Paper Group ANR 457
A Supervised Modified Hebbian Learning Method On Feed-forward Neural Networks. Towards meta-learning for multi-target regression problems. Fully-automated patient-level malaria assessment on field-prepared thin blood film microscopy images, including Supplementary Information. Rethinking Formal Models of Partially Observable Multiagent Decision Mak …
A Supervised Modified Hebbian Learning Method On Feed-forward Neural Networks
| Title | A Supervised Modified Hebbian Learning Method On Feed-forward Neural Networks |
| Authors | Rafi Qumsieh |
| Abstract | In this paper, we present a new supervised learning algorithm that is based on the Hebbian learning algorithm in an attempt to offer a substitute for back propagation along with the gradient descent for a more biologically plausible method. The best performance for the algorithm was achieved when it was run on a feed-forward neural network with the MNIST handwritten digits data set reaching an accuracy of 70.4% on the test data set and 71.48% on the validation data set. |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/2001.01687v1 |
| https://arxiv.org/pdf/2001.01687v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-supervised-modified-hebbian-learning-method |
| Repo | |
| Framework | |
Towards meta-learning for multi-target regression problems
| Title | Towards meta-learning for multi-target regression problems |
| Authors | Gabriel Jonas Aguiar, Everton José Santana, Saulo Martiello Mastelini, Rafael Gomes Mantovani, Sylvio Barbon Jr |
| Abstract | Several multi-target regression methods were devel-oped in the last years aiming at improving predictive performanceby exploring inter-target correlation within the problem. However, none of these methods outperforms the others for all problems. This motivates the development of automatic approachesto recommend the most suitable multi-target regression method. In this paper, we propose a meta-learning system to recommend the best predictive method for a given multi-target regression problem. We performed experiments with a meta-dataset generated by a total of 648 synthetic datasets. These datasets were created to explore distinct inter-targets characteristics toward recommending the most promising method. In experiments, we evaluated four different algorithms with different biases as meta-learners. Our meta-dataset is composed of 58 meta-features, based on: statistical information, correlation characteristics, linear landmarking, from the distribution and smoothness of the data, and has four different meta-labels. Results showed that induced meta-models were able to recommend the best methodfor different base level datasets with a balanced accuracy superior to 70% using a Random Forest meta-model, which statistically outperformed the meta-learning baselines. |
| Tasks | Meta-Learning |
| Published | 2019-07-25 |
| URL | https://arxiv.org/abs/1907.11277v1 |
| https://arxiv.org/pdf/1907.11277v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-meta-learning-for-multi-target |
| Repo | |
| Framework | |
Fully-automated patient-level malaria assessment on field-prepared thin blood film microscopy images, including Supplementary Information
| Title | Fully-automated patient-level malaria assessment on field-prepared thin blood film microscopy images, including Supplementary Information |
| Authors | Charles B. Delahunt, Mayoore S. Jaiswal, Matthew P. Horning, Samantha Janko, Clay M. Thompson, Sourabh Kulhare, Liming Hu, Travis Ostbye, Grace Yun, Roman Gebrehiwot, Benjamin K. Wilson, Earl Long, Stephane Proux, Dionicia Gamboa, Peter Chiodini, Jane Carter, Mehul Dhorda, David Isaboke, Bernhards Ogutu, Wellington Oyibo, Elizabeth Villasis, Kyaw Myo Tun, Christine Bachman, David Bell, Courosh Mehanian |
| Abstract | Malaria is a life-threatening disease affecting millions. Microscopy-based assessment of thin blood films is a standard method to (i) determine malaria species and (ii) quantitate high-parasitemia infections. Full automation of malaria microscopy by machine learning (ML) is a challenging task because field-prepared slides vary widely in quality and presentation, and artifacts often heavily outnumber relatively rare parasites. In this work, we describe a complete, fully-automated framework for thin film malaria analysis that applies ML methods, including convolutional neural nets (CNNs), trained on a large and diverse dataset of field-prepared thin blood films. Quantitation and species identification results are close to sufficiently accurate for the concrete needs of drug resistance monitoring and clinical use-cases on field-prepared samples. We focus our methods and our performance metrics on the field use-case requirements. We discuss key issues and important metrics for the application of ML methods to malaria microscopy. |
| Tasks | |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1908.01901v1 |
| https://arxiv.org/pdf/1908.01901v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-automated-patient-level-malaria |
| Repo | |
| Framework | |
Rethinking Formal Models of Partially Observable Multiagent Decision Making
| Title | Rethinking Formal Models of Partially Observable Multiagent Decision Making |
| Authors | Vojtěch Kovařík, Martin Schmid, Neil Burch, Michael Bowling, Viliam Lisý |
| Abstract | Multiagent decision-making problems in partially observable environments are usually modeled as either extensive-form games (EFGs) within the game theory community or partially observable stochastic games (POSGs) within the reinforcement learning community. While most practical problems can be modeled in both formalisms, the communities using these models are mostly distinct with little sharing of ideas or advances. The last decade has seen dramatic progress in algorithms for EFGs, mainly driven by the challenge problem of poker. We have seen computational techniques achieving super-human performance, some variants of poker are essentially solved, and there are now sound local search algorithms which were previously thought impossible. While the advances have garnered attention, the fundamental advances are not yet understood outside the EFG community. This can be largely explained by the starkly different formalisms between the game theory and reinforcement learning communities and, further, by the unsuitability of the original EFG formalism to make the ideas simple and clear. This paper aims to address these hindrances, by advocating a new unifying formalism, a variant of POSGs, which we call Factored-Observation Games (FOGs). We prove that any timeable perfect-recall EFG can be efficiently modeled as a FOG as well as relating FOGs to other existing formalisms. Additionally, a FOG explicitly identifies the public and private components of observations, which is fundamental to the recent EFG breakthroughs. We conclude by presenting the two building-blocks of these breakthroughs — counterfactual regret minimization and public state decomposition — in the new formalism, illustrating our goal of a simpler path for sharing recent advances between game theory and reinforcement learning community. |
| Tasks | Decision Making |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.11110v1 |
| https://arxiv.org/pdf/1906.11110v1.pdf | |
| PWC | https://paperswithcode.com/paper/rethinking-formal-models-of-partially |
| Repo | |
| Framework | |
Robust DCD-Based Recursive Adaptive Algorithms
| Title | Robust DCD-Based Recursive Adaptive Algorithms |
| Authors | Y. Yu, L. Lu, Z. Zheng, W. Wang, Y. Zakharov, R. C. de Lamare |
| Abstract | The dichotomous coordinate descent (DCD) algorithm has been successfully used for significant reduction in the complexity of recursive least squares (RLS) algorithms. In this work, we generalize the application of the DCD algorithm to RLS adaptive filtering in impulsive noise scenarios and derive a unified update formula. By employing different robust strategies against impulsive noise, we develop novel computationally efficient DCD-based robust recursive algorithms. Furthermore, to equip the proposed algorithms with the ability to track abrupt changes in unknown systems, a simple variable forgetting factor mechanism is also developed. Simulation results for channel identification scenarios in impulsive noise demonstrate the effectiveness of the proposed algorithms. |
| Tasks | |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.06369v1 |
| https://arxiv.org/pdf/1908.06369v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-dcd-based-recursive-adaptive |
| Repo | |
| Framework | |
Batch simulations and uncertainty quantification in Gaussian process surrogate approximate Bayesian computation
| Title | Batch simulations and uncertainty quantification in Gaussian process surrogate approximate Bayesian computation |
| Authors | Marko Järvenpää, Aki Vehtari, Pekka Marttinen |
| Abstract | Surrogate models such as Gaussian processes (GP) have been proposed to accelerate approximate Bayesian computation (ABC) when the statistical model of interest is expensive-to-simulate. In one such promising framework the discrepancy between simulated and observed data is modelled with a GP which is further used to form a model-based estimator for the intractable posterior. In this article we improve this approach in several ways. We develop batch-sequential Bayesian experimental design strategies to parallellise the expensive simulations. In earlier work only sequential strategies have been used. Current surrogate-based ABC methods also do not fully account the uncertainty due to the limited budget of simulations as they output only a point estimate of the ABC posterior. We propose a numerical method to fully quantify the uncertainty in, for example, ABC posterior moments. We also provide some new analysis on the GP modelling assumptions in the resulting improved framework called Bayesian ABC and on its connection to Bayesian quadrature (BQ) and Bayesian optimisation (BO). Experiments with several toy and real-world simulation models demonstrate advantages of the proposed techniques. |
| Tasks | Bayesian Optimisation, Gaussian Processes |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06121v2 |
| https://arxiv.org/pdf/1910.06121v2.pdf | |
| PWC | https://paperswithcode.com/paper/batch-simulations-and-uncertainty |
| Repo | |
| Framework | |
Simultaneous reconstruction of the initial pressure and sound speed in photoacoustic tomography using a deep-learning approach
| Title | Simultaneous reconstruction of the initial pressure and sound speed in photoacoustic tomography using a deep-learning approach |
| Authors | Hongming Shan, Christopher Wiedeman, Ge Wang, Yang Yang |
| Abstract | Photoacoustic tomography seeks to reconstruct an acoustic initial pressure distribution from the measurement of the ultrasound waveforms. Conventional methods assume a-prior knowledge of the sound speed distribution, which practically is unknown. One way to circumvent the issue is to simultaneously reconstruct both the acoustic initial pressure and speed. In this article, we develop a novel data-driven method that integrates an advanced deep neural network through model-based iteration. The image of the initial pressure is significantly improved in our numerical simulation. |
| Tasks | |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09951v2 |
| https://arxiv.org/pdf/1907.09951v2.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-reconstruction-of-the-initial |
| Repo | |
| Framework | |
Large Scale Question Answering using Tourism Data
| Title | Large Scale Question Answering using Tourism Data |
| Authors | Danish Contractor, Krunal Shah, Aditi Partap, Mausam, Parag Singla |
| Abstract | Real world question answering can be significantly more complex than what most existing QA datasets reflect. Questions posed by users on websites, such as online travel forums, may consist of multiple sentences and not everything mentioned in a question may be relevant for finding its answer. Such questions typically have a huge candidate answer space and require complex reasoning over large knowledge corpora. We introduce the novel task of answering entity-seeking recommendation questions using a collection of reviews that describe candidate answer entities. We harvest a QA dataset that contains 48,147 paragraph-sized real user questions from travelers seeking recommendations for hotels, attractions and restaurants. Each candidate answer is associated with a collection of unstructured reviews. This dataset is challenging because commonly used neural architectures for QA are prohibitively expensive for a task of this scale. As a solution, we design a scalable cluster-select-rerank approach. It first clusters text for each entity to identify exemplar sentences describing an entity. It then uses a scalable neural information retrieval (IR) module to subselect a set of potential entities from the large candidate set. A reranker uses a deeper attention-based architecture to pick the best answers from the selected entities. This strategy performs better than a pure IR or a pure attention-based reasoning approach yielding nearly 10% relative improvement in Accuracy@3 over both approaches. |
| Tasks | Information Retrieval, Question Answering |
| Published | 2019-09-08 |
| URL | https://arxiv.org/abs/1909.03527v1 |
| https://arxiv.org/pdf/1909.03527v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-question-answering-using-tourism |
| Repo | |
| Framework | |
Transform-Invariant Convolutional Neural Networks for Image Classification and Search
| Title | Transform-Invariant Convolutional Neural Networks for Image Classification and Search |
| Authors | Xu Shen, Xinmei Tian, Anfeng He, Shaoyan Sun, Dacheng Tao |
| Abstract | Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and non-linear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transform-invariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval. The code is available at https://github.com/jasonustc/caffe-multigpu/tree/TICNN. |
| Tasks | Image Classification, Image Retrieval |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1912.01447v1 |
| https://arxiv.org/pdf/1912.01447v1.pdf | |
| PWC | https://paperswithcode.com/paper/transform-invariant-convolutional-neural |
| Repo | |
| Framework | |
Affect Enriched Word Embeddings for News Information Retrieval
| Title | Affect Enriched Word Embeddings for News Information Retrieval |
| Authors | Tommaso Teofili, Niyati Chhaya |
| Abstract | Distributed representations of words have shown to be useful to improve the effectiveness of IR systems in many sub-tasks like query expansion, retrieval and ranking. Algorithms like word2vec, GloVe and others are also key factors in many improvements in different NLP tasks. One common issue with such embedding models is that words like happy and sad appear in similar contexts and hence are wrongly clustered close in the embedding space. In this paper we leverage Aff2Vec, a set of word embeddings models which include affect information, in order to better capture the affect aspect in news text to achieve better results in information retrieval tasks, also such embeddings are less hit by the synonym/antonym issue. We evaluate their effectiveness on two IR related tasks (query expansion and ranking) over the New York Times dataset (TREC-core ‘17) comparing them against other word embeddings based models and classic ranking models. |
| Tasks | Information Retrieval, Word Embeddings |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01772v1 |
| https://arxiv.org/pdf/1909.01772v1.pdf | |
| PWC | https://paperswithcode.com/paper/affect-enriched-word-embeddings-for-news |
| Repo | |
| Framework | |
Deep Probabilistic Kernels for Sample-Efficient Learning
| Title | Deep Probabilistic Kernels for Sample-Efficient Learning |
| Authors | Ankur Mallick, Chaitanya Dwivedi, Bhavya Kailkhura, Gauri Joshi, T. Yong-Jin Han |
| Abstract | Gaussian Processes (GPs) with an appropriate kernel are known to provide accurate predictions and uncertainty estimates even with very small amounts of labeled data. However, GPs are generally unable to learn a good representation that can encode intricate structures in high dimensional data. The representation power of GPs depends heavily on kernel functions used to quantify the similarity between data points. Traditional GP kernels are not very effective at capturing similarity between high dimensional data points, while methods that use deep neural networks to learn a kernel are not sample-efficient. To overcome these drawbacks, we propose deep probabilistic kernels which use a probabilistic neural network to map high-dimensional data to a probability distribution in a low dimensional subspace, and leverage the rich work on kernels between distributions to capture the similarity between these distributions. Experiments on a variety of datasets show that building a GP using this covariance kernel solves the conflicting problems of representation learning and sample efficiency. Our model can be extended beyond GPs to other small-data paradigms such as few-shot classification where we show competitive performance with state-of-the-art models on the mini-Imagenet dataset. |
| Tasks | Gaussian Processes, Representation Learning |
| Published | 2019-10-13 |
| URL | https://arxiv.org/abs/1910.05858v1 |
| https://arxiv.org/pdf/1910.05858v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-probabilistic-kernels-for-sample |
| Repo | |
| Framework | |
Attention-based Pairwise Multi-Perspective Convolutional Neural Network for Answer Selection in Question Answering
| Title | Attention-based Pairwise Multi-Perspective Convolutional Neural Network for Answer Selection in Question Answering |
| Authors | Jamshid Mozafari, Mohammad Ali Nematbakhsh, Afsaneh Fatemi |
| Abstract | Over the past few years, question answering and information retrieval systems have become widely used. These systems attempt to find the answer of the asked questions from raw text sources. A component of these systems is Answer Selection which selects the most relevant from candidate answers. Syntactic similarities were mostly used to compute the similarity, but in recent works, deep neural networks have been used, making a significant improvement in this field. In this research, a model is proposed to select the most relevant answers to the factoid question from the candidate answers. The proposed model ranks the candidate answers in terms of semantic and syntactic similarity to the question, using convolutional neural networks. In this research, Attention mechanism and Sparse feature vector use the context-sensitive interactions between questions and answer sentence. Wide convolution increases the importance of the interrogative word. Pairwise ranking is used to learn differentiable representations to distinguish positive and negative answers. Our model indicates strong performance on the TrecQA Raw beating previous state-of-the-art systems by 1.4% in MAP and 1.1% in MRR while using the benefits of no additional syntactic parsers and external tools. The results show that using context-sensitive interactions between question and answer sentences can help to find the correct answer more accurately. |
| Tasks | Answer Selection, Information Retrieval, Question Answering |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.01059v3 |
| https://arxiv.org/pdf/1909.01059v3.pdf | |
| PWC | https://paperswithcode.com/paper/attention-based-pairwise-multi-perspective |
| Repo | |
| Framework | |
Hybrid Style Siamese Network: Incorporating style loss in complimentary apparels retrieval
| Title | Hybrid Style Siamese Network: Incorporating style loss in complimentary apparels retrieval |
| Authors | Mayukh Bhattacharyya, Sayan Nag |
| Abstract | Image Retrieval grows to be an integral part of fashion e-commerce ecosystem as it keeps expanding in multitudes. Other than the retrieval of visually similar items, the retrieval of visually compatible or complimentary items is also an important aspect of it. Normal Siamese Networks tend to work well on complimentary items retrieval. But it fails to identify low level style features which make items compatible in human eyes. These low level style features are captured to a large extent in techniques used in neural style transfer. This paper proposes a mechanism of utilising those methods in this retrieval task and capturing the low level style features through a hybrid siamese network coupled with a hybrid loss. The experimental results indicate that the proposed method outperforms traditional siamese networks in retrieval tasks for complimentary items. |
| Tasks | Image Retrieval, Style Transfer |
| Published | 2019-11-23 |
| URL | https://arxiv.org/abs/1912.05014v1 |
| https://arxiv.org/pdf/1912.05014v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-style-siamese-network-incorporating |
| Repo | |
| Framework | |
Distributional Analysis of Function Words
| Title | Distributional Analysis of Function Words |
| Authors | Daniel Hole, Sebastian Pado |
| Abstract | This paper is a first attempt at reconciling the current methods of distributional semantics with the function word emphasis of formal linguistics. We consider a multiply polysemous function word, the German reflexive pronoun “sich”, and investigate in which ways natural subclasses of this word known from the theoretical and typological literature map onto recent models from distributional semantics. |
| Tasks | |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10449v1 |
| https://arxiv.org/pdf/1907.10449v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributional-analysis-of-function-words |
| Repo | |
| Framework | |
Camera Obscurer: Generative Art for Design Inspiration
| Title | Camera Obscurer: Generative Art for Design Inspiration |
| Authors | Dilpreet Singh, Nina Rajcic, Simon Colton, Jon McCormack |
| Abstract | We investigate using generated decorative art as a source of inspiration for design tasks. Using a visual similarity search for image retrieval, the \emph{Camera Obscurer} app enables rapid searching of tens of thousands of generated abstract images of various types. The seed for a visual similarity search is a given image, and the retrieved generated images share some visual similarity with the seed. Implemented in a hand-held device, the app empowers users to use photos of their surroundings to search through the archive of generated images and other image archives. Being abstract in nature, the retrieved images supplement the seed image rather than replace it, providing different visual stimuli including shapes, colours, textures and juxtapositions, in addition to affording their own interpretations. This approach can therefore be used to provide inspiration for a design task, with the abstract images suggesting new ideas that might give direction to a graphic design project. We describe a crowdsourcing experiment with the app to estimate user confidence in retrieved images, and we describe a pilot study where Camera Obscurer provided inspiration for a design task. These experiments have enabled us to describe future improvements, and to begin to understand sources of visual inspiration for design tasks. |
| Tasks | Image Retrieval |
| Published | 2019-03-06 |
| URL | http://arxiv.org/abs/1903.02165v1 |
| http://arxiv.org/pdf/1903.02165v1.pdf | |
| PWC | https://paperswithcode.com/paper/camera-obscurer-generative-art-for-design |
| Repo | |
| Framework | |
