Paper Group ANR 1164
InstructableCrowd: Creating IF-THEN Rules for Smartphones via Conversations with the Crowd. Skin Lesion Analyser: An Efficient Seven-Way Multi-Class Skin Cancer Classification Using MobileNet. Partial differential equation regularization for supervised machine learning. Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k- …
InstructableCrowd: Creating IF-THEN Rules for Smartphones via Conversations with the Crowd
| Title | InstructableCrowd: Creating IF-THEN Rules for Smartphones via Conversations with the Crowd |
| Authors | Ting-Hao ‘Kenneth’ Huang, Amos Azaria, Oscar J. Romero, Jeffrey P. Bigham |
| Abstract | Natural language interfaces have become a common part of modern digital life. Chatbots utilize text-based conversations to communicate with users; personal assistants on smartphones such as Google Assistant take direct speech commands from their users; and speech-controlled devices such as Amazon Echo use voice as their only input mode. In this paper, we introduce InstructableCrowd, a crowd-powered system that allows users to program their devices via conversation. The user verbally expresses a problem to the system, in which a group of crowd workers collectively respond and program relevant multi-part IF-THEN rules to help the user. The IF-THEN rules generated by InstructableCrowd connect relevant sensor combinations (e.g., location, weather, device acceleration, etc.) to useful effectors (e.g., text messages, device alarms, etc.). Our study showed that non-programmers can use the conversational interface of InstructableCrowd to create IF-THEN rules that have similar quality compared with the rules created manually. InstructableCrowd generally illustrates how users may converse with their devices, not only to trigger simple voice commands, but also to personalize their increasingly powerful and complicated devices. |
| Tasks | |
| Published | 2019-09-12 |
| URL | https://arxiv.org/abs/1909.05725v1 |
| https://arxiv.org/pdf/1909.05725v1.pdf | |
| PWC | https://paperswithcode.com/paper/instructablecrowd-creating-if-then-rules-for |
| Repo | |
| Framework | |
Skin Lesion Analyser: An Efficient Seven-Way Multi-Class Skin Cancer Classification Using MobileNet
| Title | Skin Lesion Analyser: An Efficient Seven-Way Multi-Class Skin Cancer Classification Using MobileNet |
| Authors | Saket S. Chaturvedi, Kajol Gupta, Prakash. S. Prasad |
| Abstract | Skin cancer, a major form of cancer, is a critical public health problem with 123,000 newly diagnosed melanoma cases and between 2 and 3 million non-melanoma cases worldwide each year. The leading cause of skin cancer is high exposure of skin cells to UV radiation, which can damage the DNA inside skin cells leading to uncontrolled growth of skin cells. Skin cancer is primarily diagnosed visually employing clinical screening, a biopsy, dermoscopic analysis, and histopathological examination. It has been demonstrated that the dermoscopic analysis in the hands of inexperienced dermatologists may cause a reduction in diagnostic accuracy. Early detection and screening of skin cancer have the potential to reduce mortality and morbidity. Previous studies have shown Deep Learning ability to perform better than human experts in several visual recognition tasks. In this paper, we propose an efficient seven-way automated multi-class skin cancer classification system having performance comparable with expert dermatologists. We used a pretrained MobileNet model to train over HAM10000 dataset using transfer learning. The model classifies skin lesion image with a categorical accuracy of 83.1 percent, top2 accuracy of 91.36 percent and top3 accuracy of 95.34 percent. The weighted average of precision, recall, and f1-score were found to be 0.89, 0.83, and 0.83 respectively. The model has been deployed as a web application for public use at (https://saketchaturvedi.github.io). This fast, expansible method holds the potential for substantial clinical impact, including broadening the scope of primary care practice and augmenting clinical decision-making for dermatology specialists. |
| Tasks | Decision Making, Skin Cancer Classification, Transfer Learning |
| Published | 2019-07-07 |
| URL | https://arxiv.org/abs/1907.03220v2 |
| https://arxiv.org/pdf/1907.03220v2.pdf | |
| PWC | https://paperswithcode.com/paper/skin-lesion-analyser-an-efficient-seven-way |
| Repo | |
| Framework | |
Partial differential equation regularization for supervised machine learning
| Title | Partial differential equation regularization for supervised machine learning |
| Authors | Adam M Oberman |
| Abstract | This article is an overview of supervised machine learning problems for regression and classification. Topics include: kernel methods, training by stochastic gradient descent, deep learning architecture, losses for classification, statistical learning theory, and dimension independent generalization bounds. Implicit regularization in deep learning examples are presented, including data augmentation, adversarial training, and additive noise. These methods are reframed as explicit gradient regularization. |
| Tasks | Data Augmentation |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01612v1 |
| https://arxiv.org/pdf/1910.01612v1.pdf | |
| PWC | https://paperswithcode.com/paper/partial-differential-equation-regularization |
| Repo | |
| Framework | |
Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means
| Title | Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means |
| Authors | Andrea Agostinelli, Kai Arulkumaran, Marta Sarrico, Pierre Richemond, Anil Anthony Bharath |
| Abstract | Recently, neuro-inspired episodic control (EC) methods have been developed to overcome the data-inefficiency of standard deep reinforcement learning approaches. Using non-/semi-parametric models to estimate the value function, they learn rapidly, retrieving cached values from similar past states. In realistic scenarios, with limited resources and noisy data, maintaining meaningful representations in memory is essential to speed up the learning and avoid catastrophic forgetting. Unfortunately, EC methods have a large space and time complexity. We investigate different solutions to these problems based on prioritising and ranking stored states, as well as online clustering techniques. We also propose a new dynamic online k-means algorithm that is both computationally-efficient and yields significantly better performance at smaller memory sizes; we validate this approach on classic reinforcement learning environments and Atari games. |
| Tasks | Atari Games |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09560v1 |
| https://arxiv.org/pdf/1911.09560v1.pdf | |
| PWC | https://paperswithcode.com/paper/memory-efficient-episodic-control |
| Repo | |
| Framework | |
Modelling Sequential Music Track Skips using a Multi-RNN Approach
| Title | Modelling Sequential Music Track Skips using a Multi-RNN Approach |
| Authors | Christian Hansen, Casper Hansen, Stephen Alstrup, Jakob Grue Simonsen, Christina Lioma |
| Abstract | Modelling sequential music skips provides streaming companies the ability to better understand the needs of the user base, resulting in a better user experience by reducing the need to manually skip certain music tracks. This paper describes the solution of the University of Copenhagen DIKU-IR team in the ‘Spotify Sequential Skip Prediction Challenge’, where the task was to predict the skip behaviour of the second half in a music listening session conditioned on the first half. We model this task using a Multi-RNN approach consisting of two distinct stacked recurrent neural networks, where one network focuses on encoding the first half of the session and the other network focuses on utilizing the encoding to make sequential skip predictions. The encoder network is initialized by a learned session-wide music encoding, and both of them utilize a learned track embedding. Our final model consists of a majority voted ensemble of individually trained models, and ranked 2nd out of 45 participating teams in the competition with a mean average accuracy of 0.641 and an accuracy on the first skip prediction of 0.807. Our code is released at https://github.com/Varyn/WSDM-challenge-2019-spotify. |
| Tasks | |
| Published | 2019-03-20 |
| URL | http://arxiv.org/abs/1903.08408v1 |
| http://arxiv.org/pdf/1903.08408v1.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-sequential-music-track-skips-using |
| Repo | |
| Framework | |
Efficient decorrelation of features using Gramian in Reinforcement Learning
| Title | Efficient decorrelation of features using Gramian in Reinforcement Learning |
| Authors | Borislav Mavrin, Daniel Graves, Alan Chan |
| Abstract | Learning good representations is a long standing problem in reinforcement learning (RL). One of the conventional ways to achieve this goal in the supervised setting is through regularization of the parameters. Extending some of these ideas to the RL setting has not yielded similar improvements in learning. In this paper, we develop an online regularization framework for decorrelating features in RL and demonstrate its utility in several test environments. We prove that the proposed algorithm converges in the linear function approximation setting and does not change the main objective of maximizing cumulative reward. We demonstrate how to scale the approach to deep RL using the Gramian of the features achieving linear computational complexity in the number of features and squared complexity in size of the batch. We conduct an extensive empirical study of the new approach on Atari 2600 games and show a significant improvement in sample efficiency in 40 out of 49 games. |
| Tasks | Atari Games |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08610v1 |
| https://arxiv.org/pdf/1911.08610v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-decorrelation-of-features-using |
| Repo | |
| Framework | |
Variational Auto-encoder Based Bayesian Poisson Tensor Factorization for Sparse and Imbalanced Count Data
| Title | Variational Auto-encoder Based Bayesian Poisson Tensor Factorization for Sparse and Imbalanced Count Data |
| Authors | Yuan Jin, Lan Du, Longxiang Gao, Yong Xiang, Yunfeng Li, Ruohua Xu |
| Abstract | Non-negative tensor factorization models enable predictive analysis on count data. Among them, Bayesian Poisson-Gamma models are able to derive full posterior distributions of latent factors and are less sensitive to sparse count data. However, current inference methods for these Bayesian models adopt restricted update rules for the posterior parameters. They also fail to share the update information to better cope with the data sparsity. Moreover, these models are not endowed with a component that handles the imbalance in count data values. In this paper, we propose a novel variational auto-encoder framework called VAE-BPTF which addresses the above issues. It uses multi-layer perceptron networks to encode and share complex update information. The encoded information is then reweighted per data instance to penalize common data values before aggregated to compute the posterior parameters for the latent factors. Under synthetic data evaluation, VAE-BPTF tended to recover the right number of latent factors and posterior parameter values. It also outperformed current models in both reconstruction errors and latent factor (semantic) coherence across five real-world datasets. Furthermore, the latent factors inferred by VAE-BPTF are perceived to be meaningful and coherent under a qualitative analysis. |
| Tasks | |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.05570v1 |
| https://arxiv.org/pdf/1910.05570v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-auto-encoder-based-bayesian |
| Repo | |
| Framework | |
ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations
| Title | ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations |
| Authors | Daniel Seita, David Chan, Roshan Rao, Chen Tang, Mandi Zhao, John Canny |
| Abstract | Learning from demonstrations is a popular tool for accelerating and reducing the exploration requirements of reinforcement learning. When providing expert demonstrations to human students, we know that the demonstrations must fall within a particular range of difficulties called the “Zone of Proximal Development (ZPD)". If they are too easy the student learns nothing, but if they are too difficult the student is unable to follow along. This raises the question: Given a set of potential demonstrators, which among them is best suited for teaching any particular learner? Prior work, such as the popular Deep Q-learning from Demonstrations (DQfD) algorithm has generally focused on single demonstrators. In this work we consider the problem of choosing among multiple demonstrators of varying skill levels. Our results align with intuition from human learners: it is not always the best policy to draw demonstrations from the best performing demonstrator (in terms of reward). We show that careful selection of teaching strategies can result in sample efficiency gains in the learner’s environment across nine Atari games |
| Tasks | Atari Games, Q-Learning |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1910.12154v1 |
| https://arxiv.org/pdf/1910.12154v1.pdf | |
| PWC | https://paperswithcode.com/paper/zpd-teaching-strategies-for-deep |
| Repo | |
| Framework | |
Interpretability Study on Deep Learning for Jet Physics at the Large Hadron Collider
| Title | Interpretability Study on Deep Learning for Jet Physics at the Large Hadron Collider |
| Authors | Taoli Cheng |
| Abstract | Using deep neural networks for identifying physics objects at the Large Hadron Collider (LHC) has become a powerful alternative approach in recent years. After successful training of deep neural networks, examining the trained networks not only helps us understand the behaviour of neural networks, but also helps improve the performance of deep learning models through proper interpretation. We take jet tagging problem at the LHC as an example, using recursive neural networks as a starting point, aim at a thorough understanding of the behaviour of the physics-oriented DNNs and the information encoded in the embedding space. We make a comparative study on a series of different jet tagging tasks dominated by different underlying physics. Interesting observations on the latent space are obtained. |
| Tasks | |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.01872v1 |
| https://arxiv.org/pdf/1911.01872v1.pdf | |
| PWC | https://paperswithcode.com/paper/interpretability-study-on-deep-learning-for |
| Repo | |
| Framework | |
Reinforcement Learning with Structured Hierarchical Grammar Representations of Actions
| Title | Reinforcement Learning with Structured Hierarchical Grammar Representations of Actions |
| Authors | Petros Christodoulou, Robert Tjarko Lange, Ali Shafti, A. Aldo Faisal |
| Abstract | From a young age humans learn to use grammatical principles to hierarchically combine words into sentences. Action grammars is the parallel idea, that there is an underlying set of rules (a “grammar”) that govern how we hierarchically combine actions to form new, more complex actions. We introduce the Action Grammar Reinforcement Learning (AG-RL) framework which leverages the concept of action grammars to consistently improve the sample efficiency of Reinforcement Learning agents. AG-RL works by using a grammar inference algorithm to infer the “action grammar” of an agent midway through training. The agent’s action space is then augmented with macro-actions identified by the grammar. We apply this framework to Double Deep Q-Learning (AG-DDQN) and a discrete action version of Soft Actor-Critic (AG-SAC) and find that it improves performance in 8 out of 8 tested Atari games (median +31%, max +668%) and 19 out of 20 tested Atari games (median +96%, maximum +3,756%) respectively without substantive hyperparameter tuning. We also show that AG-SAC beats the model-free state-of-the-art for sample efficiency in 17 out of the 20 tested Atari games (median +62%, maximum +13,140%), again without substantive hyperparameter tuning. |
| Tasks | Atari Games, Q-Learning |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02876v2 |
| https://arxiv.org/pdf/1910.02876v2.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-with-structured-1 |
| Repo | |
| Framework | |
The utility of a convolutional neural network for generating a myelin volume index map from rapid simultaneous relaxometry imaging
| Title | The utility of a convolutional neural network for generating a myelin volume index map from rapid simultaneous relaxometry imaging |
| Authors | Yasuhiko Tachibana, Akifumi Hagiwara, Masaaki Hori, Jeff Kershaw, Misaki Nakazawa, Tokuhiko Omatsu, Riwa Kishimoto, Kazumasa Yokoyama, Nobutaka Hattori, Shigeki Aoki, Tatsuya Higashi, Takayuki Obata |
| Abstract | Background and Purpose: A current algorithm to obtain a synthetic myelin volume fraction map (SyMVF) from rapid simultaneous relaxometry imaging (RSRI) has a potential problem, that it does not incorporate information from surrounding pixels. The purpose of this study was to develop a method that utilizes a convolutional neural network (CNN) to overcome this problem. Methods: RSRI and magnetization transfer images from 20 healthy volunteers were included. A CNN was trained to reconstruct RSRI-related metric maps into a myelin volume-related index (generated myelin volume index: GenMVI) map using the myelin volume index map calculated from magnetization transfer images (MTMVI) as reference. The SyMVF and GenMVI maps were statistically compared by testing how well they correlated with the MTMVI map. The correlations were evaluated based on: (i) averaged values obtained from 164 atlas-based ROIs, and (ii) pixel-based comparison for ROIs defined in four different tissue types (cortical and subcortical gray matter, white matter, and whole brain). Results: For atlas-based ROIs, the overall correlation with the MTMVI map was higher for the GenMVI map than for the SyMVF map. In the pixel-based comparison, correlation with the MTMVI map was stronger for the GenMVI map than for the SyMVF map, and the difference in the distribution for the volunteers was significant (Wilcoxon sign-rank test, P<.001) in all tissue types. Conclusion: The proposed method is useful, as it can incorporate more specific information about local tissue properties than the existing method. |
| Tasks | |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1904.10960v1 |
| http://arxiv.org/pdf/1904.10960v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-utility-of-a-convolutional-neural-network |
| Repo | |
| Framework | |
Universal and non-universal text statistics: Clustering coefficient for language identification
| Title | Universal and non-universal text statistics: Clustering coefficient for language identification |
| Authors | Diego Espitia, Hernán Larralde |
| Abstract | In this work we analyze statistical properties of 91 relatively small texts in 7 different languages (Spanish, English, French, German, Turkish, Russian, Icelandic) as well as texts with randomly inserted spaces. Despite the size (around 11260 different words), the well known universal statistical laws – namely Zipf and Herdan-Heap’s laws – are confirmed, and are in close agreement with results obtained elsewhere. We also construct a word co-occurrence network of each text. While the degree distribution is again universal, we note that the distribution of Clustering Coefficients, which depend strongly on the local structure of networks, can be used to differentiate between languages, as well as to distinguish natural languages from random texts. |
| Tasks | Language Identification |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.08915v2 |
| https://arxiv.org/pdf/1911.08915v2.pdf | |
| PWC | https://paperswithcode.com/paper/universal-and-non-universal-text-statistics |
| Repo | |
| Framework | |
The Comparison of Methods for Individual Treatment Effect Detection
| Title | The Comparison of Methods for Individual Treatment Effect Detection |
| Authors | Aleksey Buzmakov, Daria Semenova, Maria Temirkaeva |
| Abstract | Today, treatment effect estimation at the individual level is a vital problem in many areas of science and business. For example, in marketing, estimates of the treatment effect are used to select the most efficient promo-mechanics; in medicine, individual treatment effects are used to determine the optimal dose of medication for each patient and so on. At the same time, the question on choosing the best method, i.e., the method that ensures the smallest predictive error (for instance, RMSE) or the highest total (average) value of the effect, remains open. Accordingly, in this paper we compare the effectiveness of machine learning methods for estimation of individual treatment effects. The comparison is performed on the Criteo Uplift Modeling Dataset. In this paper we show that the combination of the Logistic Regression method and the Difference Score method as well as Uplift Random Forest method provide the best correctness of Individual Treatment Effect prediction on the top 30% observations of the test dataset. |
| Tasks | |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01443v1 |
| https://arxiv.org/pdf/1912.01443v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-comparison-of-methods-for-individual |
| Repo | |
| Framework | |
Simpson’s Paradox and the implications for medical trials
| Title | Simpson’s Paradox and the implications for medical trials |
| Authors | Norman Fenton, Martin Neil, Anthony Constantinou |
| Abstract | This paper describes Simpson’s paradox, and explains its serious implications for randomised control trials. In particular, we show that for any number of variables we can simulate the result of a controlled trial which uniformly points to one conclusion (such as ‘drug is effective’) for every possible combination of the variable states, but when a previously unobserved confounding variable is included every possible combination of the variables state points to the opposite conclusion (‘drug is not effective’). In other words no matter how many variables are considered, and no matter how ‘conclusive’ the result, one cannot conclude the result is truly ‘valid’ since there is theoretically an unobserved confounding variable that could completely reverse the result. |
| Tasks | |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01422v1 |
| https://arxiv.org/pdf/1912.01422v1.pdf | |
| PWC | https://paperswithcode.com/paper/simpsons-paradox-and-the-implications-for |
| Repo | |
| Framework | |
Comparative Study of Differentially Private Synthetic Data Algorithms and Evaluation Standards
| Title | Comparative Study of Differentially Private Synthetic Data Algorithms and Evaluation Standards |
| Authors | Claire McKay Bowen, Joshua Snoke |
| Abstract | Differentially private synthetic data generation is becoming a popular solution that releases analytically useful data while preserving the privacy of individuals in the data. In order to utilize these algorithms for public policy decisions, policymakers need an accurate understanding of these algorithms’ comparative performance. Correspondingly, data practitioners also require standard metrics for evaluating the analytic qualities of the synthetic data. In this paper, we present an in-depth evaluation of several differentially private synthetic data algorithms using the actual differentially private synthetic data sets created by contestants in the recent National Institute of Standards and Technology’s (NIST) “Differentially Private Synthetic Data Challenge.” We offer both theoretical and practical analyses of these algorithms. We frame the NIST data challenge methods within the broader differentially private synthetic data literature. In addition, we implement two of our own utility metric algorithms on the differentially private synthetic data and compare these metrics’ results to the NIST data challenge outcome. Our comparative assessment of the differentially private data synthesis methods and the quality metrics shows the relative usefulness, general strengths and weaknesses, preferred choices of algorithms and metrics. Finally we give implications of our evaluation for policymakers seeking to implement differentially private synthetic data algorithms on future data products. |
| Tasks | Synthetic Data Generation |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12704v1 |
| https://arxiv.org/pdf/1911.12704v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparative-study-of-differentially-private |
| Repo | |
| Framework | |
