Paper Group ANR 561
Combining Bayesian Approaches and Evolutionary Techniques for the Inference of Breast Cancer Networks. Meta Inverse Reinforcement Learning via Maximum Reward Sharing for Human Motion Analysis. Review. Machine learning techniques for traffic sign detection. PCA-Initialized Deep Neural Networks Applied To Document Image Analysis. Equivalence Between …
Combining Bayesian Approaches and Evolutionary Techniques for the Inference of Breast Cancer Networks
| Title | Combining Bayesian Approaches and Evolutionary Techniques for the Inference of Breast Cancer Networks |
| Authors | Stefano Beretta, Mauro Castelli, Ivo Goncalves, Ivan Merelli, Daniele Ramazzotti |
| Abstract | Gene and protein networks are very important to model complex large-scale systems in molecular biology. Inferring or reverseengineering such networks can be defined as the process of identifying gene/protein interactions from experimental data through computational analysis. However, this task is typically complicated by the enormously large scale of the unknowns in a rather small sample size. Furthermore, when the goal is to study causal relationships within the network, tools capable of overcoming the limitations of correlation networks are required. In this work, we make use of Bayesian Graphical Models to attach this problem and, specifically, we perform a comparative study of different state-of-the-art heuristics, analyzing their performance in inferring the structure of the Bayesian Network from breast cancer data. |
| Tasks | |
| Published | 2017-03-08 |
| URL | http://arxiv.org/abs/1703.03041v1 |
| http://arxiv.org/pdf/1703.03041v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-bayesian-approaches-and |
| Repo | |
| Framework | |
Meta Inverse Reinforcement Learning via Maximum Reward Sharing for Human Motion Analysis
| Title | Meta Inverse Reinforcement Learning via Maximum Reward Sharing for Human Motion Analysis |
| Authors | Kun Li, Joel W. Burdick |
| Abstract | This work handles the inverse reinforcement learning (IRL) problem where only a small number of demonstrations are available from a demonstrator for each high-dimensional task, insufficient to estimate an accurate reward function. Observing that each demonstrator has an inherent reward for each state and the task-specific behaviors mainly depend on a small number of key states, we propose a meta IRL algorithm that first models the reward function for each task as a distribution conditioned on a baseline reward function shared by all tasks and dependent only on the demonstrator, and then finds the most likely reward function in the distribution that explains the task-specific behaviors. We test the method in a simulated environment on path planning tasks with limited demonstrations, and show that the accuracy of the learned reward function is significantly improved. We also apply the method to analyze the motion of a patient under rehabilitation. |
| Tasks | |
| Published | 2017-10-07 |
| URL | http://arxiv.org/abs/1710.03592v2 |
| http://arxiv.org/pdf/1710.03592v2.pdf | |
| PWC | https://paperswithcode.com/paper/meta-inverse-reinforcement-learning-via |
| Repo | |
| Framework | |
Review. Machine learning techniques for traffic sign detection
| Title | Review. Machine learning techniques for traffic sign detection |
| Authors | Rinat Mukhometzianov, Ying Wang |
| Abstract | An automatic road sign detection system localizes road signs from within images captured by an on-board camera of a vehicle, and support the driver to properly ride the vehicle. Most existing algorithms include a preprocessing step, feature extraction and detection step. This paper arranges the methods applied to road sign detection into two groups: general machine learning, neural networks. In this review, the issues related to automatic road sign detection are addressed, the popular existing methods developed to tackle the road sign detection problem are reviewed, and a comparison of the features of these methods is composed. |
| Tasks | |
| Published | 2017-12-12 |
| URL | http://arxiv.org/abs/1712.04391v2 |
| http://arxiv.org/pdf/1712.04391v2.pdf | |
| PWC | https://paperswithcode.com/paper/review-machine-learning-techniques-for |
| Repo | |
| Framework | |
PCA-Initialized Deep Neural Networks Applied To Document Image Analysis
| Title | PCA-Initialized Deep Neural Networks Applied To Document Image Analysis |
| Authors | Mathias Seuret, Michele Alberti, Rolf Ingold, Marcus Liwicki |
| Abstract | In this paper, we present a novel approach for initializing deep neural networks, i.e., by turning PCA into neural layers. Usually, the initialization of the weights of a deep neural network is done in one of the three following ways: 1) with random values, 2) layer-wise, usually as Deep Belief Network or as auto-encoder, and 3) re-use of layers from another network (transfer learning). Therefore, typically, many training epochs are needed before meaningful weights are learned, or a rather similar dataset is required for seeding a fine-tuning of transfer learning. In this paper, we describe how to turn a PCA into an auto-encoder, by generating an encoder layer of the PCA parameters and furthermore adding a decoding layer. We analyze the initialization technique on real documents. First, we show that a PCA-based initialization is quick and leads to a very stable initialization. Furthermore, for the task of layout analysis we investigate the effectiveness of PCA-based initialization and show that it outperforms state-of-the-art random weight initialization methods. |
| Tasks | Transfer Learning |
| Published | 2017-02-01 |
| URL | http://arxiv.org/abs/1702.00177v1 |
| http://arxiv.org/pdf/1702.00177v1.pdf | |
| PWC | https://paperswithcode.com/paper/pca-initialized-deep-neural-networks-applied |
| Repo | |
| Framework | |
Equivalence Between Policy Gradients and Soft Q-Learning
| Title | Equivalence Between Policy Gradients and Soft Q-Learning |
| Authors | John Schulman, Xi Chen, Pieter Abbeel |
| Abstract | Two of the leading approaches for model-free reinforcement learning are policy gradient methods and $Q$-learning methods. $Q$-learning methods can be effective and sample-efficient when they work, however, it is not well-understood why they work, since empirically, the $Q$-values they estimate are very inaccurate. A partial explanation may be that $Q$-learning methods are secretly implementing policy gradient updates: we show that there is a precise equivalence between $Q$-learning and policy gradient methods in the setting of entropy-regularized reinforcement learning, that “soft” (entropy-regularized) $Q$-learning is exactly equivalent to a policy gradient method. We also point out a connection between $Q$-learning methods and natural policy gradient methods. Experimentally, we explore the entropy-regularized versions of $Q$-learning and policy gradients, and we find them to perform as well as (or slightly better than) the standard variants on the Atari benchmark. We also show that the equivalence holds in practical settings by constructing a $Q$-learning method that closely matches the learning dynamics of A3C without using a target network or $\epsilon$-greedy exploration schedule. |
| Tasks | Policy Gradient Methods, Q-Learning |
| Published | 2017-04-21 |
| URL | http://arxiv.org/abs/1704.06440v4 |
| http://arxiv.org/pdf/1704.06440v4.pdf | |
| PWC | https://paperswithcode.com/paper/equivalence-between-policy-gradients-and-soft |
| Repo | |
| Framework | |
Fast and Strong Convergence of Online Learning Algorithms
| Title | Fast and Strong Convergence of Online Learning Algorithms |
| Authors | Zheng-Chu Guo, Lei Shi |
| Abstract | In this paper, we study the online learning algorithm without explicit regularization terms. This algorithm is essentially a stochastic gradient descent scheme in a reproducing kernel Hilbert space (RKHS). The polynomially decaying step size in each iteration can play a role of regularization to ensure the generalization ability of online learning algorithm. We develop a novel capacity dependent analysis on the performance of the last iterate of online learning algorithm. The contribution of this paper is two-fold. First, our nice analysis can lead to the convergence rate in the standard mean square distance which is the best so far. Second, we establish, for the first time, the strong convergence of the last iterate with polynomially decaying step sizes in the RKHS norm. We demonstrate that the theoretical analysis established in this paper fully exploits the fine structure of the underlying RKHS, and thus can lead to sharp error estimates of online learning algorithm. |
| Tasks | |
| Published | 2017-10-10 |
| URL | http://arxiv.org/abs/1710.03600v1 |
| http://arxiv.org/pdf/1710.03600v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-strong-convergence-of-online |
| Repo | |
| Framework | |
Batch Policy Gradient Methods for Improving Neural Conversation Models
| Title | Batch Policy Gradient Methods for Improving Neural Conversation Models |
| Authors | Kirthevasan Kandasamy, Yoram Bachrach, Ryota Tomioka, Daniel Tarlow, David Carter |
| Abstract | We study reinforcement learning of chatbots with recurrent neural network architectures when the rewards are noisy and expensive to obtain. For instance, a chatbot used in automated customer service support can be scored by quality assurance agents, but this process can be expensive, time consuming and noisy. Previous reinforcement learning work for natural language processing uses on-policy updates and/or is designed for on-line learning settings. We demonstrate empirically that such strategies are not appropriate for this setting and develop an off-policy batch policy gradient method (BPG). We demonstrate the efficacy of our method via a series of synthetic experiments and an Amazon Mechanical Turk experiment on a restaurant recommendations dataset. |
| Tasks | Chatbot, Policy Gradient Methods |
| Published | 2017-02-10 |
| URL | http://arxiv.org/abs/1702.03334v1 |
| http://arxiv.org/pdf/1702.03334v1.pdf | |
| PWC | https://paperswithcode.com/paper/batch-policy-gradient-methods-for-improving |
| Repo | |
| Framework | |
Solving Mixed Model Workplace Time-dependent Assembly Line Balancing Problem with FSS Algorithm
| Title | Solving Mixed Model Workplace Time-dependent Assembly Line Balancing Problem with FSS Algorithm |
| Authors | Joao Batista Monteiro FIlho, Isabela Maria Carneiro de Albuquerque, Fernando Buarque de Lima Neto |
| Abstract | Balancing assembly lines, a family of optimization problems commonly known as Assembly Line Balancing Problem, is notoriously NP-Hard. They comprise a set of problems of enormous practical interest to manufacturing industry due to the relevant frequency of this type of production paradigm. For this reason, many researchers on Computational Intelligence and Industrial Engineering have been conceiving algorithms for tackling different versions of assembly line balancing problems utilizing different methodologies. In this article, it was proposed a problem version referred as Mixed Model Workplace Time-dependent Assembly Line Balancing Problem with the intention of including pressing issues of real assembly lines in the optimization problem, to which four versions were conceived. Heuristic search procedures were used, namely two Swarm Intelligence algorithms from the Fish School Search family: the original version, named “vanilla”, and a special variation including a stagnation avoidance routine. Either approaches solved the newly posed problem achieving good results when compared to Particle Swarm Optimization algorithm. |
| Tasks | |
| Published | 2017-07-19 |
| URL | http://arxiv.org/abs/1707.06132v1 |
| http://arxiv.org/pdf/1707.06132v1.pdf | |
| PWC | https://paperswithcode.com/paper/solving-mixed-model-workplace-time-dependent |
| Repo | |
| Framework | |
Pixel Recursive Super Resolution
| Title | Pixel Recursive Super Resolution |
| Authors | Ryan Dahl, Mohammad Norouzi, Jonathon Shlens |
| Abstract | We present a pixel recursive super resolution model that synthesizes realistic details into images while enhancing their resolution. A low resolution image may correspond to multiple plausible high resolution images, thus modeling the super resolution process with a pixel independent conditional model often results in averaging different details–hence blurry edges. By contrast, our model is able to represent a multimodal conditional distribution by properly modeling the statistical dependencies among the high resolution image pixels, conditioned on a low resolution input. We employ a PixelCNN architecture to define a strong prior over natural images and jointly optimize this prior with a deep conditioning convolutional network. Human evaluations indicate that samples from our proposed model look more photo realistic than a strong L2 regression baseline. |
| Tasks | Super-Resolution |
| Published | 2017-02-02 |
| URL | http://arxiv.org/abs/1702.00783v2 |
| http://arxiv.org/pdf/1702.00783v2.pdf | |
| PWC | https://paperswithcode.com/paper/pixel-recursive-super-resolution |
| Repo | |
| Framework | |
Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines
| Title | Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines |
| Authors | Andreas Kölsch, Muhammad Zeshan Afzal, Markus Ebbecke, Marcus Liwicki |
| Abstract | This paper presents an approach for real-time training and testing for document image classification. In production environments, it is crucial to perform accurate and (time-)efficient training. Existing deep learning approaches for classifying documents do not meet these requirements, as they require much time for training and fine-tuning the deep architectures. Motivated from Computer Vision, we propose a two-stage approach. The first stage trains a deep network that works as feature extractor and in the second stage, Extreme Learning Machines (ELMs) are used for classification. The proposed approach outperforms all previously reported structural and deep learning based methods with a final accuracy of 83.24% on Tobacco-3482 dataset, leading to a relative error reduction of 25% when compared to a previous Convolutional Neural Network (CNN) based approach (DeepDocClassifier). More importantly, the training time of the ELM is only 1.176 seconds and the overall prediction time for 2,482 images is 3.066 seconds. As such, this novel approach makes deep learning-based document classification suitable for large-scale real-time applications. |
| Tasks | Document Classification, Document Image Classification, Image Classification |
| Published | 2017-11-03 |
| URL | http://arxiv.org/abs/1711.05862v1 |
| http://arxiv.org/pdf/1711.05862v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-document-image-classification-using |
| Repo | |
| Framework | |
CTD: Fast, Accurate, and Interpretable Method for Static and Dynamic Tensor Decompositions
| Title | CTD: Fast, Accurate, and Interpretable Method for Static and Dynamic Tensor Decompositions |
| Authors | Jungwoo Lee, Dongjin Choi, Lee Sael |
| Abstract | How can we find patterns and anomalies in a tensor, or multi-dimensional array, in an efficient and directly interpretable way? How can we do this in an online environment, where a new tensor arrives each time step? Finding patterns and anomalies in a tensor is a crucial problem with many applications, including building safety monitoring, patient health monitoring, cyber security, terrorist detection, and fake user detection in social networks. Standard PARAFAC and Tucker decomposition results are not directly interpretable. Although a few sampling-based methods have previously been proposed towards better interpretability, they need to be made faster, more memory efficient, and more accurate. In this paper, we propose CTD, a fast, accurate, and directly interpretable tensor decomposition method based on sampling. CTD-S, the static version of CTD, provably guarantees a high accuracy that is 17 ~ 83x more accurate than that of the state-of-the-art method. Also, CTD-S is made 5 ~ 86x faster, and 7 ~ 12x more memory-efficient than the state-of-the-art method by removing redundancy. CTD-D, the dynamic version of CTD, is the first interpretable dynamic tensor decomposition method ever proposed. Also, it is made 2 ~ 3x faster than already fast CTD-S by exploiting factors at previous time step and by reordering operations. With CTD, we demonstrate how the results can be effectively interpreted in the online distributed denial of service (DDoS) attack detection. |
| Tasks | |
| Published | 2017-10-09 |
| URL | http://arxiv.org/abs/1710.03608v1 |
| http://arxiv.org/pdf/1710.03608v1.pdf | |
| PWC | https://paperswithcode.com/paper/ctd-fast-accurate-and-interpretable-method |
| Repo | |
| Framework | |
Nonnegative/binary matrix factorization with a D-Wave quantum annealer
| Title | Nonnegative/binary matrix factorization with a D-Wave quantum annealer |
| Authors | Daniel O’Malley, Velimir V. Vesselinov, Boian S. Alexandrov, Ludmil B. Alexandrov |
| Abstract | D-Wave quantum annealers represent a novel computational architecture and have attracted significant interest, but have been used for few real-world computations. Machine learning has been identified as an area where quantum annealing may be useful. Here, we show that the D-Wave 2X can be effectively used as part of an unsupervised machine learning method. This method can be used to analyze large datasets. The D-Wave only limits the number of features that can be extracted from the dataset. We apply this method to learn the features from a set of facial images. |
| Tasks | |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01605v1 |
| http://arxiv.org/pdf/1704.01605v1.pdf | |
| PWC | https://paperswithcode.com/paper/nonnegativebinary-matrix-factorization-with-a |
| Repo | |
| Framework | |
Using Convolutional Neural Networks to Count Palm Trees in Satellite Images
| Title | Using Convolutional Neural Networks to Count Palm Trees in Satellite Images |
| Authors | Eu Koon Cheang, Teik Koon Cheang, Yong Haur Tay |
| Abstract | In this paper we propose a supervised learning system for counting and localizing palm trees in high-resolution, panchromatic satellite imagery (40cm/pixel to 1.5m/pixel). A convolutional neural network classifier trained on a set of palm and no-palm images is applied across a satellite image scene in a sliding window fashion. The resultant confidence map is smoothed with a uniform filter. A non-maximal suppression is applied onto the smoothed confidence map to obtain peaks. Trained with a small dataset of 500 images of size 40x40 cropped from satellite images, the system manages to achieve a tree count accuracy of over 99%. |
| Tasks | |
| Published | 2017-01-23 |
| URL | http://arxiv.org/abs/1701.06462v1 |
| http://arxiv.org/pdf/1701.06462v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-convolutional-neural-networks-to-count |
| Repo | |
| Framework | |
Logics and practices of transparency and opacity in real-world applications of public sector machine learning
| Title | Logics and practices of transparency and opacity in real-world applications of public sector machine learning |
| Authors | Michael Veale |
| Abstract | Machine learning systems are increasingly used to support public sector decision-making across a variety of sectors. Given concerns around accountability in these domains, and amidst accusations of intentional or unintentional bias, there have been increased calls for transparency of these technologies. Few, however, have considered how logics and practices concerning transparency have been understood by those involved in the machine learning systems already being piloted and deployed in public bodies today. This short paper distils insights about transparency on the ground from interviews with 27 such actors, largely public servants and relevant contractors, across 5 OECD countries. Considering transparency and opacity in relation to trust and buy-in, better decision-making, and the avoidance of gaming, it seeks to provide useful insights for those hoping to develop socio-technical approaches to transparency that might be useful to practitioners on-the-ground. An extended, archival version of this paper is available as Veale M., Van Kleek M., & Binns R. (2018). `Fairness and accountability design needs for algorithmic support in high-stakes public sector decision-making’ Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI’18), http://doi.org/10.1145/3173574.3174014. | |
| Tasks | Decision Making |
| Published | 2017-06-19 |
| URL | http://arxiv.org/abs/1706.09249v3 |
| http://arxiv.org/pdf/1706.09249v3.pdf | |
| PWC | https://paperswithcode.com/paper/logics-and-practices-of-transparency-and |
| Repo | |
| Framework | |
Surrogate Aided Unsupervised Recovery of Sparse Signals in Single Index Models for Binary Outcomes
| Title | Surrogate Aided Unsupervised Recovery of Sparse Signals in Single Index Models for Binary Outcomes |
| Authors | Abhishek Chakrabortty, Matey Neykov, Raymond Carroll, Tianxi Cai |
| Abstract | We consider the recovery of regression coefficients, denoted by $\boldsymbol{\beta}_0$, for a single index model (SIM) relating a binary outcome $Y$ to a set of possibly high dimensional covariates $\boldsymbol{X}$, based on a large but ‘unlabeled’ dataset $\mathcal{U}$, with $Y$ never observed. On $\mathcal{U}$, we fully observe $\boldsymbol{X}$ and additionally, a surrogate $S$ which, while not being strongly predictive of $Y$ throughout the entirety of its support, can forecast it with high accuracy when it assumes extreme values. Such datasets arise naturally in modern studies involving large databases such as electronic medical records (EMR) where $Y$, unlike $(\boldsymbol{X}, S)$, is difficult and/or expensive to obtain. In EMR studies, an example of $Y$ and $S$ would be the true disease phenotype and the count of the associated diagnostic codes respectively. Assuming another SIM for $S$ given $\boldsymbol{X}$, we show that under sparsity assumptions, we can recover $\boldsymbol{\beta}_0$ proportionally by simply fitting a least squares LASSO estimator to the subset of the observed data on $(\boldsymbol{X}, S)$ restricted to the extreme sets of $S$, with $Y$ imputed using the surrogacy of $S$. We obtain sharp finite sample performance bounds for our estimator, including deterministic deviation bounds and probabilistic guarantees. We demonstrate the effectiveness of our approach through multiple simulation studies, as well as by application to real data from an EMR study conducted at the Partners HealthCare Systems. |
| Tasks | |
| Published | 2017-01-18 |
| URL | http://arxiv.org/abs/1701.05230v3 |
| http://arxiv.org/pdf/1701.05230v3.pdf | |
| PWC | https://paperswithcode.com/paper/surrogate-aided-unsupervised-recovery-of |
| Repo | |
| Framework | |
