Paper Group ANR 479
Experiments with Different Indexing Techniques for Text Retrieval tasks on Gujarati Language using Bag of Words Approach. Fast Generating A Large Number of Gumbel-Max Variables. NestedVAE: Isolating Common Factors via Weak Supervision. AQPDCITY Dataset: Picture-Based PM2.5 Monitoring in the Urban Area of Big Cities. Incremental Fast Subclass Discri …
Experiments with Different Indexing Techniques for Text Retrieval tasks on Gujarati Language using Bag of Words Approach
| Title | Experiments with Different Indexing Techniques for Text Retrieval tasks on Gujarati Language using Bag of Words Approach |
| Authors | Dr. Jyoti Pareek, Hardik Joshi, Krunal Chauhan, Rushikesh Patel |
| Abstract | This paper presents results of various experiments carried out to improve text retrieval of gujarati text documents. Text retrieval involves searching and ranking of text documents for a given set of query terms. We have tested various retrieval models that uses bag-of-words approach. Bag-of-words approach is a traditional approach that is being used till date where the text document is represented as collection of words. Measures like frequency count, inverse document frequency etc. are used to signify and rank relevant documents for user queries. Different ranking models have been used to quantify ranking performance using the metric of mean average precision. Gujarati is a morphologically rich language, we have compared techniques like stop word removal, stemming and frequent case generation against baseline to measure the improvements in information retrieval tasks. Most of the techniques are language dependent and requires development of language specific tools. We used plain unprocessed word index as the baseline, we have seen significant improvements in comparison of MAP values after applying different indexing techniques when compared to the baseline. |
| Tasks | Information Retrieval |
| Published | 2020-02-05 |
| URL | https://arxiv.org/abs/2002.01792v1 |
| https://arxiv.org/pdf/2002.01792v1.pdf | |
| PWC | https://paperswithcode.com/paper/experiments-with-different-indexing |
| Repo | |
| Framework | |
Fast Generating A Large Number of Gumbel-Max Variables
| Title | Fast Generating A Large Number of Gumbel-Max Variables |
| Authors | Yiyan Qi, Pinghui Wang, Yuanming Zhang, Junzhou Zhao, Guangjian Tian, Xiaohong Guan |
| Abstract | The well-known Gumbel-Max Trick for sampling elements from a categorical distribution (or more generally a nonnegative vector) and its variants have been widely used in areas such as machine learning and information retrieval. To sample a random element $i$ (or a Gumbel-Max variable $i$) in proportion to its positive weight $v_i$, the Gumbel-Max Trick first computes a Gumbel random variable $g_i$ for each positive weight element $i$, and then samples the element $i$ with the largest value of $g_i+\ln v_i$. Recently, applications including similarity estimation and graph embedding require to generate $k$ independent Gumbel-Max variables from high dimensional vectors. However, it is computationally expensive for a large $k$ (e.g., hundreds or even thousands) when using the traditional Gumbel-Max Trick. To solve this problem, we propose a novel algorithm, \emph{FastGM}, that reduces the time complexity from $O(kn^+)$ to $O(k \ln k + n^+)$, where $n^+$ is the number of positive elements in the vector of interest. Instead of computing $k$ independent Gumbel random variables directly, we find that there exists a technique to generate these variables in descending order. Using this technique, our method FastGM computes variables $g_i+\ln v_i$ for all positive elements $i$ in descending order. As a result, FastGM significantly reduces the computation time because we can stop the procedure of Gumbel random variables computing for many elements especially for those with small weights. Experiments on a variety of real-world datasets show that FastGM is orders of magnitude faster than state-of-the-art methods without sacrificing accuracy and incurring additional expenses. |
| Tasks | Graph Embedding, Information Retrieval |
| Published | 2020-02-02 |
| URL | https://arxiv.org/abs/2002.00413v1 |
| https://arxiv.org/pdf/2002.00413v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-generating-a-large-number-of-gumbel-max |
| Repo | |
| Framework | |
NestedVAE: Isolating Common Factors via Weak Supervision
| Title | NestedVAE: Isolating Common Factors via Weak Supervision |
| Authors | Matthew J. Vowels, Necati Cihan Camgoz, Richard Bowden |
| Abstract | Fair and unbiased machine learning is an important and active field of research, as decision processes are increasingly driven by models that learn from data. Unfortunately, any biases present in the data may be learned by the model, thereby inappropriately transferring that bias into the decision making process. We identify the connection between the task of bias reduction and that of isolating factors common between domains whilst encouraging domain specific invariance. To isolate the common factors we combine the theory of deep latent variable models with information bottleneck theory for scenarios whereby data may be naturally paired across domains and no additional supervision is required. The result is the Nested Variational AutoEncoder (NestedVAE). Two outer VAEs with shared weights attempt to reconstruct the input and infer a latent space, whilst a nested VAE attempts to reconstruct the latent representation of one image, from the latent representation of its paired image. In so doing, the nested VAE isolates the common latent factors/causes and becomes invariant to unwanted factors that are not shared between paired images. We also propose a new metric to provide a balanced method of evaluating consistency and classifier performance across domains which we refer to as the Adjusted Parity metric. An evaluation of NestedVAE on both domain and attribute invariance, change detection, and learning common factors for the prediction of biological sex demonstrates that NestedVAE significantly outperforms alternative methods. |
| Tasks | Decision Making, Latent Variable Models |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11576v1 |
| https://arxiv.org/pdf/2002.11576v1.pdf | |
| PWC | https://paperswithcode.com/paper/nestedvae-isolating-common-factors-via-weak |
| Repo | |
| Framework | |
AQPDCITY Dataset: Picture-Based PM2.5 Monitoring in the Urban Area of Big Cities
| Title | AQPDCITY Dataset: Picture-Based PM2.5 Monitoring in the Urban Area of Big Cities |
| Authors | Yonghui Zhang, Ke Gu |
| Abstract | Since Particulate Matters (PMs) are closely related to people’s living and health, it has become one of the most important indicator of air quality monitoring around the world. But the existing sensor-based methods for PM monitoring have remarkable disadvantages, such as low-density monitoring stations and high-requirement monitoring conditions. It is highly desired to devise a method that can obtain the PM concentration at any location for the following air quality control in time. The prior works indicate that the PM concentration can be monitored by using ubiquitous photos. To further investigate such issue, we gathered 1,500 photos in big cities to establish a new AQPDCITY dataset. Experiments conducted to check nine state-of-the-art methods on this dataset show that the performance of those above methods perform poorly in the AQPDCITY dataset. |
| Tasks | |
| Published | 2020-03-22 |
| URL | https://arxiv.org/abs/2003.09784v1 |
| https://arxiv.org/pdf/2003.09784v1.pdf | |
| PWC | https://paperswithcode.com/paper/aqpdcity-dataset-picture-based-pm25 |
| Repo | |
| Framework | |
Incremental Fast Subclass Discriminant Analysis
| Title | Incremental Fast Subclass Discriminant Analysis |
| Authors | Kateryna Chumachenko, Jenni Raitoharju, Moncef Gabbouj, Alexandros Iosifidis |
| Abstract | This paper proposes an incremental solution to Fast Subclass Discriminant Analysis (fastSDA). We present an exact and an approximate linear solution, along with an approximate kernelized variant. Extensive experiments on eight image datasets with different incremental batch sizes show the superiority of the proposed approach in terms of training time and accuracy being equal or close to fastSDA solution and outperforming other methods. |
| Tasks | |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04348v1 |
| https://arxiv.org/pdf/2002.04348v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-fast-subclass-discriminant |
| Repo | |
| Framework | |
Plasticity-Enhanced Domain-Wall MTJ Neural Networks for Energy-Efficient Online Learning
| Title | Plasticity-Enhanced Domain-Wall MTJ Neural Networks for Energy-Efficient Online Learning |
| Authors | Christopher H. Bennett, T. Patrick Xiao, Can Cui, Naimul Hassan, Otitoaleke G. Akinola, Jean Anne C. Incorvia, Alvaro Velasquez, Joseph S. Friedman, Matthew J. Marinella |
| Abstract | Machine learning implements backpropagation via abundant training samples. We demonstrate a multi-stage learning system realized by a promising non-volatile memory device, the domain-wall magnetic tunnel junction (DW-MTJ). The system consists of unsupervised (clustering) as well as supervised sub-systems, and generalizes quickly (with few samples). We demonstrate interactions between physical properties of this device and optimal implementation of neuroscience-inspired plasticity learning rules, and highlight performance on a suite of tasks. Our energy analysis confirms the value of the approach, as the learning budget stays below 20 $\mu J$ even for large tasks used typically in machine learning. |
| Tasks | |
| Published | 2020-03-04 |
| URL | https://arxiv.org/abs/2003.02357v1 |
| https://arxiv.org/pdf/2003.02357v1.pdf | |
| PWC | https://paperswithcode.com/paper/plasticity-enhanced-domain-wall-mtj-neural |
| Repo | |
| Framework | |
Human Posture Recognition and Gesture Imitation with a Humanoid Robot
| Title | Human Posture Recognition and Gesture Imitation with a Humanoid Robot |
| Authors | Amir Aly |
| Abstract | This study proposes different approaches for static and dynamic gesture analysis and imitation with the social robot Nao |
| Tasks | |
| Published | 2020-02-05 |
| URL | https://arxiv.org/abs/2002.01779v3 |
| https://arxiv.org/pdf/2002.01779v3.pdf | |
| PWC | https://paperswithcode.com/paper/human-posture-recognition-and-gesture |
| Repo | |
| Framework | |
Explaining Motion Relevance for Activity Recognition in Video Deep Learning Models
| Title | Explaining Motion Relevance for Activity Recognition in Video Deep Learning Models |
| Authors | Liam Hiley, Alun Preece, Yulia Hicks, Supriyo Chakraborty, Prudhvi Gurram, Richard Tomsett |
| Abstract | A small subset of explainability techniques developed initially for image recognition models has recently been applied for interpretability of 3D Convolutional Neural Network models in activity recognition tasks. Much like the models themselves, the techniques require little or no modification to be compatible with 3D inputs. However, these explanation techniques regard spatial and temporal information jointly. Therefore, using such explanation techniques, a user cannot explicitly distinguish the role of motion in a 3D model’s decision. In fact, it has been shown that these models do not appropriately factor motion information into their decision. We propose a selective relevance method for adapting the 2D explanation techniques to provide motion-specific explanations, better aligning them with the human understanding of motion as conceptually separate from static spatial features. We demonstrate the utility of our method in conjunction with several widely-used 2D explanation methods, and show that it improves explanation selectivity for motion. Our results show that the selective relevance method can not only provide insight on the role played by motion in the model’s decision – in effect, revealing and quantifying the model’s spatial bias – but the method also simplifies the resulting explanations for human consumption. |
| Tasks | Activity Recognition |
| Published | 2020-03-31 |
| URL | https://arxiv.org/abs/2003.14285v1 |
| https://arxiv.org/pdf/2003.14285v1.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-motion-relevance-for-activity |
| Repo | |
| Framework | |
Ascertaining price formation in cryptocurrency markets with DeepLearning
| Title | Ascertaining price formation in cryptocurrency markets with DeepLearning |
| Authors | Fan Fang, Waichung Chung, Carmine Ventre, Michail Basios, Leslie Kanthan, Lingbo Li, Fan Wu |
| Abstract | The cryptocurrency market is amongst the fastest-growing of all the financial markets in the world. Unlike traditional markets, such as equities, foreign exchange and commodities, cryptocurrency market is considered to have larger volatility and illiquidity. This paper is inspired by the recent success of using deep learning for stock market prediction. In this work, we analyze and present the characteristics of the cryptocurrency market in a high-frequency setting. In particular, we applied a deep learning approach to predict the direction of the mid-price changes on the upcoming tick. We monitored live tick-level data from $8$ cryptocurrency pairs and applied both statistical and machine learning techniques to provide a live prediction. We reveal that promising results are possible for cryptocurrencies, and in particular, we achieve a consistent $78%$ accuracy on the prediction of the mid-price movement on live exchange rate of Bitcoins vs US dollars. |
| Tasks | Stock Market Prediction |
| Published | 2020-02-09 |
| URL | https://arxiv.org/abs/2003.00803v1 |
| https://arxiv.org/pdf/2003.00803v1.pdf | |
| PWC | https://paperswithcode.com/paper/ascertaining-price-formation-in |
| Repo | |
| Framework | |
Type-2 Fuzzy Set based Hesitant Fuzzy Linguistic Term Sets for Linguistic Decision Making
| Title | Type-2 Fuzzy Set based Hesitant Fuzzy Linguistic Term Sets for Linguistic Decision Making |
| Authors | Taniya Seth, Pranab K. Muhuri |
| Abstract | Approaches based on computing with words find good applicability in decision making systems. Predominantly finding their basis in type-1 fuzzy sets, computing with words approaches employ type-1 fuzzy sets as semantics of the linguistic terms. However, type-2 fuzzy sets have been proven to be scientifically more appropriate to represent linguistic information in practical systems. They take into account both the intra-uncertainty as well as the inter-uncertainty in cases where the linguistic information comes from a group of experts. Hence in this paper, we propose to introduce linguistic terms whose semantics are denoted by interval type-2 fuzzy sets within the hesitant fuzzy linguistic term set framework, resulting in type-2 fuzzy sets based hesitant fuzzy linguistic term sets. We also introduce a novel method of computing type-2 fuzzy envelopes out of multiple interval type-2 fuzzy sets with trapezoidal membership functions. Furthermore, the proposed framework with interval type-2 fuzzy sets is applied on a supplier performance evaluation scenario. Since humans are predominantly involved in the entire process of supply chain, their feedback is crucial while deciding many factors. Towards the end of the paper, we compare our presented model with various existing models and demonstrate the advantages of the former. |
| Tasks | Decision Making |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11714v1 |
| https://arxiv.org/pdf/2002.11714v1.pdf | |
| PWC | https://paperswithcode.com/paper/type-2-fuzzy-set-based-hesitant-fuzzy |
| Repo | |
| Framework | |
The PHOTON Wizard – Towards Educational Machine Learning Code Generators
| Title | The PHOTON Wizard – Towards Educational Machine Learning Code Generators |
| Authors | Ramona Leenings, Nils Ralf Winter, Kelvin Sarink, Jan Ernsting, Xiaoyi Jiang, Udo Dannlowski, Tim Hahn |
| Abstract | Despite the tremendous efforts to democratize machine learning, especially in applied-science, the application is still often hampered by the lack of coding skills. As we consider programmatic understanding key to building effective and efficient machine learning solutions, we argue for a novel educational approach that builds upon the accessibility and acceptance of graphical user interfaces to convey programming skills to an applied-science target group. We outline a proof-of-concept, open-source web application, the PHOTON Wizard, which dynamically translates GUI interactions into valid source code for the Python machine learning framework PHOTON. Thereby, users possessing theoretical machine learning knowledge gain key insights into the model development workflow as well as an intuitive understanding of custom implementations. Specifically, the PHOTON Wizard integrates the concept of Educational Machine Learning Code Generators to teach users how to write code for designing, training, optimizing and evaluating custom machine learning pipelines. |
| Tasks | |
| Published | 2020-02-13 |
| URL | https://arxiv.org/abs/2002.05432v1 |
| https://arxiv.org/pdf/2002.05432v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-photon-wizard-towards-educational-machine |
| Repo | |
| Framework | |
Quantum Interference for Counting Clusters
| Title | Quantum Interference for Counting Clusters |
| Authors | Rohit R Muthyala, Davi Geiger, Zvi M. Kedem |
| Abstract | Counting the number of clusters, when these clusters overlap significantly is a challenging problem in machine learning. We argue that a purely mathematical quantum theory, formulated using the path integral technique, when applied to non-physics modeling leads to non-physics quantum theories that are statistical in nature. We show that a quantum theory can be a more robust statistical theory to separate data to count overlapping clusters. The theory is also confirmed from data simulations.This works identify how quantum theory can be effective in counting clusters and hope to inspire the field to further apply such techniques. |
| Tasks | |
| Published | 2020-01-03 |
| URL | https://arxiv.org/abs/2001.04251v1 |
| https://arxiv.org/pdf/2001.04251v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-interference-for-counting-clusters |
| Repo | |
| Framework | |
Regret Bound of Adaptive Control in Linear Quadratic Gaussian (LQG) Systems
| Title | Regret Bound of Adaptive Control in Linear Quadratic Gaussian (LQG) Systems |
| Authors | Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar |
| Abstract | We study the problem of adaptive control in partially observable linear quadratic Gaussian control systems, where the model dynamics are unknown a priori. We propose LqgOpt, a novel reinforcement learning algorithm based on the principle of optimism in the face of uncertainty, to effectively minimize the overall control cost. We employ the predictor state evolution representation of the system dynamics and propose a new approach for closed-loop system identification, estimation, and confidence bound construction. LqgOpt efficiently explores the system dynamics, estimates the model parameters up to their confidence interval, and deploys the controller of the most optimistic model for further exploration and exploitation. We provide stability guarantees for LqgOpt, and prove the regret upper bound of $\tilde{\mathcal{O}}(\sqrt{T})$ for adaptive control of linear quadratic Gaussian (LQG) systems, where $T$ is the time horizon of the problem. |
| Tasks | |
| Published | 2020-03-12 |
| URL | https://arxiv.org/abs/2003.05999v1 |
| https://arxiv.org/pdf/2003.05999v1.pdf | |
| PWC | https://paperswithcode.com/paper/regret-bound-of-adaptive-control-in-linear |
| Repo | |
| Framework | |
Perspectives and Ethics of the Autonomous Artificial Thinking Systems
| Title | Perspectives and Ethics of the Autonomous Artificial Thinking Systems |
| Authors | Joël Colloc |
| Abstract | The feasibility of autonomous artificial thinking systems needs to compare the way the human beings acquire their information and develops the thought with the current capacities of the autonomous information systems. Our model uses four hierarchies: the hierarchy of information systems, the cognitive hierarchy, the linguistic hierarchy and the digital informative hierarchy that combines artificial intelligence, the power of computers models, methods and tools to develop autonomous information systems. The question of the capability of autonomous system to provide a form of artificial thought arises with the ethical consequences on the social life and the perspective of transhumanism. |
| Tasks | |
| Published | 2020-01-13 |
| URL | https://arxiv.org/abs/2001.04270v1 |
| https://arxiv.org/pdf/2001.04270v1.pdf | |
| PWC | https://paperswithcode.com/paper/perspectives-and-ethics-of-the-autonomous |
| Repo | |
| Framework | |
Information-Theoretic Free Energy as Emotion Potential: Emotional Valence as a Function of Complexity and Novelty
| Title | Information-Theoretic Free Energy as Emotion Potential: Emotional Valence as a Function of Complexity and Novelty |
| Authors | Hideyoshi Yanagisawa |
| Abstract | This study extends the mathematical model of emotion dimensions that we previously proposed (Yanagisawa, et al. 2019, Front Comput Neurosci) to consider perceived complexity as well as novelty, as a source of arousal potential. Berlyne’s hedonic function of arousal potential (or the inverse U-shaped curve, the so-called Wundt curve) is assumed. We modeled the arousal potential as information contents to be processed in the brain after sensory stimuli are perceived (or recognized), which we termed sensory surprisal. We mathematically demonstrated that sensory surprisal represents free energy, and it is equivalent to a summation of information gain (or information from novelty) and perceived complexity (or information from complexity), which are the collative variables forming the arousal potential. We demonstrated empirical evidence with visual stimuli (profile shapes of butterfly) supporting the hypothesis that the summation of perceived novelty and complexity shapes the inverse U-shaped beauty function. We discussed the potential of free energy as a mathematical principle explaining emotion initiators. |
| Tasks | |
| Published | 2020-03-23 |
| URL | https://arxiv.org/abs/2003.10073v1 |
| https://arxiv.org/pdf/2003.10073v1.pdf | |
| PWC | https://paperswithcode.com/paper/information-theoretic-free-energy-as-emotion |
| Repo | |
| Framework | |
