January 30, 2020

2992 words 15 mins read

Paper Group ANR 272

Fitness Done Right: a Real-time Intelligent Personal Trainer for Exercise Correction. Distributed Synthesis of Surveillance Strategies for Mobile Sensors. Visualizing Topographic Independent Component Analysis with Movies. GRP Model for Sensorimotor Learning. On Multi-Armed Bandit Designs for Phase I Clinical Trials. Trees and Islands – Machine le …

Fitness Done Right: a Real-time Intelligent Personal Trainer for Exercise Correction


Title	Fitness Done Right: a Real-time Intelligent Personal Trainer for Exercise Correction
Authors	Yun Chen, Yiyue Chen, Zhengzhong Tu
Abstract	Keeping fit has been increasingly important for people nowadays. However, people may not get expected exercise results without following professional guidance while hiring personal trainers is expensive. In this paper, an effective real-time system called Fitness Done Right (FDR) is proposed for helping people exercise correctly on their own. The system includes detecting human body parts, recognizing exercise pose and detecting errors for test poses as well as giving correction advice. Generally, two branch multi-stage CNN is used for training data sets in order to learn human body parts and associations. Then, considering two poses, which are plank and squat in our model, we design a detection algorithm, combining Euclidean and angle distances, to determine the pose in the image. Finally, key values for key features of the two poses are computed correspondingly in the pose error detection part, which helps give correction advice. We conduct our system in real-time situation with error rate down to $1.2%$, and the screenshots of experimental results are also presented.
Tasks
Published	2019-10-30
URL	https://arxiv.org/abs/1911.07935v1
PDF	https://arxiv.org/pdf/1911.07935v1.pdf
PWC	https://paperswithcode.com/paper/fitness-done-right-a-real-time-intelligent
Repo
Framework

Distributed Synthesis of Surveillance Strategies for Mobile Sensors


Title	Distributed Synthesis of Surveillance Strategies for Mobile Sensors
Authors	Suda Bharadwaj, Rayna Dimitrova, Ufuk Topcu
Abstract	We study the problem of synthesizing strategies for a mobile sensor network to conduct surveillance in partnership with static alarm triggers. We formulate the problem as a multi-agent reactive synthesis problem with surveillance objectives specified as temporal logic formulas. In order to avoid the state space blow-up arising from a centralized strategy computation, we propose a method to decentralize the surveillance strategy synthesis by decomposing the multi-agent game into subgames that can be solved independently. We also decompose the global surveillance specification into local specifications for each sensor, and show that if the sensors satisfy their local surveillance specifications, then the sensor network as a whole will satisfy the global surveillance objective. Thus, our method is able to guarantee global surveillance properties in a mobile sensor network while synthesizing completely decentralized strategies with no need for coordination between the sensors. We also present a case study in which we demonstrate an application of decentralized surveillance strategy synthesis.
Tasks
Published	2019-02-06
URL	http://arxiv.org/abs/1902.02393v1
PDF	http://arxiv.org/pdf/1902.02393v1.pdf
PWC	https://paperswithcode.com/paper/distributed-synthesis-of-surveillance
Repo
Framework

Visualizing Topographic Independent Component Analysis with Movies


Title	Visualizing Topographic Independent Component Analysis with Movies
Authors	Zhimin Chen, Darius Parvin, Maedbh King, Susan Hao
Abstract	Independent component analysis (ICA) has often been used as a tool to model natural image statistics by separating multivariate signals in the image into components that are assumed to be independent. However, these estimated components oftentimes have higher order dependencies, such as co-activation of components, that are not accounted for in the model. Topographic independent component analysis(TICA), a modification of ICA, takes into account higher order dependencies and orders components topographically as a function of dependence. Here, we aim to visualize the time course of TICA basis activations to movie stimuli. We find that the activity of TICA bases are often clustered and move continuously, potentially resembling activity of topographically organized cells in the visual cortex.
Tasks
Published	2019-01-24
URL	http://arxiv.org/abs/1901.08239v1
PDF	http://arxiv.org/pdf/1901.08239v1.pdf
PWC	https://paperswithcode.com/paper/visualizing-topographic-independent-component
Repo
Framework

GRP Model for Sensorimotor Learning


Title	GRP Model for Sensorimotor Learning
Authors	Tianyu Li, Bolun Dai
Abstract	Learning from complex demonstrations is challenging, especially when the demonstration consists of different strategies. A popular approach is to use a deep neural network to perform imitation learning. However, the structure of that deep neural network has to be ``deep” enough to capture all possible scenarios. Besides the machine learning issue, how humans learn in the sense of physiology has rarely been addressed and relevant works on spinal cord learning are rarer. In this work, we develop a novel modular learning architecture, the Generator and Responsibility Predictor (GRP) model, which automatically learns the sub-task policies from an unsegmented controller demonstration and learns to switch between the policies. We also introduce a more physiological based neural network architecture. We implemented our GRP model and our proposed neural network to form a model the transfers the swing leg control from the brain to the spinal cord. Our result suggests that by using the GRP model the brain can successfully transfer the target swing leg control to the spinal cord and the resulting model can switch between sub-control policies automatically. \|
Tasks	Imitation Learning
Published	2019-03-01
URL	http://arxiv.org/abs/1903.00568v1
PDF	http://arxiv.org/pdf/1903.00568v1.pdf
PWC	https://paperswithcode.com/paper/grp-model-for-sensorimotor-learning
Repo
Framework

On Multi-Armed Bandit Designs for Phase I Clinical Trials


Title	On Multi-Armed Bandit Designs for Phase I Clinical Trials
Authors	Maryam Aziz, Emilie Kaufmann, Marie-Karelle Riviere
Abstract	We study the problem of finding the optimal dosage in a phase I clinical trial through the multi-armed bandit lens. We advocate the use of the Thompson Sampling principle, a flexible algorithm that can accommodate different types of monotonicity assumptions on the toxicity and efficacy of the doses. For the simplest version of Thompson Sampling, based on a uniform prior distribution for each dose, we provide finite-time upper bounds on the number of sub-optimal dose selections, which is unprecedented for dose finding algorithms. Through a large simulation study, we then show that Thompson Sampling based on more sophisticated prior distributions outperform state-of-the-art dose identification algorithms in different types of phase I clinical trials.
Tasks
Published	2019-03-17
URL	http://arxiv.org/abs/1903.07082v1
PDF	http://arxiv.org/pdf/1903.07082v1.pdf
PWC	https://paperswithcode.com/paper/on-multi-armed-bandit-designs-for-phase-i
Repo
Framework

Trees and Islands – Machine learning approach to nuclear physics


Title	Trees and Islands – Machine learning approach to nuclear physics
Authors	Nishchal R. Dwivedi
Abstract	We implement machine learning algorithms to nuclear data. These algorithms are purely data driven and generate models that are capable to capture intricate trends. Gradient boosted trees algorithm is employed to generate a trained model from existing nuclear data, which is used for prediction for data of damping parameter, shell correction energies, quadrupole deformation, pairing gaps, level densities and giant dipole resonance for large number of nuclei. We, in particular, predict level density parameter for superheavy elements which is of great current interest. The predictions made by the machine learning algorithm is found to have standard deviation from 0.00035 to 0.73.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.09764v1
PDF	https://arxiv.org/pdf/1907.09764v1.pdf
PWC	https://paperswithcode.com/paper/trees-and-islands-machine-learning-approach
Repo
Framework

Prior Information Guided Regularized Deep Learning for Cell Nucleus Detection


Title	Prior Information Guided Regularized Deep Learning for Cell Nucleus Detection
Authors	Mohammad Tofighi, Tiantong Guo, Jairam K. P. Vanamala, Vishal Monga
Abstract	Cell nuclei detection is a challenging research topic because of limitations in cellular image quality and diversity of nuclear morphology, i.e. varying nuclei shapes, sizes, and overlaps between multiple cell nuclei. This has been a topic of enduring interest with promising recent success shown by deep learning methods. These methods train Convolutional Neural Networks (CNNs) with a training set of input images and known, labeled nuclei locations. Many such methods are supplemented by spatial or morphological processing. Using a set of canonical cell nuclei shapes, prepared with the help of a domain expert, we develop a new approach that we call Shape Priors with Convolutional Neural Networks (SP-CNN). We further extend the network to introduce a shape prior (SP) layer and then allowing it to become trainable (i.e. optimizable). We call this network tunable SP-CNN (TSP-CNN). In summary, we present new network structures that can incorporate ‘expected behavior’ of nucleus shapes via two components: learnable layers that perform the nucleus detection and a fixed processing part that guides the learning with prior information. Analytically, we formulate two new regularization terms that are targeted at: 1) learning the shapes, 2) reducing false positives while simultaneously encouraging detection inside the cell nucleus boundary. Experimental results on two challenging datasets reveal that the proposed SP-CNN and TSP-CNN can outperform state-of-the-art alternatives.
Tasks
Published	2019-01-21
URL	http://arxiv.org/abs/1901.07061v1
PDF	http://arxiv.org/pdf/1901.07061v1.pdf
PWC	https://paperswithcode.com/paper/prior-information-guided-regularized-deep
Repo
Framework

Compressive Learning for Semi-Parametric Models


Title	Compressive Learning for Semi-Parametric Models
Authors	Michael P. Sheehan, Antoine Gonon, Mike E. Davies
Abstract	In the compressive learning theory, instead of solving a statistical learning problem from the input data, a so-called sketch is computed from the data prior to learning. The sketch has to capture enough information to solve the problem directly from it, allowing to discard the dataset from the memory. This is useful when dealing with large datasets as the size of the sketch does not scale with the size of the database. In this paper, we reformulate the original compressive learning framework to explicitly cater for the class of semi-parametric models. The reformulation takes account of the inherent topology and structure of semi-parametric models, creating an intuitive pathway to the development of compressive learning algorithms. We apply our developed framework to both the semi-parametric models of independent component analysis and subspace clustering, demonstrating the robustness of the framework to explicitly show when a compression in complexity can be achieved.
Tasks
Published	2019-10-22
URL	https://arxiv.org/abs/1910.10024v1
PDF	https://arxiv.org/pdf/1910.10024v1.pdf
PWC	https://paperswithcode.com/paper/compressive-learning-for-semi-parametric
Repo
Framework

DeepPlace: Learning to Place Applications in Multi-Tenant Clusters


Title	DeepPlace: Learning to Place Applications in Multi-Tenant Clusters
Authors	Subrata Mitra, Shanka Subhra Mondal, Nikhil Sheoran, Neeraj Dhake, Ravinder Nehra, Ramanuja Simha
Abstract	Large multi-tenant production clusters often have to handle a variety of jobs and applications with a variety of complex resource usage characteristics. It is non-trivial and non-optimal to manually create placement rules for scheduling that would decide which applications should co-locate. In this paper, we present DeepPlace, a scheduler that learns to exploits various temporal resource usage patterns of applications using Deep Reinforcement Learning (Deep RL) to reduce resource competition across jobs running in the same machine while at the same time optimizing for overall cluster utilization.
Tasks
Published	2019-07-30
URL	https://arxiv.org/abs/1907.12916v1
PDF	https://arxiv.org/pdf/1907.12916v1.pdf
PWC	https://paperswithcode.com/paper/deepplace-learning-to-place-applications-in
Repo
Framework

Concept-Centric Visual Turing Tests for Method Validation


Title	Concept-Centric Visual Turing Tests for Method Validation
Authors	Tatiana Fountoukidou, Raphael Sznitman
Abstract	Recent advances in machine learning for medical imaging have led to impressive increases in model complexity and overall capabilities. However, the ability to discern the precise information a machine learning method is using to make decisions has lagged behind and it is often unclear how these performances are in fact achieved. Conventional evaluation metrics that reduce method performance to a single number or a curve only provide limited insights. Yet, systems used in clinical practice demand thorough validation that such crude characterizations miss. To this end, we present a framework to evaluate classification methods based on a number of interpretable concepts that are crucial for a clinical task. Our approach is inspired by the Turing Test concept and how to devise a test that adaptively questions a method for its ability to interpret medical images. To do this, we make use of a Twenty Questions paradigm whereby we use a probabilistic model to characterize the method’s capacity to grasp task-specific concepts, and we introduce a strategy to sequentially query the method according to its previous answers. The results show that the probabilistic model is able to expose both the dataset’s and the method’s biases, and can be used to reduced the number of queries needed for confident performance evaluation.
Tasks
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06414v2
PDF	https://arxiv.org/pdf/1907.06414v2.pdf
PWC	https://paperswithcode.com/paper/concept-centric-visual-turing-tests-for
Repo
Framework

Meta-learning of Sequential Strategies


Title	Meta-learning of Sequential Strategies
Authors	Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin Miller, Mohammad Azar, Ian Osband, Neil Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg
Abstract	In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. Our goal is to equip the reader with the conceptual foundations of this tool for building new, scalable agents that operate on broad domains. To do so, we present basic algorithmic templates for building near-optimal predictors and reinforcement learners which behave as if they had a probabilistic model that allowed them to efficiently exploit task structure. Furthermore, we recast memory-based meta-learning within a Bayesian framework, showing that the meta-learned strategies are near-optimal because they amortize Bayes-filtered data, where the adaptation is implemented in the memory dynamics as a state-machine of sufficient statistics. Essentially, memory-based meta-learning translates the hard problem of probabilistic sequential inference into a regression problem.
Tasks	Meta-Learning
Published	2019-05-08
URL	https://arxiv.org/abs/1905.03030v2
PDF	https://arxiv.org/pdf/1905.03030v2.pdf
PWC	https://paperswithcode.com/paper/meta-learning-of-sequential-strategies
Repo
Framework

Two-Stream Region Convolutional 3D Network for Temporal Activity Detection


Title	Two-Stream Region Convolutional 3D Network for Temporal Activity Detection
Authors	Huijuan Xu, Abir Das, Kate Saenko
Abstract	We address the problem of temporal activity detection in continuous, untrimmed video streams. This is a difficult task that requires extracting meaningful spatio-temporal features to capture activities, accurately localizing the start and end times of each activity. We introduce a new model, Region Convolutional 3D Network (R-C3D), which encodes the video streams using a three-dimensional fully convolutional network, then generates candidate temporal regions containing activities and finally classifies selected regions into specific activities. Computation is saved due to the sharing of convolutional features between the proposal and the classification pipelines. We further improve the detection performance by efficiently integrating an optical flow based motion stream with the original RGB stream. The two-stream network is jointly optimized by fusing the flow and RGB feature maps at different levels. Additionally, the training stage incorporates an online hard example mining strategy to address the extreme foreground-background imbalance typically observed in any detection pipeline. Instead of heuristically sampling the candidate segments for the final activity classification stage, we rank them according to their performance and only select the worst performers to update the model. This improves the model without heavy hyper-parameter tuning. Extensive experiments on three benchmark datasets are carried out to show superior performance over existing temporal activity detection methods. Our model achieves state-of-the-art results on the THUMOS’14 and Charades datasets. We further demonstrate that our model is a general temporal activity detection framework that does not rely on assumptions about particular dataset properties by evaluating our approach on the ActivityNet dataset.
Tasks	Action Detection, Action Recognition In Videos, Activity Detection, Optical Flow Estimation
Published	2019-06-05
URL	https://arxiv.org/abs/1906.02182v1
PDF	https://arxiv.org/pdf/1906.02182v1.pdf
PWC	https://paperswithcode.com/paper/two-stream-region-convolutional-3d-network
Repo
Framework

Complete Variable-Length Codes: An Excursion into Word Edit Operations


Title	Complete Variable-Length Codes: An Excursion into Word Edit Operations
Authors	Jean Néraud
Abstract	Given an alphabet A and a binary relation $\tau$ $\subseteq$ A * x A * , a language X $\subseteq$ A * is $\tau$-independent if $\tau$ (X) $\cap$ X = $\emptyset$; X is $\tau$-closed if $\tau$ (X) $\subseteq$ X. The language X is complete if any word over A is a factor of some concatenation of words in X. Given a family of languages F containing X, X is maximal in F if no other set of F can stricly contain X. A language X $\subseteq$ A * is a variable-length code if any equation among the words of X is necessarily trivial. The study discusses the relationship between maximality and completeness in the case of $\tau$-independent or $\tau$-closed variable-length codes. We focus to the binary relations by which the images of words are computed by deleting, inserting, or substituting some characters.
Tasks
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02646v1
PDF	https://arxiv.org/pdf/1912.02646v1.pdf
PWC	https://paperswithcode.com/paper/complete-variable-length-codes-an-excursion
Repo
Framework

On the Idiosyncrasies of the Mandarin Chinese Classifier System


Title	On the Idiosyncrasies of the Mandarin Chinese Classifier System
Authors	Shijia Liu, Hongyuan Mei, Adina Williams, Ryan Cotterell
Abstract	While idiosyncrasies of the Chinese classifier system have been a richly studied topic among linguists (Adams and Conklin, 1973; Erbaugh, 1986; Lakoff, 1986), not much work has been done to quantify them with statistical methods. In this paper, we introduce an information-theoretic approach to measuring idiosyncrasy; we examine how much the uncertainty in Mandarin Chinese classifiers can be reduced by knowing semantic information about the nouns that the classifiers modify. Using the empirical distribution of classifiers from the parsed Chinese Gigaword corpus (Graff et al., 2005), we compute the mutual information (in bits) between the distribution over classifiers and distributions over other linguistic quantities. We investigate whether semantic classes of nouns and adjectives differ in how much they reduce uncertainty in classifier choice, and find that it is not fully idiosyncratic; while there are no obvious trends for the majority of semantic classes, shape nouns reduce uncertainty in classifier choice the most.
Tasks
Published	2019-02-26
URL	http://arxiv.org/abs/1902.10193v2
PDF	http://arxiv.org/pdf/1902.10193v2.pdf
PWC	https://paperswithcode.com/paper/on-the-idiosyncrasies-of-the-mandarin-chinese
Repo
Framework

Performance boost of time-delay reservoir computing by non-resonant clock cycle


Title	Performance boost of time-delay reservoir computing by non-resonant clock cycle
Authors	Florian Stelzer, André Röhm, Kathy Lüdge, Serhiy Yanchuk
Abstract	The time-delay-based reservoir computing setup has seen tremendous success in both experiment and simulation. It allows for the construction of large neuromorphic computing systems with only few components. However, until now the interplay of the different timescales has not been investigated thoroughly. In this manuscript, we investigate the effects of a mismatch between the time-delay and the clock cycle for a general model. Typically, these two time scales are considered to be equal. Here we show that the case of equal or resonant time-delay and clock cycle could be actively detrimental and leads to an increase of the approximation error of the reservoir. In particular, we can show that non-resonant ratios of these time scales have maximal memory capacities. We achieve this by translating the periodically driven delay-dynamical system into an equivalent network. Networks that originate from a system with resonant delay-times and clock cycles fail to utilize all of their degrees of freedom, which causes the degradation of their performance.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02534v2
PDF	https://arxiv.org/pdf/1905.02534v2.pdf
PWC	https://paperswithcode.com/paper/performance-boost-of-time-delay-reservoir
Repo
Framework