of residual blocks is used to lift 2D joints to 3D joints effectively. The proposed method achieves promising results with mean per joint position error at 42.39 on the validation dataset on `3D Human Pose Estimation within the ECCV 2018 PoseTrack Challenge.'

arXiv:1810.01398

Optimal Completion Distillation for Sequence Learning

We present Optimal Completion Distillation (OCD), a training procedure for optimizing sequence to sequence models based on edit distance. OCD is efficient, has no hyper-parameters of its own, and does not require pretraining or joint optimization with conditional log-likelihood. Given a partial sequence generated by the model, we first identify the set of optimal suffixes that minimize the total edit distance, using an efficient dynamic programming algorithm. Then, for each position of the generated sequence, we use a target distribution that puts equal probability on the first token of all the optimal suffixes. OCD achieves the state-of-the-art performance on end-to-end speech recognition, on both Wall Street Journal and Librispeech datasets, achieving $9.3\%$ WER and $4.5\%$ WER respectively.

arXiv:1810.01193

Characterization of Visual Object Representations in Rat Primary Visual Cortex

For most animal species, quick and reliable identification of visual objects is critical for survival. This applies also to rodents, which, in recent years, have become increasingly popular models of visual functions. For this reason in this work we analyzed how various properties of visual objects are represented in rat primary visual cortex (V1). The analysis has been carried out through supervised (classification) and unsupervised (clustering) learning methods. We assessed quantitatively the discrimination capabilities of V1 neurons by demonstrating how photometric properties (luminosity and object position in the scene) can be derived directly from the neuronal responses.

arXiv:1809.10788

Learning and Acting in Peripersonal Space: Moving, Reaching, and Grasping

The young infant explores its body, its sensorimotor system, and the immediately accessible parts of its environment, over the course of a few months creating a model of peripersonal space useful for reaching and grasping objects around it. Drawing on constraints from the empirical literature on infant behavior, we present a preliminary computational model of this learning process, implemented and evaluated on a physical robot. The learning agent explores the relationship between the configuration space of the arm, sensing joint angles through proprioception, and its visual perceptions of the hand and grippers. The resulting knowledge is represented as the peripersonal space (PPS) graph, where nodes represent states of the arm, edges represent safe movements, and paths represent safe trajectories from one pose to another. In our model, the learning process is driven by intrinsic motivation. When repeatedly performing an action, the agent learns the typical result, but also detects unusual outcomes, and is motivated to learn how to make those unusual results reliable. Arm motions typically leave the static background unchanged, but occasionally bump an object, changing its static position. The reach action is learned as a reliable way to bump and move an object in the environment. Similarly, once a reliable reach action is learned, it typically makes a quasi-static change in the environment, moving an object from one static position to another. The unusual outcome is that the object is accidentally grasped (thanks to the innate Palmar reflex), and thereafter moves dynamically with the hand. Learning to make grasps reliable is more complex than for reaches, but we demonstrate significant progress. Our current results are steps toward autonomous sensorimotor learning of motion, reaching, and grasping in peripersonal space, based on unguided exploration and intrinsic motivation.

arXiv:1809.10276

Growing and Retaining AI Talent for the United States Government

Artificial Intelligence and Machine Learning have become transformative to a number of industries, and as such many industries need for AI talent is increasing the demand for individuals with these skills. This continues to exacerbate the difficulty of acquiring and retaining talent for the United States Federal Government, both for its direct employees as well as the companies that support it. We take the position that by focusing on growing and retaining current talent through a number of cultural changes, the government can work to remediate this problem today.

arXiv:1809.09767공식 코드 · Papers with Code

Night-to-Day Image Translation for Retrieval-based Localization

Visual localization is a key step in many robotics pipelines, allowing the robot to (approximately) determine its position and orientation in the world. An efficient and scalable approach to visual localization is to use image retrieval techniques. These approaches identify the image most similar to a query photo in a database of geo-tagged images and approximate the query's pose via the pose of the retrieved database image. However, image retrieval across drastically different illumination conditions, e.g. day and night, is still a problem with unsatisfactory results, even in this age of powerful neural models. This is due to a lack of a suitably diverse dataset with true correspondences to perform end-to-end learning. A recent class of neural models allows for realistic translation of images among visual domains with relatively little training data and, most importantly, without ground-truth pairings. In this paper, we explore the task of accurately localizing images captured from two traversals of the same area in both day and night. We propose ToDayGAN - a modified image-translation model to alter nighttime driving images to a more useful daytime representation. We then compare the daytime and translated night images to obtain a pose estimate for the night image using the known 6-DOF position of the closest day image. Our approach improves localization performance by over 250% compared the current state-of-the-art, in the context of standard metrics in multiple categories.

arXiv:1809.05645

OffsetNet: Deep Learning for Localization in the Lung using Rendered Images

Navigating surgical tools in the dynamic and tortuous anatomy of the lung's airways requires accurate, real-time localization of the tools with respect to the preoperative scan of the anatomy. Such localization can inform human operators or enable closed-loop control by autonomous agents, which would require accuracy not yet reported in the literature. In this paper, we introduce a deep learning architecture, called OffsetNet, to accurately localize a bronchoscope in the lung in real-time. After training on only 30 minutes of recorded camera images in conserved regions of a lung phantom, OffsetNet tracks the bronchoscope's motion on a held-out recording through these same regions at an update rate of 47 Hz and an average position error of 1.4 mm. Because this model performs poorly in less conserved regions, we augment the training dataset with simulated images from these regions. To bridge the gap between camera and simulated domains, we implement domain randomization and a generative adversarial network (GAN). After training on simulated images, OffsetNet tracks the bronchoscope's motion in less conserved regions at an average position error of 2.4 mm, which meets conservative thresholds required for successful tracking.

arXiv:1809.06139

Automatic Electrodes Detection during simultaneous EEG/fMRI acquisition

Simultaneous EEG/fMRI acquisition allows to measure brain activity at high spatial-temporal resolution. The localisation of EEG sources depends on several parameters including the position of the electrodes on the scalp. The position of the MR electrodes during its acquisitions is obtained with the use of the UTE sequence allowing their visualisation. The retrieval of the electrodes consists in obtaining the volume where the electrodes are located by applying a sphere detection algorithm. We detect around 90% of electrodes for each subject, and our UTE-based electrode detection showed an average position error of 3.7mm for all subjects.

arXiv:1809.05283

Macquarie University at BioASQ 6b: Deep learning and deep reinforcement learning for query-based multi-document summarisation

This paper describes Macquarie University's contribution to the BioASQ Challenge (BioASQ 6b, Phase B). We focused on the extraction of the ideal answers, and the task was approached as an instance of query-based multi-document summarisation. In particular, this paper focuses on the experiments related to the deep learning and reinforcement learning approaches used in the submitted runs. The best run used a deep learning model under a regression-based framework. The deep learning architecture used features derived from the output of LSTM chains on word embeddings, plus features based on similarity with the query, and sentence position. The reinforcement learning approach was a proof-of-concept prototype that trained a global policy using REINFORCE. The global policy was implemented as a neural network that used $tf.idf$ features encoding the candidate sentence, question, and context.

arXiv:1809.05216

Enhanced Optic Disk and Cup Segmentation with Glaucoma Screening from Fundus Images using Position encoded CNNs

In this manuscript, we present a robust method for glaucoma screening from fundus images using an ensemble of convolutional neural networks (CNNs). The pipeline comprises of first segmenting the optic disk and optic cup from the fundus image, then extracting a patch centered around the optic disk and subsequently feeding to the classification network to differentiate the image as diseased or healthy. In the segmentation network, apart from the image, we make use of spatial co-ordinate (X \& Y) space so as to learn the structure of interest better. The classification network is composed of a DenseNet201 and a ResNet18 which were pre-trained on a large cohort of natural images. On the REFUGE validation data (n=400), the segmentation network achieved a dice score of 0.88 and 0.64 for optic disc and optic cup respectively. For the tasking differentiating images affected with glaucoma from healthy images, the area under the ROC curve was observed to be 0.85.

arXiv:1809.04771

Towards Coinductive Theory Exploration in Horn Clause Logic: Position Paper

Coinduction occurs in two guises in Horn clause logic: in proofs of self-referencing properties and relations, and in proofs involving construction of (possibly irregular) infinite data. Both instances of coinductive reasoning appeared in the literature before, but a systematic analysis of these two kinds of proofs and of their relation was lacking. We propose a general proof-theoretic framework for handling both kinds of coinduction arising in Horn clause logic. To this aim, we propose a coinductive extension of Miller et al's framework of uniform proofs and prove its soundness relative to coinductive models of Horn clause logic.

arXiv:1809.04536

Unpaired Brain MR-to-CT Synthesis using a Structure-Constrained CycleGAN

The cycleGAN is becoming an influential method in medical image synthesis. However, due to a lack of direct constraints between input and synthetic images, the cycleGAN cannot guarantee structural consistency between these two images, and such consistency is of extreme importance in medical imaging. To overcome this, we propose a structure-constrained cycleGAN for brain MR-to-CT synthesis using unpaired data that defines an extra structure-consistency loss based on the modality independent neighborhood descriptor to constrain structural consistency. Additionally, we use a position-based selection strategy for selecting training images instead of a completely random selection scheme. Experimental results on synthesizing CT images from brain MR images demonstrate that our method is better than the conventional cycleGAN and approximates the cycleGAN trained with paired data.

arXiv:1809.03928공식 코드 · Papers with Code

SAI, a Sensible Artificial Intelligence that plays Go

We propose a multiple-komi modification of the AlphaGo Zero/Leela Zero paradigm. The winrate as a function of the komi is modeled with a two-parameters sigmoid function, so that the neural network must predict just one more variable to assess the winrate for all komi values. A second novel feature is that training is based on self-play games that occasionally branch -- with changed komi -- when the position is uneven. With this setting, reinforcement learning is showed to work on 7x7 Go, obtaining very strong playing agents. As a useful byproduct, the sigmoid parameters given by the network allow to estimate the score difference on the board, and to evaluate how much the game is decided.

arXiv:1809.03406공식 코드 · Papers with Code

Combining imagination and heuristics to learn strategies that generalize

Deep reinforcement learning can match or exceed human performance in stable contexts, but with minor changes to the environment artificial networks, unlike humans, often cannot adapt. Humans rely on a combination of heuristics to simplify computational load and imagination to extend experiential learning to new and more challenging environments. Motivated by theories of the hierarchical organization of the human prefrontal networks, we have developed a model of hierarchical reinforcement learning that combines both heuristics and imagination into a stumbler-strategist network. We test performance of this network using Wythoff's game, a gridworld environment with a known optimal strategy. We show that a heuristic labeling of each position as hot or cold, combined with imagined play, both accelerates learning and promotes transfer to novel games, while also improving model interpretability.

arXiv:1809.03402

Does Your Phone Know Your Touch?

This paper explores supervised techniques for continuous anomaly detection from biometric touch screen data. A capacitive sensor array used to mimic a touch screen as used to collect touch and swipe gestures from participants. The gestures are recorded over fixed segments of time, with position and force measured for each gesture. Support Vector Machine, Logistic Regression, and Gaussian mixture models were tested to learn individual touch patterns. Test results showed true negative and true positive scores of over 95% accuracy for all gesture types, with logistic regression models far outperforming the other methods. A more expansive and varied data collection over longer periods of time is needed to determine pragmatic usage of these results.

arXiv:1809.02983공식 코드 · Papers with Code

Dual Attention Network for Scene Segmentation

In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the selfattention mechanism. Unlike previous works that capture contexts by multi-scale features fusion, we propose a Dual Attention Networks (DANet) to adaptively integrate local features with their global dependencies. Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively. The position attention module selectively aggregates the features at each position by a weighted sum of the features at all positions. Similar features would be related to each other regardless of their distances. Meanwhile, the channel attention module selectively emphasizes interdependent channel maps by integrating associated features among all channel maps. We sum the outputs of the two attention modules to further improve feature representation which contributes to more precise segmentation results. We achieve new state-of-the-art segmentation performance on three challenging scene segmentation datasets, i.e., Cityscapes, PASCAL Context and COCO Stuff dataset. In particular, a Mean IoU score of 81.5% on Cityscapes test set is achieved without using coarse data. We make the code and trained model publicly available at https://github.com/junfu1115/DANet