October 19, 2019

3050 words 15 mins read

Paper Group ANR 170

A Cyber Science Based Ontology for Artificial General Intelligence Containment. A Unified Framework for Generalizable Style Transfer: Style and Content Separation. Effects of Lombard Reflex on the Performance of Deep-Learning-Based Audio-Visual Speech Enhancement Systems. On Training Targets and Objective Functions for Deep-Learning-Based Audio-Vis …

A Cyber Science Based Ontology for Artificial General Intelligence Containment


Title	A Cyber Science Based Ontology for Artificial General Intelligence Containment
Authors	Jason M. Pittman, Courtney E. Soboleski
Abstract	The development of artificial general intelligence is considered by many to be inevitable. What such intelligence does after becoming aware is not so certain. To that end, research suggests that the likelihood of artificial general intelligence becoming hostile to humans is significant enough to warrant inquiry into methods to limit such potential. Thus, containment of artificial general intelligence is a timely and meaningful research topic. While there is limited research exploring possible containment strategies, such work is bounded by the underlying field the strategies draw upon. Accordingly, we set out to construct an ontology to describe necessary elements in any future containment technology. Using existing academic literature, we developed a single domain ontology containing five levels, 32 codes, and 32 associated descriptors. Further, we constructed ontology diagrams to demonstrate intended relationships. We then identified humans, AGI, and the cyber world as novel agent objects necessary for future containment activities. Collectively, the work addresses three critical gaps: (a) identifying and arranging fundamental constructs; (b) situating AGI containment within cyber science; and (c) developing scientific rigor within the field.
Tasks
Published	2018-01-28
URL	http://arxiv.org/abs/1801.09317v1
PDF	http://arxiv.org/pdf/1801.09317v1.pdf
PWC	https://paperswithcode.com/paper/a-cyber-science-based-ontology-for-artificial
Repo
Framework

A Unified Framework for Generalizable Style Transfer: Style and Content Separation


Title	A Unified Framework for Generalizable Style Transfer: Style and Content Separation
Authors	Yexun Zhang, Ya Zhang, Wenbin Cai
Abstract	Image style transfer has drawn broad attention in recent years. However, most existing methods aim to explicitly model the transformation between different styles, and the learned model is thus not generalizable to new styles. We here propose a unified style transfer framework for both character typeface transfer and neural style transfer tasks leveraging style and content separation. A key merit of such framework is its generalizability to new styles and contents. The overall framework consists of style encoder, content encoder, mixer and decoder. The style encoder and content encoder are used to extract the style and content representations from the corresponding reference images. The mixer integrates the above two representations and feeds it into the decoder to generate images with the target style and content. During training, the encoder networks learn to extract styles and contents from limited size of style/content reference images. This learning framework allows simultaneous style transfer among multiple styles and can be deemed as a special `multi-task’ learning scenario. The encoders are expected to capture the underlying features for different styles and contents which is generalizable to new styles and contents. Under this framework, we design two individual networks for character typeface transfer and neural style transfer, respectively. For character typeface transfer, to separate the style features and content features, we leverage the conditional dependence of styles and contents given an image. For neural style transfer, we leverage the statistical information of feature maps in certain layers to represent style. Extensive experimental results have demonstrated the effectiveness and robustness of the proposed methods. \|
Tasks	Multi-Task Learning, Style Transfer
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05173v1
PDF	http://arxiv.org/pdf/1806.05173v1.pdf
PWC	https://paperswithcode.com/paper/a-unified-framework-for-generalizable-style
Repo
Framework

Effects of Lombard Reflex on the Performance of Deep-Learning-Based Audio-Visual Speech Enhancement Systems


Title	Effects of Lombard Reflex on the Performance of Deep-Learning-Based Audio-Visual Speech Enhancement Systems
Authors	Daniel Michelsanti, Zheng-Hua Tan, Sigurdur Sigurdsson, Jesper Jensen
Abstract	Humans tend to change their way of speaking when they are immersed in a noisy environment, a reflex known as Lombard effect. Current speech enhancement systems based on deep learning do not usually take into account this change in the speaking style, because they are trained with neutral (non-Lombard) speech utterances recorded under quiet conditions to which noise is artificially added. In this paper, we investigate the effects that the Lombard reflex has on the performance of audio-visual speech enhancement systems based on deep learning. The results show that a gap in the performance of as much as approximately 5 dB between the systems trained on neutral speech and the ones trained on Lombard speech exists. This indicates the benefit of taking into account the mismatch between neutral and Lombard speech in the design of audio-visual speech enhancement systems.
Tasks	Speech Enhancement
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06250v1
PDF	http://arxiv.org/pdf/1811.06250v1.pdf
PWC	https://paperswithcode.com/paper/effects-of-lombard-reflex-on-the-performance
Repo
Framework

On Training Targets and Objective Functions for Deep-Learning-Based Audio-Visual Speech Enhancement


Title	On Training Targets and Objective Functions for Deep-Learning-Based Audio-Visual Speech Enhancement
Authors	Daniel Michelsanti, Zheng-Hua Tan, Sigurdur Sigurdsson, Jesper Jensen
Abstract	Audio-visual speech enhancement (AV-SE) is the task of improving speech quality and intelligibility in a noisy environment using audio and visual information from a talker. Recently, deep learning techniques have been adopted to solve the AV-SE task in a supervised manner. In this context, the choice of the target, i.e. the quantity to be estimated, and the objective function, which quantifies the quality of this estimate, to be used for training is critical for the performance. This work is the first that presents an experimental study of a range of different targets and objective functions used to train a deep-learning-based AV-SE system. The results show that the approaches that directly estimate a mask perform the best overall in terms of estimated speech quality and intelligibility, although the model that directly estimates the log magnitude spectrum performs as good in terms of estimated speech quality.
Tasks	Speech Enhancement
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06234v1
PDF	http://arxiv.org/pdf/1811.06234v1.pdf
PWC	https://paperswithcode.com/paper/on-training-targets-and-objective-functions
Repo
Framework

Regression and Classification by Zonal Kriging


Title	Regression and Classification by Zonal Kriging
Authors	Jean Serra, Jesus Angulo, B Ravi Kiran
Abstract	Consider a family $Z={\boldsymbol{x_{i}},y_{i}$,$1\leq i\leq N}$ of $N$ pairs of vectors $\boldsymbol{x_{i}} \in \mathbb{R}^d$ and scalars $y_{i}$ that we aim to predict for a new sample vector $\mathbf{x}_0$. Kriging models $y$ as a sum of a deterministic function $m$, a drift which depends on the point $\boldsymbol{x}$, and a random function $z$ with zero mean. The zonality hypothesis interprets $y$ as a weighted sum of $d$ random functions of a single independent variables, each of which is a kriging, with a quadratic form for the variograms drift. We can therefore construct an unbiased estimator $y^{}(\boldsymbol{x_{0}})=\sum_{i}\lambda^{i}z(\boldsymbol{x_{i}})$ de $y(\boldsymbol{x_{0}})$ with minimal variance $E[y^{}(\boldsymbol{x_{0}})-y(\boldsymbol{x_{0}})]^{2}$, with the help of the known training set points. We give the explicitly closed form for $\lambda^{i}$ without having calculated the inverse of the matrices.
Tasks
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12507v2
PDF	http://arxiv.org/pdf/1811.12507v2.pdf
PWC	https://paperswithcode.com/paper/regression-and-classification-by-zonal
Repo
Framework

Kernel Machines Beat Deep Neural Networks on Mask-based Single-channel Speech Enhancement


Title	Kernel Machines Beat Deep Neural Networks on Mask-based Single-channel Speech Enhancement
Authors	Like Hui, Siyuan Ma, Mikhail Belkin
Abstract	We apply a fast kernel method for mask-based single-channel speech enhancement. Specifically, our method solves a kernel regression problem associated to a non-smooth kernel function (exponential power kernel) with a highly efficient iterative method (EigenPro). Due to the simplicity of this method, its hyper-parameters such as kernel bandwidth can be automatically and efficiently selected using line search with subsamples of training data. We observe an empirical correlation between the regression loss (mean square error) and regular metrics for speech enhancement. This observation justifies our training target and motivates us to achieve lower regression loss by training separate kernel model per frequency subband. We compare our method with the state-of-the-art deep neural networks on mask-based HINT and TIMIT. Experimental results show that our kernel method consistently outperforms deep neural networks while requiring less training time.
Tasks	Speech Enhancement
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02095v1
PDF	http://arxiv.org/pdf/1811.02095v1.pdf
PWC	https://paperswithcode.com/paper/kernel-machines-beat-deep-neural-networks-on
Repo
Framework

A Contextual-bandit-based Approach for Informed Decision-making in Clinical Trials


Title	A Contextual-bandit-based Approach for Informed Decision-making in Clinical Trials
Authors	Yogatheesan Varatharajah, Brent Berry, Sanmi Koyejo, Ravishankar Iyer
Abstract	Clinical trials involving multiple treatments utilize randomization of the treatment assignments to enable the evaluation of treatment efficacies in an unbiased manner. Such evaluation is performed in post hoc studies that usually use supervised-learning methods that rely on large amounts of data collected in a randomized fashion. That approach often proves to be suboptimal in that some participants may suffer and even die as a result of having not received the most appropriate treatments during the trial. Reinforcement-learning methods improve the situation by making it possible to learn the treatment efficacies dynamically during the course of the trial, and to adapt treatment assignments accordingly. Recent efforts using \textit{multi-arm bandits}, a type of reinforcement-learning methods, have focused on maximizing clinical outcomes for a population that was assumed to be homogeneous. However, those approaches have failed to account for the variability among participants that is becoming increasingly evident as a result of recent clinical-trial-based studies. We present a contextual-bandit-based online treatment optimization algorithm that, in choosing treatments for new participants in the study, takes into account not only the maximization of the clinical outcomes but also the patient characteristics. We evaluated our algorithm using a real clinical trial dataset from the International Stroke Trial. The results of our retrospective analysis indicate that the proposed approach performs significantly better than either a random assignment of treatments (the current gold standard) or a multi-arm-bandit-based approach, providing substantial gains in the percentage of participants who are assigned the most suitable treatments. The contextual-bandit and multi-arm bandit approaches provide 72.63% and 64.34% gains, respectively, compared to a random assignment.
Tasks	Decision Making
Published	2018-09-01
URL	http://arxiv.org/abs/1809.00258v1
PDF	http://arxiv.org/pdf/1809.00258v1.pdf
PWC	https://paperswithcode.com/paper/a-contextual-bandit-based-approach-for
Repo
Framework

Modeling reverse thinking for machine learning


Title	Modeling reverse thinking for machine learning
Authors	Li Huihui, Wen Guihua
Abstract	Human inertial thinking schemes can be formed through learning, which are then applied to quickly solve similar problems later. However, when problems are significantly different, inertial thinking generally presents the solutions that are definitely imperfect. In such cases, people will apply creative thinking, such as reverse thinking, to solve problems. Similarly, machine learning methods also form inertial thinking schemes through learning the knowledge from a large amount of data. However, when the testing data are vastly difference, the formed inertial thinking schemes will inevitably generate errors. This kind of inertial thinking is called illusion inertial thinking. Because all machine learning methods do not consider illusion inertial thinking, in this paper we propose a new method that uses reverse thinking to correct illusion inertial thinking, which increases the generalization ability of machine learning methods. Experimental results on benchmark datasets are used to validate the proposed method.
Tasks
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00158v1
PDF	http://arxiv.org/pdf/1803.00158v1.pdf
PWC	https://paperswithcode.com/paper/modeling-reverse-thinking-for-machine
Repo
Framework

Graph based Entropy for Detecting Explanatory Signs of Changes in Market


Title	Graph based Entropy for Detecting Explanatory Signs of Changes in Market
Authors	Yukio Ohsawa
Abstract	Graph based entropy, an index of the diversity of events in their distribution to parts of a co-occurrence graph, is proposed for detecting signs of structural changes in the data that are informative in explaining latent dynamics of consumers behavior. For obtaining graph-based entropy, connected subgraphs are first obtained from the graph of co-occurrences of items in the data. Then, the distribution of items occurring in events in the data to these sub-graphs is reflected on the value of graph-based entropy. For the data on the position of sale, a change in this value is regarded as a sign of the appearance, the separation, the disappearance, or the uniting of consumers interests. These phenomena are regarded as the signs of dynamic changes in consumers behavior that may be the effects of external events and information. Experiments show that graph-based entropy outperforms baseline methods that can be used for change detection, in explaining substantial changes and their signs in consumers preference of items in supermarket stores.
Tasks
Published	2018-11-06
URL	http://arxiv.org/abs/1811.12165v1
PDF	http://arxiv.org/pdf/1811.12165v1.pdf
PWC	https://paperswithcode.com/paper/181112165
Repo
Framework

Trainable Adaptive Window Switching for Speech Enhancement


Title	Trainable Adaptive Window Switching for Speech Enhancement
Authors	Yuma Koizumi, Noboru Harada, Yoichi Haneda
Abstract	This study proposes a trainable adaptive window switching (AWS) method and apply it to a deep-neural-network (DNN) for speech enhancement in the modified discrete cosine transform domain. Time-frequency (T-F) mask processing in the short-time Fourier transform (STFT)-domain is a typical speech enhancement method. To recover the target signal precisely, DNN-based short-time frequency transforms have recently been investigated and used instead of the STFT. However, since such a fixed-resolution short-time frequency transform method has a T-F resolution problem based on the uncertainty principle, not only the short-time frequency transform but also the length of the windowing function should be optimized. To overcome this problem, we incorporate AWS into the speech enhancement procedure, and the windowing function of each time-frame is manipulated using a DNN depending on the input signal. We confirmed that the proposed method achieved a higher signal-to-distortion ratio than conventional speech enhancement methods in fixed-resolution frequency domains.
Tasks	Speech Enhancement
Published	2018-11-05
URL	http://arxiv.org/abs/1811.02438v4
PDF	http://arxiv.org/pdf/1811.02438v4.pdf
PWC	https://paperswithcode.com/paper/trainable-adaptive-window-switching-for
Repo
Framework

NEU Meta-Learning and its Universal Approximation Properties


Title	NEU Meta-Learning and its Universal Approximation Properties
Authors	Anastasis Kratsios, Cody Hyndman
Abstract	We introduce a new meta-learning procedure, called non-Euclidean upgrading (NEU), which learns algorithm-specific geometries by deforming the ambient space until the algorithm can achieve optimal performance. We prove that these deformations have several novel and semi-classical universal approximation properties. These deformations can be used to approximate any continuous, Borel, or modular-Lebesgue integrable functions to arbitrary precision. Further, these deformations can transport any data-set into any other data-set in a finite number of iterations while leaving most of the space fixed. The NEU meta-algorithm embeds these deformations into a wide range of learning algorithms. We prove that the NEU version of the original algorithm must perform better than the original learning algorithm. Moreover, by quantifying model-free learning algorithms as specific unconstrained optimization problems, we find that the NEU version of a learning algorithm must perform better than the model-free extension of the original algorithm. The properties and performance of the NEU meta-algorithm are examined in various simulation studies and applications to financial data.
Tasks	Meta-Learning
Published	2018-08-31
URL	https://arxiv.org/abs/1809.00082v2
PDF	https://arxiv.org/pdf/1809.00082v2.pdf
PWC	https://paperswithcode.com/paper/the-neu-meta-algorithm-for-geometric-learning
Repo
Framework

On decision regions of narrow deep neural networks


Title	On decision regions of narrow deep neural networks
Authors	Hans-Peter Beise, Steve Dias Da Cruz, Udo Schröder
Abstract	We show that for neural network functions that have width less or equal to the input dimension all connected components of decision regions are unbounded. The result holds for continuous and strictly monotonic activation functions as well as for ReLU activation. This complements recent results on approximation capabilities of [Hanin 2017 Approximating] and connectivity of decision regions of [Nguyen 2018 Neural] for such narrow neural networks. Further, we give an example that negatively answers the question posed in [Nguyen 2018 Neural] whether one of their main results still holds for ReLU activation. Our results are illustrated by means of numerical experiments.
Tasks
Published	2018-07-03
URL	https://arxiv.org/abs/1807.01194v3
PDF	https://arxiv.org/pdf/1807.01194v3.pdf
PWC	https://paperswithcode.com/paper/on-decision-regions-of-narrow-deep-neural
Repo
Framework

Semi-Supervised Methods for Out-of-Domain Dependency Parsing


Title	Semi-Supervised Methods for Out-of-Domain Dependency Parsing
Authors	Juntao Yu
Abstract	Dependency parsing is one of the important natural language processing tasks that assigns syntactic trees to texts. Due to the wider availability of dependency corpora and improved parsing and machine learning techniques, parsing accuracies of supervised learning-based systems have been significantly improved. However, due to the nature of supervised learning, those parsing systems highly rely on the manually annotated training corpora. They work reasonably good on the in-domain data but the performance drops significantly when tested on out-of-domain texts. To bridge the performance gap between in-domain and out-of-domain, this thesis investigates three semi-supervised techniques for out-of-domain dependency parsing, namely co-training, self-training and dependency language models. Our approaches use easily obtainable unlabelled data to improve out-of-domain parsing accuracies without the need of expensive corpora annotation. The evaluations on several English domains and multi-lingual data show quite good improvements on parsing accuracy. Overall this work conducted a survey of semi-supervised methods for out-of-domain dependency parsing, where I extended and compared a number of important semi-supervised methods in a unified framework. The comparison between those techniques shows that self-training works equally well as co-training on out-of-domain parsing, while dependency language models can improve both in- and out-of-domain accuracies.
Tasks	Dependency Parsing
Published	2018-10-04
URL	http://arxiv.org/abs/1810.02100v1
PDF	http://arxiv.org/pdf/1810.02100v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-methods-for-out-of-domain
Repo
Framework

Eigenvalue analogy for confidence estimation in item-based recommender systems


Title	Eigenvalue analogy for confidence estimation in item-based recommender systems
Authors	Maurizio Ferrari Dacrema, Paolo Cremonesi
Abstract	Item-item collaborative filtering (CF) models are a well known and studied family of recommender systems, however current literature does not provide any theoretical explanation of the conditions under which item-based recommendations will succeed or fail. We investigate the existence of an ideal item-based CF method able to make perfect recommendations. This CF model is formalized as an eigenvalue problem, where estimated ratings are equivalent to the true (unknown) ratings multiplied by a user-specific eigenvalue of the similarity matrix. Preliminary experiments show that the magnitude of the eigenvalue is proportional to the accuracy of recommendations for that user and therefore it can provide reliable measure of confidence.
Tasks	Recommendation Systems
Published	2018-08-31
URL	http://arxiv.org/abs/1809.02052v2
PDF	http://arxiv.org/pdf/1809.02052v2.pdf
PWC	https://paperswithcode.com/paper/eigenvalue-analogy-for-confidence-estimation
Repo
Framework

Learning What Information to Give in Partially Observed Domains


Title	Learning What Information to Give in Partially Observed Domains
Authors	Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez
Abstract	In many robotic applications, an autonomous agent must act within and explore a partially observed environment that is unobserved by its human teammate. We consider such a setting in which the agent can, while acting, transmit declarative information to the human that helps them understand aspects of this unseen environment. In this work, we address the algorithmic question of how the agent should plan out what actions to take and what information to transmit. Naturally, one would expect the human to have preferences, which we model information-theoretically by scoring transmitted information based on the change it induces in weighted entropy of the human’s belief state. We formulate this setting as a belief MDP and give a tractable algorithm for solving it approximately. Then, we give an algorithm that allows the agent to learn the human’s preferences online, through exploration. We validate our approach experimentally in simulated discrete and continuous partially observed search-and-recover domains. Visit http://tinyurl.com/chitnis-corl-18 for a supplementary video.
Tasks
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08263v4
PDF	http://arxiv.org/pdf/1805.08263v4.pdf
PWC	https://paperswithcode.com/paper/learning-what-information-to-give-in
Repo
Framework