Paper Group ANR 200
Seamless Integration and Coordination of Cognitive Skills in Humanoid Robots: A Deep Learning Approach. Distributed Solution of Large-Scale Linear Systems via Accelerated Projection-Based Consensus. Exploiting oddsmaker bias to improve the prediction of NFL outcomes. Overcomplete Frame Thresholding for Acoustic Scene Analysis. Fault Detection of Br …
Seamless Integration and Coordination of Cognitive Skills in Humanoid Robots: A Deep Learning Approach
| Title | Seamless Integration and Coordination of Cognitive Skills in Humanoid Robots: A Deep Learning Approach |
| Authors | Jungsik Hwang, Jun Tani |
| Abstract | This study investigates how adequate coordination among the different cognitive processes of a humanoid robot can be developed through end-to-end learning of direct perception of visuomotor stream. We propose a deep dynamic neural network model built on a dynamic vision network, a motor generation network, and a higher-level network. The proposed model was designed to process and to integrate direct perception of dynamic visuomotor patterns in a hierarchical model characterized by different spatial and temporal constraints imposed on each level. We conducted synthetic robotic experiments in which a robot learned to read human’s intention through observing the gestures and then to generate the corresponding goal-directed actions. Results verify that the proposed model is able to learn the tutored skills and to generalize them to novel situations. The model showed synergic coordination of perception, action and decision making, and it integrated and coordinated a set of cognitive skills including visual perception, intention reading, attention switching, working memory, action preparation and execution in a seamless manner. Analysis reveals that coherent internal representations emerged at each level of the hierarchy. Higher-level representation reflecting actional intention developed by means of continuous integration of the lower-level visuo-proprioceptive stream. |
| Tasks | Decision Making |
| Published | 2017-06-08 |
| URL | http://arxiv.org/abs/1706.02423v1 |
| http://arxiv.org/pdf/1706.02423v1.pdf | |
| PWC | https://paperswithcode.com/paper/seamless-integration-and-coordination-of |
| Repo | |
| Framework | |
Distributed Solution of Large-Scale Linear Systems via Accelerated Projection-Based Consensus
| Title | Distributed Solution of Large-Scale Linear Systems via Accelerated Projection-Based Consensus |
| Authors | Navid Azizan-Ruhi, Farshad Lahouti, Salman Avestimehr, Babak Hassibi |
| Abstract | Solving a large-scale system of linear equations is a key step at the heart of many algorithms in machine learning, scientific computing, and beyond. When the problem dimension is large, computational and/or memory constraints make it desirable, or even necessary, to perform the task in a distributed fashion. In this paper, we consider a common scenario in which a taskmaster intends to solve a large-scale system of linear equations by distributing subsets of the equations among a number of computing machines/cores. We propose an accelerated distributed consensus algorithm, in which at each iteration every machine updates its solution by adding a scaled version of the projection of an error signal onto the nullspace of its system of equations, and where the taskmaster conducts an averaging over the solutions with momentum. The convergence behavior of the proposed algorithm is analyzed in detail and analytically shown to compare favorably with the convergence rate of alternative distributed methods, namely distributed gradient descent, distributed versions of Nesterov’s accelerated gradient descent and heavy-ball method, the block Cimmino method, and ADMM. On randomly chosen linear systems, as well as on real-world data sets, the proposed method offers significant speed-up relative to all the aforementioned methods. Finally, our analysis suggests a novel variation of the distributed heavy-ball method, which employs a particular distributed preconditioning, and which achieves the same theoretical convergence rate as the proposed consensus-based method. |
| Tasks | |
| Published | 2017-08-04 |
| URL | http://arxiv.org/abs/1708.01413v2 |
| http://arxiv.org/pdf/1708.01413v2.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-solution-of-large-scale-linear |
| Repo | |
| Framework | |
Exploiting oddsmaker bias to improve the prediction of NFL outcomes
| Title | Exploiting oddsmaker bias to improve the prediction of NFL outcomes |
| Authors | Erik J. Schlicht |
| Abstract | Accurately predicting the outcome of sporting events has been a goal for many groups who seek to maximize profit. What makes this challenging is that the outcome of an event can be influenced by many factors that dynamically change across time. Oddsmakers attempt to estimate these factors by using both algorithmic and subjective methods to set the spread. However, it is well-known that both human and algorithmic decision-making can be biased, so this paper explores if oddsmaker biases can be used in an exploitative manner, in order to improve the prediction of NFL game outcomes. Real-world gambling data was used to train and test different predictive models under varying assumptions. The results show that methods that leverage oddsmaker biases in an exploitative manner perform best under the conditions tested in this paper. These findings suggest that leveraging human and algorithmic decision biases in an exploitative manner may be useful for predicting the outcomes of competitive events, and could lead to increased profit for those who have financial interest in the outcomes. |
| Tasks | Decision Making |
| Published | 2017-10-18 |
| URL | http://arxiv.org/abs/1710.06551v2 |
| http://arxiv.org/pdf/1710.06551v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-oddsmaker-bias-to-improve-the |
| Repo | |
| Framework | |
Overcomplete Frame Thresholding for Acoustic Scene Analysis
| Title | Overcomplete Frame Thresholding for Acoustic Scene Analysis |
| Authors | Romain Cosentino, Randall Balestriero, Richard Baraniuk, Ankit Patel |
| Abstract | In this work, we derive a generic overcomplete frame thresholding scheme based on risk minimization. Overcomplete frames being favored for analysis tasks such as classification, regression or anomaly detection, we provide a way to leverage those optimal representations in real-world applications through the use of thresholding. We validate the method on a large scale bird activity detection task via the scattering network architecture performed by means of continuous wavelets, known for being an adequate dictionary in audio environments. |
| Tasks | Action Detection, Activity Detection, Anomaly Detection |
| Published | 2017-12-25 |
| URL | http://arxiv.org/abs/1712.09117v1 |
| http://arxiv.org/pdf/1712.09117v1.pdf | |
| PWC | https://paperswithcode.com/paper/overcomplete-frame-thresholding-for-acoustic |
| Repo | |
| Framework | |
Fault Detection of Broken Rotor Bar in LS-PMSM Using Random Forests
| Title | Fault Detection of Broken Rotor Bar in LS-PMSM Using Random Forests |
| Authors | Juan C. Quiroz, Norman Mariun, Mohammad Rezazadeh Mehrjou, Mahdi Izadi, Norhisam Misron, Mohd Amran Mohd Radzi |
| Abstract | This paper proposes a new approach to diagnose broken rotor bar failure in a line start-permanent magnet synchronous motor (LS-PMSM) using random forests. The transient current signal during the motor startup was acquired from a healthy motor and a faulty motor with a broken rotor bar fault. We extracted 13 statistical time domain features from the startup transient current signal, and used these features to train and test a random forest to determine whether the motor was operating under normal or faulty conditions. For feature selection, we used the feature importances from the random forest to reduce the number of features to two features. The results showed that the random forest classifies the motor condition as healthy or faulty with an accuracy of 98.8% using all features and with an accuracy of 98.4% by using only the mean-index and impulsion features. The performance of the random forest was compared with a decision tree, Na"ive Bayes classifier, logistic regression, linear ridge, and a support vector machine, with the random forest consistently having a higher accuracy than the other algorithms. The proposed approach can be used in industry for online monitoring and fault diagnostic of LS-PMSM motors and the results can be helpful for the establishment of preventive maintenance plans in factories. |
| Tasks | Fault Detection, Feature Selection |
| Published | 2017-11-03 |
| URL | http://arxiv.org/abs/1711.02510v1 |
| http://arxiv.org/pdf/1711.02510v1.pdf | |
| PWC | https://paperswithcode.com/paper/fault-detection-of-broken-rotor-bar-in-ls |
| Repo | |
| Framework | |
Towards Around-Device Interaction using Corneal Imaging
| Title | Towards Around-Device Interaction using Corneal Imaging |
| Authors | Daniel Schneider, Jens Grubert |
| Abstract | Around-device interaction techniques aim at extending the input space using various sensing modalities on mobile and wearable devices. In this paper, we present our work towards extending the input area of mobile devices using front-facing device-centered cameras that capture reflections in the human eye. As current generation mobile devices lack high resolution front-facing cameras we study the feasibility of around-device interaction using corneal reflective imaging based on a high resolution camera. We present a workflow, a technical prototype and an evaluation, including a migration path from high resolution to low resolution imagers. Our study indicates, that under optimal conditions a spatial sensing resolution of 5 cm in the vicinity of a mobile phone is possible. |
| Tasks | |
| Published | 2017-09-04 |
| URL | http://arxiv.org/abs/1709.00966v1 |
| http://arxiv.org/pdf/1709.00966v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-around-device-interaction-using |
| Repo | |
| Framework | |
Combining Keystroke Dynamics and Face Recognition for User Verification
| Title | Combining Keystroke Dynamics and Face Recognition for User Verification |
| Authors | Abhinav Gupta, Agrim Khanna, Anmol Jagetia, Devansh Sharma, Sanchit Alekh, Vaibhav Choudhary |
| Abstract | The massive explosion and ubiquity of computing devices and the outreach of the web have been the most defining events of the century so far. As more and more people gain access to the internet, traditional know-something and have-something authentication methods such as PINs and passwords are proving to be insufficient for prohibiting unauthorized access to increasingly personal data on the web. Therefore, the need of the hour is a user-verification system that is not only more reliable and secure, but also unobtrusive and minimalistic. Keystroke Dynamics is a novel Biometric Technique; it is not only unobtrusive, but also transparent and inexpensive. The fusion of keystroke dynamics and Face Recognition engenders the most desirable characteristics of a verification system. Our implementation uses Hidden Markov Models (HMM) for modelling the Keystroke Dynamics, with the help of two widely used Feature Vectors: Keypress Latency and Keypress Duration. On the other hand, Face Recognition makes use of the traditional Eigenfaces approach.The results show that the system has a high precision, with a False Acceptance Rate of 5.4% and a False Rejection Rate of 9.2%. Moreover, it is also future-proof, as the hardware requirements, i.e. camera and keyboard (physical or on-screen), have become an indispensable part of modern computing. |
| Tasks | Face Recognition |
| Published | 2017-08-02 |
| URL | http://arxiv.org/abs/1708.00931v1 |
| http://arxiv.org/pdf/1708.00931v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-keystroke-dynamics-and-face |
| Repo | |
| Framework | |
Application of Support Vector Machine Modeling and Graph Theory Metrics for Disease Classification
| Title | Application of Support Vector Machine Modeling and Graph Theory Metrics for Disease Classification |
| Authors | Jessica M. Rudd |
| Abstract | Disease classification is a crucial element of biomedical research. Recent studies have demonstrated that machine learning techniques, such as Support Vector Machine (SVM) modeling, produce similar or improved predictive capabilities in comparison to the traditional method of Logistic Regression. In addition, it has been found that social network metrics can provide useful predictive information for disease modeling. In this study, we combine simulated social network metrics with SVM to predict diabetes in a sample of data from the Behavioral Risk Factor Surveillance System. In this dataset, Logistic Regression outperformed SVM with ROC index of 81.8 and 81.7 for models with and without graph metrics, respectively. SVM with a polynomial kernel had ROC index of 72.9 and 75.6 for models with and without graph metrics, respectively. Although this did not perform as well as Logistic Regression, the results are consistent with previous studies utilizing SVM to classify diabetes. |
| Tasks | |
| Published | 2017-08-01 |
| URL | http://arxiv.org/abs/1708.00122v1 |
| http://arxiv.org/pdf/1708.00122v1.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-support-vector-machine |
| Repo | |
| Framework | |
A multitask deep learning model for real-time deployment in embedded systems
| Title | A multitask deep learning model for real-time deployment in embedded systems |
| Authors | Miquel Martí, Atsuto Maki |
| Abstract | We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We develop a multitask model for both Object Detection and Semantic Segmentation and analyze the challenges that appear during its training. Our multitask network is 1.6x faster, lighter and uses less memory than deploying the single-task models in parallel. We conclude that MTL has the potential to give superior performance in exchange of a more complex training process that introduces challenges not present in single-task models. |
| Tasks | Object Detection, Semantic Segmentation |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1711.00146v1 |
| http://arxiv.org/pdf/1711.00146v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-multitask-deep-learning-model-for-real-time |
| Repo | |
| Framework | |
On spectral partitioning of signed graphs
| Title | On spectral partitioning of signed graphs |
| Authors | Andrew V. Knyazev |
| Abstract | We argue that the standard graph Laplacian is preferable for spectral partitioning of signed graphs compared to the signed Laplacian. Simple examples demonstrate that partitioning based on signs of components of the leading eigenvectors of the signed Laplacian may be meaningless, in contrast to partitioning based on the Fiedler vector of the standard graph Laplacian for signed graphs. We observe that negative eigenvalues are beneficial for spectral partitioning of signed graphs, making the Fiedler vector easier to compute. |
| Tasks | |
| Published | 2017-01-05 |
| URL | http://arxiv.org/abs/1701.01394v2 |
| http://arxiv.org/pdf/1701.01394v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-spectral-partitioning-of-signed-graphs |
| Repo | |
| Framework | |
Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition
| Title | Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition |
| Authors | Mohammad Rostami, Soheil Kolouri, Kyungnam Kim, Eric Eaton |
| Abstract | Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience. Current lifelong learning algorithms rely upon a single learning agent that has centralized access to all data. In this paper, we extend the idea of lifelong learning from a single agent to a network of multiple agents that collectively learn a series of tasks. Each agent faces some (potentially unique) set of tasks; the key idea is that knowledge learned from these tasks may benefit other agents trying to learn different (but related) tasks. Our Collective Lifelong Learning Algorithm (CoLLA) provides an efficient way for a network of agents to share their learned knowledge in a distributed and decentralized manner, while preserving the privacy of the locally observed data. Note that a decentralized scheme is a subclass of distributed algorithms where a central server does not exist and in addition to data, computations are also distributed among the agents. We provide theoretical guarantees for robust performance of the algorithm and empirically demonstrate that CoLLA outperforms existing approaches for distributed multi-task learning on a variety of data sets. |
| Tasks | Multi-Task Learning |
| Published | 2017-09-15 |
| URL | http://arxiv.org/abs/1709.05412v2 |
| http://arxiv.org/pdf/1709.05412v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-agent-distributed-lifelong-learning-for |
| Repo | |
| Framework | |
Music Generation by Deep Learning - Challenges and Directions
| Title | Music Generation by Deep Learning - Challenges and Directions |
| Authors | Jean-Pierre Briot, François Pachet |
| Abstract | In addition to traditional tasks such as prediction, classification and translation, deep learning is receiving growing attention as an approach for music generation, as witnessed by recent research groups such as Magenta at Google and CTRL (Creator Technology Research Lab) at Spotify. The motivation is in using the capacity of deep learning architectures and training techniques to automatically learn musical styles from arbitrary musical corpora and then to generate samples from the estimated distribution. However, a direct application of deep learning to generate content rapidly reaches limits as the generated content tends to mimic the training set without exhibiting true creativity. Moreover, deep learning architectures do not offer direct ways for controlling generation (e.g., imposing some tonality or other arbitrary constraints). Furthermore, deep learning architectures alone are autistic automata which generate music autonomously without human user interaction, far from the objective of interactively assisting musicians to compose and refine music. Issues such as: control, structure, creativity and interactivity are the focus of our analysis. In this paper, we select some limitations of a direct application of deep learning to music generation, analyze why the issues are not fulfilled and how to address them by possible approaches. Various examples of recent systems are cited as examples of promising directions. |
| Tasks | Music Generation |
| Published | 2017-12-09 |
| URL | http://arxiv.org/abs/1712.04371v2 |
| http://arxiv.org/pdf/1712.04371v2.pdf | |
| PWC | https://paperswithcode.com/paper/music-generation-by-deep-learning-challenges |
| Repo | |
| Framework | |
A Neural Model for User Geolocation and Lexical Dialectology
| Title | A Neural Model for User Geolocation and Lexical Dialectology |
| Authors | Afshin Rahimi, Trevor Cohn, Timothy Baldwin |
| Abstract | We propose a simple yet effective text- based user geolocation model based on a neural network with one hidden layer, which achieves state of the art performance over three Twitter benchmark geolocation datasets, in addition to producing word and phrase embeddings in the hidden layer that we show to be useful for detecting dialectal terms. As part of our analysis of dialectal terms, we release DAREDS, a dataset for evaluating dialect term detection methods. |
| Tasks | |
| Published | 2017-04-13 |
| URL | http://arxiv.org/abs/1704.04008v3 |
| http://arxiv.org/pdf/1704.04008v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-neural-model-for-user-geolocation-and |
| Repo | |
| Framework | |
Large-Scale Mapping of Human Activity using Geo-Tagged Videos
| Title | Large-Scale Mapping of Human Activity using Geo-Tagged Videos |
| Authors | Yi Zhu, Sen Liu, Shawn Newsam |
| Abstract | This paper is the first work to perform spatio-temporal mapping of human activity using the visual content of geo-tagged videos. We utilize a recent deep-learning based video analysis framework, termed hidden two-stream networks, to recognize a range of activities in YouTube videos. This framework is efficient and can run in real time or faster which is important for recognizing events as they occur in streaming video or for reducing latency in analyzing already captured video. This is, in turn, important for using video in smart-city applications. We perform a series of experiments to show our approach is able to accurately map activities both spatially and temporally. We also demonstrate the advantages of using the visual content over the tags/titles. |
| Tasks | |
| Published | 2017-06-24 |
| URL | http://arxiv.org/abs/1706.07911v3 |
| http://arxiv.org/pdf/1706.07911v3.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-mapping-of-human-activity-using |
| Repo | |
| Framework | |
A smartphone application to measure the quality of pest control spraying machines via image analysis
| Title | A smartphone application to measure the quality of pest control spraying machines via image analysis |
| Authors | Bruno B. Machado, Gabriel Spadon, Mauro S. Arruda, Wesley N. Goncalves, Andre C. P. L. F. Carvalho, Jose F. Rodrigues-Jr |
| Abstract | The need for higher agricultural productivity has demanded the intensive use of pesticides. However, their correct use depends on assessment methods that can accurately predict how well the pesticides’ spraying covered the intended crop region. Some methods have been proposed in the literature, but their high cost and low portability harm their widespread use. This paper proposes and experimentally evaluates a new methodology based on the use of a smartphone-based mobile application, named DropLeaf. Experiments performed using DropLeaf showed that, in addition to its versatility, it can predict with high accuracy the pesticide spraying. DropLeaf is a five-fold image-processing methodology based on: (i) color space conversion, (ii) threshold noise removal, (iii) convolutional operations of dilation and erosion, (iv) detection of contour markers in the water-sensitive card, and, (v) identification of droplets via the marker-controlled watershed transformation. The authors performed successful experiments over two case studies, the first using a set of synthetic cards and the second using a real-world crop. The proposed tool can be broadly used by farmers equipped with conventional mobile phones, improving the use of pesticides with health, environmental and financial benefits. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07828v3 |
| http://arxiv.org/pdf/1711.07828v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-smartphone-application-to-measure-the |
| Repo | |
| Framework | |
