Paper Group ANR 359
Machine Learning Suites for Online Toxicity Detection. Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras. A Cost-Effective Framework for Preference Elicitation and Aggregation. Effective Parallel Corpus Mining using Bilingual Sentence Embeddings. Adversarial Sampling and Training for Semi-Supervised Information Retrie …
Machine Learning Suites for Online Toxicity Detection
| Title | Machine Learning Suites for Online Toxicity Detection |
| Authors | David Noever |
| Abstract | To identify and classify toxic online commentary, the modern tools of data science transform raw text into key features from which either thresholding or learning algorithms can make predictions for monitoring offensive conversations. We systematically evaluate 62 classifiers representing 19 major algorithmic families against features extracted from the Jigsaw dataset of Wikipedia comments. We compare the classifiers based on statistically significant differences in accuracy and relative execution time. Among these classifiers for identifying toxic comments, tree-based algorithms provide the most transparently explainable rules and rank-order the predictive contribution of each feature. Among 28 features of syntax, sentiment, emotion and outlier word dictionaries, a simple bad word list proves most predictive of offensive commentary. |
| Tasks | |
| Published | 2018-10-03 |
| URL | http://arxiv.org/abs/1810.01869v1 |
| http://arxiv.org/pdf/1810.01869v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-suites-for-online-toxicity |
| Repo | |
| Framework | |
Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras
| Title | Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras |
| Authors | Marco Cannici, Marco Ciccone, Andrea Romanoni, Matteo Matteucci |
| Abstract | Event-based cameras, also known as neuromorphic cameras, are bioinspired sensors able to perceive changes in the scene at high frequency with low power consumption. Becoming available only very recently, a limited amount of work addresses object detection on these devices. In this paper we propose two neural networks architectures for object detection: YOLE, which integrates the events into surfaces and uses a frame-based model to process them, and fcYOLE, an asynchronous event-based fully convolutional network which uses a novel and general formalization of the convolutional and max pooling layers to exploit the sparsity of camera events. We evaluate the algorithm with different extensions of publicly available datasets and on a novel synthetic dataset. |
| Tasks | Object Detection |
| Published | 2018-05-21 |
| URL | https://arxiv.org/abs/1805.07931v3 |
| https://arxiv.org/pdf/1805.07931v3.pdf | |
| PWC | https://paperswithcode.com/paper/asynchronous-convolutional-networks-for |
| Repo | |
| Framework | |
A Cost-Effective Framework for Preference Elicitation and Aggregation
| Title | A Cost-Effective Framework for Preference Elicitation and Aggregation |
| Authors | Zhibing Zhao, Haoming Li, Junming Wang, Jeffrey Kephart, Nicholas Mattei, Hui Su, Lirong Xia |
| Abstract | We propose a cost-effective framework for preference elicitation and aggregation under the Plackett-Luce model with features. Given a budget, our framework iteratively computes the most cost-effective elicitation questions in order to help the agents make a better group decision. We illustrate the viability of the framework with experiments on Amazon Mechanical Turk, which we use to estimate the cost of answering different types of elicitation questions. We compare the prediction accuracy of our framework when adopting various information criteria that evaluate the expected information gain from a question. Our experiments show carefully designed information criteria are much more efficient, i.e., they arrive at the correct answer using fewer queries, than randomly asking questions given the budget constraint. |
| Tasks | |
| Published | 2018-05-14 |
| URL | http://arxiv.org/abs/1805.05287v2 |
| http://arxiv.org/pdf/1805.05287v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-cost-effective-framework-for-preference |
| Repo | |
| Framework | |
Effective Parallel Corpus Mining using Bilingual Sentence Embeddings
| Title | Effective Parallel Corpus Mining using Bilingual Sentence Embeddings |
| Authors | Mandy Guo, Qinlan Shen, Yinfei Yang, Heming Ge, Daniel Cer, Gustavo Hernandez Abrego, Keith Stevens, Noah Constant, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil |
| Abstract | This paper presents an effective approach for parallel corpus mining using bilingual sentence embeddings. Our embedding models are trained to produce similar representations exclusively for bilingual sentence pairs that are translations of each other. This is achieved using a novel training method that introduces hard negatives consisting of sentences that are not translations but that have some degree of semantic similarity. The quality of the resulting embeddings are evaluated on parallel corpus reconstruction and by assessing machine translation systems trained on gold vs. mined sentence pairs. We find that the sentence embeddings can be used to reconstruct the United Nations Parallel Corpus at the sentence level with a precision of 48.9% for en-fr and 54.9% for en-es. When adapted to document level matching, we achieve a parallel document matching accuracy that is comparable to the significantly more computationally intensive approach of [Jakob 2010]. Using reconstructed parallel data, we are able to train NMT models that perform nearly as well as models trained on the original data (within 1-2 BLEU). |
| Tasks | Machine Translation, Parallel Corpus Mining, Semantic Similarity, Semantic Textual Similarity, Sentence Embeddings |
| Published | 2018-07-31 |
| URL | http://arxiv.org/abs/1807.11906v2 |
| http://arxiv.org/pdf/1807.11906v2.pdf | |
| PWC | https://paperswithcode.com/paper/effective-parallel-corpus-mining-using |
| Repo | |
| Framework | |
Adversarial Sampling and Training for Semi-Supervised Information Retrieval
| Title | Adversarial Sampling and Training for Semi-Supervised Information Retrieval |
| Authors | Dae Hoon Park, Yi Chang |
| Abstract | Ad-hoc retrieval models with implicit feedback often have problems, e.g., the imbalanced classes in the data set. Too few clicked documents may hurt generalization ability of the models, whereas too many non-clicked documents may harm effectiveness of the models and efficiency of training. In addition, recent neural network-based models are vulnerable to adversarial examples due to the linear nature in them. To solve the problems at the same time, we propose an adversarial sampling and training framework to learn ad-hoc retrieval models with implicit feedback. Our key idea is (i) to augment clicked examples by adversarial training for better generalization and (ii) to obtain very informational non-clicked examples by adversarial sampling and training. Experiments are performed on benchmark data sets for common ad-hoc retrieval tasks such as Web search, item recommendation, and question answering. Experimental results indicate that the proposed approaches significantly outperform strong baselines especially for high-ranked documents, and they outperform IRGAN in NDCG@5 using only 5% of labeled data for the Web search task. |
| Tasks | Information Retrieval, Question Answering |
| Published | 2018-11-09 |
| URL | https://arxiv.org/abs/1811.04155v2 |
| https://arxiv.org/pdf/1811.04155v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-sampling-and-training-for-semi |
| Repo | |
| Framework | |
A Note on Kaldi’s PLDA Implementation
| Title | A Note on Kaldi’s PLDA Implementation |
| Authors | Ke Ding |
| Abstract | Some explanations to Kaldi’s PLDA implementation to make formula derivation easier to catch. |
| Tasks | |
| Published | 2018-04-02 |
| URL | http://arxiv.org/abs/1804.00403v1 |
| http://arxiv.org/pdf/1804.00403v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-note-on-kaldis-plda-implementation |
| Repo | |
| Framework | |
Discriminative Data-driven Self-adaptive Fraud Control Decision System with Incomplete Information
| Title | Discriminative Data-driven Self-adaptive Fraud Control Decision System with Incomplete Information |
| Authors | Junxuan Li, Yung-wen Liu, Yuting Jia, Jay Nanduri |
| Abstract | While E-commerce has been growing explosively and online shopping has become popular and even dominant in the present era, online transaction fraud control has drawn considerable attention in business practice and academic research. Conventional fraud control considers mainly the interactions of two major involved decision parties, i.e. merchants and fraudsters, to make fraud classification decision without paying much attention to dynamic looping effect arose from the decisions made by other profit-related parties. This paper proposes a novel fraud control framework that can quantify interactive effects of decisions made by different parties and can adjust fraud control strategies using data analytics, artificial intelligence, and dynamic optimization techniques. Three control models, Naive, Myopic and Prospective Controls, were developed based on the availability of data attributes and levels of label maturity. The proposed models are purely data-driven and self-adaptive in a real-time manner. The field test on Microsoft real online transaction data suggested that new systems could sizably improve the company’s profit. |
| Tasks | |
| Published | 2018-10-03 |
| URL | https://arxiv.org/abs/1810.01982v2 |
| https://arxiv.org/pdf/1810.01982v2.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-data-driven-self-adaptive |
| Repo | |
| Framework | |
Quantum algorithms for feedforward neural networks
| Title | Quantum algorithms for feedforward neural networks |
| Authors | Jonathan Allcock, Chang-Yu Hsieh, Iordanis Kerenidis, Shengyu Zhang |
| Abstract | Quantum machine learning has the potential for broad industrial applications, and the development of quantum algorithms for improving the performance of neural networks is of particular interest given the central role they play in machine learning today. In this paper we present quantum algorithms for training and evaluating feedforward neural networks based on the canonical classical feedforward and backpropagation algorithms. Our algorithms rely on an efficient quantum subroutine for approximating the inner products between vectors in a robust way, and on implicitly storing large intermediate values in quantum random access memory for fast retrieval at later stages. The running times of our algorithms can be quadratically faster in the size of the network than their standard classical counterparts since they depend linearly on the number of neurons in the network, as opposed to the number of connections between neurons as in the classical case. This makes our algorithms suited for large-scale, highly-connected networks where the number of edges in the network dominates the classical algorithmic running time. Furthermore, networks trained by our quantum algorithm may have an intrinsic resilience to overfitting, as the algorithm naturally mimics the effects of classical techniques such as drop-out used to regularize networks. Our algorithms can also be used as the basis for new quantum-inspired classical algorithms which have the same dependence on the network dimensions as their quantum counterparts, but with quadratic overhead in other parameters that makes them relatively impractical. |
| Tasks | Quantum Machine Learning |
| Published | 2018-12-07 |
| URL | https://arxiv.org/abs/1812.03089v2 |
| https://arxiv.org/pdf/1812.03089v2.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-algorithms-for-feedforward-neural |
| Repo | |
| Framework | |
An Amalgamation of Classical and Quantum Machine Learning For the Classification of Adenocarcinoma and Squamous Cell Carcinoma Patients
| Title | An Amalgamation of Classical and Quantum Machine Learning For the Classification of Adenocarcinoma and Squamous Cell Carcinoma Patients |
| Authors | Siddhant Jain, Jalal Ziauddin, Paul Leonchyk, Joseph Geraci |
| Abstract | The ability to accurately classify disease subtypes is of vital importance, especially in oncology where this capability could have a life saving impact. Here we report a classification between two subtypes of non-small cell lung cancer, namely Adeno- carcinoma vs Squamous cell carcinoma. The data consists of approximately 20,000 gene expression values for each of 104 patients. The data was curated from [1] [2]. We used an amalgamation of classical and and quantum machine learning models to successfully classify these patients. We utilized feature selection methods based on univariate statistics in addition to XGBoost [3]. A novel and proprietary data representation method developed by one of the authors called QCrush was also used as it was designed to incorporate a maximal amount of information under the size constraints of the D-Wave quantum annealing computer. The machine learning was performed by a Quantum Boltzmann Machine. This paper will report our results, the various classical methods, and the quantum machine learning approach we utilized. |
| Tasks | Feature Selection, Quantum Machine Learning |
| Published | 2018-10-29 |
| URL | http://arxiv.org/abs/1810.11959v1 |
| http://arxiv.org/pdf/1810.11959v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-amalgamation-of-classical-and-quantum |
| Repo | |
| Framework | |
Implementable Quantum Classifier for Nonlinear Data
| Title | Implementable Quantum Classifier for Nonlinear Data |
| Authors | Yuxuan Du, Min-Hsiu Hsieh, Tongliang Liu, Dacheng Tao |
| Abstract | In this Letter, we propose a quantum machine learning scheme for the classification of classical nonlinear data. The main ingredients of our method are variational quantum perceptron (VQP) and a quantum generalization of classical ensemble learning. Our VQP employs parameterized quantum circuits to learn a Grover search (or amplitude amplification) operation with classical optimization, and can achieve quadratic speedup in query complexity compared to its classical counterparts. We show how the trained VQP can be used to predict future data with $O(1)$ {query} complexity. Ultimately, a stronger nonlinear classifier can be established, the so-called quantum ensemble learning (QEL), by combining a set of weak VQPs produced using a subsampling method. The subsampling method has two significant advantages. First, all $T$ weak VQPs employed in QEL can be trained in parallel, therefore, the query complexity of QEL is equal to that of each weak VQP multiplied by $T$. Second, it dramatically reduce the {runtime} complexity of encoding circuits that map classical data to a quantum state because this dataset can be significantly smaller than the original dataset given to QEL. This arguably provides a most satisfactory solution to one of the most criticized issues in quantum machine learning proposals. To conclude, we perform two numerical experiments for our VQP and QEL, implemented by Python and pyQuil library. Our experiments show that excellent performance can be achieved using a very small quantum circuit size that is implementable under current quantum hardware development. Specifically, given a nonlinear synthetic dataset with $4$ features for each example, the trained QEL can classify the test examples that are sampled away from the decision boundaries using $146$ single and two qubits quantum gates with $92%$ accuracy. |
| Tasks | Quantum Machine Learning |
| Published | 2018-09-17 |
| URL | http://arxiv.org/abs/1809.06056v1 |
| http://arxiv.org/pdf/1809.06056v1.pdf | |
| PWC | https://paperswithcode.com/paper/implementable-quantum-classifier-for |
| Repo | |
| Framework | |
A Pixel-Based Framework for Data-Driven Clothing
| Title | A Pixel-Based Framework for Data-Driven Clothing |
| Authors | Ning Jin, Yilin Zhu, Zhenglin Geng, Ronald Fedkiw |
| Abstract | With the aim of creating virtual cloth deformations more similar to real world clothing, we propose a new computational framework that recasts three dimensional cloth deformation as an RGB image in a two dimensional pattern space. Then a three dimensional animation of cloth is equivalent to a sequence of two dimensional RGB images, which in turn are driven/choreographed via animation parameters such as joint angles. This allows us to leverage popular CNNs to learn cloth deformations in image space. The two dimensional cloth pixels are extended into the real world via standard body skinning techniques, after which the RGB values are interpreted as texture offsets and displacement maps. Notably, we illustrate that our approach does not require accurate unclothed body shapes or robust skinning techniques. Additionally, we discuss how standard image based techniques such as image partitioning for higher resolution, GANs for merging partitioned image regions back together, etc., can readily be incorporated into our framework. |
| Tasks | |
| Published | 2018-12-03 |
| URL | http://arxiv.org/abs/1812.01677v1 |
| http://arxiv.org/pdf/1812.01677v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-pixel-based-framework-for-data-driven |
| Repo | |
| Framework | |
Modeling Realistic Degradations in Non-blind Deconvolution
| Title | Modeling Realistic Degradations in Non-blind Deconvolution |
| Authors | Jérémy Anger, Mauricio Delbracio, Gabriele Facciolo |
| Abstract | Most image deblurring methods assume an over-simplistic image formation model and as a result are sensitive to more realistic image degradations. We propose a novel variational framework, that explicitly handles pixel saturation, noise, quantization, as well as non-linear camera response function due to e.g., gamma correction. We show that accurately modeling a more realistic image acquisition pipeline leads to significant improvements, both in terms of image quality and PSNR. Furthermore, we show that incorporating the non-linear response in both the data and the regularization terms of the proposed energy leads to a more detailed restoration than a naive inversion of the non-linear curve. The minimization of the proposed energy is performed using stochastic optimization. A dataset consisting of realistically degraded images is created in order to evaluate the method. |
| Tasks | Deblurring, Quantization, Stochastic Optimization |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01097v1 |
| http://arxiv.org/pdf/1806.01097v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-realistic-degradations-in-non-blind |
| Repo | |
| Framework | |
A theory of consciousness: computation, algorithm, and neurobiological realization
| Title | A theory of consciousness: computation, algorithm, and neurobiological realization |
| Authors | J. H. van Hateren |
| Abstract | The most enigmatic aspect of consciousness is the fact that it is felt, as a subjective sensation. The theory proposed here aims to explain this particular aspect. The theory encompasses both the computation that is presumably involved and the way in which that computation may be realized in the brain’s neurobiology. It is assumed that the brain makes an internal estimate of an individual’s own evolutionary fitness, which can be shown to produce a special, distinct form of causation. Communicating components of the fitness estimate (either for external or internal use) requires inverting them. Such inversion can be performed by the thalamocortical feedback loop in the mammalian brain, if that loop is operating in a switched, dual-stage mode. A first (nonconscious) stage produces forward estimates, whereas the second (conscious) stage inverts those estimates. It is argued that inversion produces another special, distinct form of causation, which is spatially localized and is plausibly sensed as the feeling of consciousness. |
| Tasks | |
| Published | 2018-04-09 |
| URL | https://arxiv.org/abs/1804.02952v4 |
| https://arxiv.org/pdf/1804.02952v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-theory-of-consciousness-computation |
| Repo | |
| Framework | |
Smile detection in the wild based on transfer learning
| Title | Smile detection in the wild based on transfer learning |
| Authors | Xin Guo, Luisa F. Polanía, Kenneth E. Barner |
| Abstract | Smile detection from unconstrained facial images is a specialized and challenging problem. As one of the most informative expressions, smiles convey basic underlying emotions, such as happiness and satisfaction, which lead to multiple applications, e.g., human behavior analysis and interactive controlling. Compared to the size of databases for face recognition, far less labeled data is available for training smile detection systems. To leverage the large amount of labeled data from face recognition datasets and to alleviate overfitting on smile detection, an efficient transfer learning-based smile detection approach is proposed in this paper. Unlike previous works which use either hand-engineered features or train deep convolutional networks from scratch, a well-trained deep face recognition model is explored and fine-tuned for smile detection in the wild. Three different models are built as a result of fine-tuning the face recognition model with different inputs, including aligned, unaligned and grayscale images generated from the GENKI-4K dataset. Experiments show that the proposed approach achieves improved state-of-the-art performance. Robustness of the model to noise and blur artifacts is also evaluated in this paper. |
| Tasks | Face Recognition, Transfer Learning |
| Published | 2018-01-17 |
| URL | http://arxiv.org/abs/1802.02185v1 |
| http://arxiv.org/pdf/1802.02185v1.pdf | |
| PWC | https://paperswithcode.com/paper/smile-detection-in-the-wild-based-on-transfer |
| Repo | |
| Framework | |
Predictive Image Regression for Longitudinal Studies with Missing Data
| Title | Predictive Image Regression for Longitudinal Studies with Missing Data |
| Authors | Sharmin Pathan, Yi Hong |
| Abstract | In this paper, we propose a predictive regression model for longitudinal images with missing data based on large deformation diffeomorphic metric mapping (LDDMM) and deep neural networks. Instead of directly predicting image scans, our model predicts a vector momentum sequence associated with a baseline image. This momentum sequence parameterizes the original image sequence in the LDDMM framework and lies in the tangent space of the baseline image, which is Euclidean. A recurrent network with long term-short memory (LSTM) units encodes the time-varying changes in the vector-momentum sequence, and a convolutional neural network (CNN) encodes the baseline image of the vector momenta. Features extracted by the LSTM and CNN are fed into a decoder network to reconstruct the vector momentum sequence, which is used for the image sequence prediction by deforming the baseline image with LDDMM shooting. To handle the missing images at some time points, we adopt a binary mask to ignore their reconstructions in the loss calculation. We evaluate our model on synthetically generated images and the brain MRIs from the OASIS dataset. Experimental results demonstrate the promising predictions of the spatiotemporal changes in both datasets, irrespective of large or subtle changes in longitudinal image sequences. |
| Tasks | |
| Published | 2018-08-19 |
| URL | http://arxiv.org/abs/1808.07553v1 |
| http://arxiv.org/pdf/1808.07553v1.pdf | |
| PWC | https://paperswithcode.com/paper/predictive-image-regression-for-longitudinal |
| Repo | |
| Framework | |
