Paper Group ANR 1662
Machine-learning techniques for the optimal design of acoustic metamaterials. Design and Evaluation of Product Aesthetics: A Human-Machine Hybrid Approach. Robust Linear Discriminant Analysis Using Ratio Minimization of L1,2-Norms. Conditional Response Generation Using Variational Alignment. Medical Imaging with Deep Learning: MIDL 2019 – Extended …
Machine-learning techniques for the optimal design of acoustic metamaterials
| Title | Machine-learning techniques for the optimal design of acoustic metamaterials |
| Authors | Andrea Bacigalupo, Giorgio Gnecco, Marco Lepidi, Luigi Gambarotta |
| Abstract | Recently, an increasing research effort has been dedicated to analyse the transmission and dispersion properties of periodic acoustic metamaterials, characterized by the presence of local resonators. Within this context, particular attention has been paid to the optimization of the amplitudes and center frequencies of selected stop and pass bands inside the Floquet-Bloch spectra of the acoustic metamaterials featured by a chiral or antichiral microstructure. Novel functional applications of such research are expected in the optimal parametric design of smart tunable mechanical filters and directional waveguides. The present paper deals with the maximization of the amplitude of low-frequency band gaps, by proposing suitable numerical techniques to solve the associated optimization problems. Specifically, the feasibility and effectiveness of Radial Basis Function networks and Quasi-Monte Carlo methods for the interpolation of the objective functions of such optimization problems are discussed, and their numerical application to a specific acoustic metamaterial with tetrachiral microstructure is presented. The discussion is motivated theoretically by the high computational effort often needed for an exact evaluation of the objective functions arising in band gap optimization problems, when iterative algorithms are used for their approximate solution. By replacing such functions with suitable surrogate objective functions constructed applying machine-learning techniques, well performing suboptimal solutions can be obtained with a smaller computational effort. Numerical results demonstrate the effective potential of the proposed approach. Current directions of research involving the use of additional machine-learning techniques are also presented. |
| Tasks | Band Gap |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10645v1 |
| https://arxiv.org/pdf/1908.10645v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-techniques-for-the-optimal |
| Repo | |
| Framework | |
Design and Evaluation of Product Aesthetics: A Human-Machine Hybrid Approach
| Title | Design and Evaluation of Product Aesthetics: A Human-Machine Hybrid Approach |
| Authors | Alex Burnap, John R. Hauser, Artem Timoshenko |
| Abstract | Aesthetics are critically important to market acceptance in many product categories. In the automotive industry in particular, an improved aesthetic design can boost sales by 30% or more. Firms invest heavily in designing and testing new product aesthetics. A single automotive “theme clinic” costs between $100,000 and $1,000,000, and hundreds are conducted annually. We use machine learning to augment human judgment when designing and testing new product aesthetics. The model combines a probabilistic variational autoencoder (VAE) and adversarial components from generative adversarial networks (GAN), along with modeling assumptions that address managerial requirements for firm adoption. We train our model with data from an automotive partner-7,000 images evaluated by targeted consumers and 180,000 high-quality unrated images. Our model predicts well the appeal of new aesthetic designs-38% improvement relative to a baseline and substantial improvement over both conventional machine learning models and pretrained deep learning models. New automotive designs are generated in a controllable manner for the design team to consider, which we also empirically verify are appealing to consumers. These results, combining human and machine inputs for practical managerial usage, suggest that machine learning offers significant opportunity to augment aesthetic design. |
| Tasks | |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07786v1 |
| https://arxiv.org/pdf/1907.07786v1.pdf | |
| PWC | https://paperswithcode.com/paper/design-and-evaluation-of-product-aesthetics-a |
| Repo | |
| Framework | |
Robust Linear Discriminant Analysis Using Ratio Minimization of L1,2-Norms
| Title | Robust Linear Discriminant Analysis Using Ratio Minimization of L1,2-Norms |
| Authors | Feiping Nie, Hua Wang, Zheng Wang, Heng Huang |
| Abstract | As one of the most popular linear subspace learning methods, the Linear Discriminant Analysis (LDA) method has been widely studied in machine learning community and applied to many scientific applications. Traditional LDA minimizes the ratio of squared L2-norms, which is sensitive to outliers. In recent research, many L1-norm based robust Principle Component Analysis methods were proposed to improve the robustness to outliers. However, due to the difficulty of L1-norm ratio optimization, so far there is no existing work to utilize sparsity-inducing norms for LDA objective. In this paper, we propose a novel robust linear discriminant analysis method based on the L1,2-norm ratio minimization. Minimizing the L1,2-norm ratio is a much more challenging problem than the traditional methods, and there is no existing optimization algorithm to solve such non-smooth terms ratio problem. We derive a new efficient algorithm to solve this challenging problem, and provide a theoretical analysis on the convergence of our algorithm. The proposed algorithm is easy to implement, and converges fast in practice. Extensive experiments on both synthetic data and nine real benchmark data sets show the effectiveness of the proposed robust LDA method. |
| Tasks | |
| Published | 2019-06-29 |
| URL | https://arxiv.org/abs/1907.00211v1 |
| https://arxiv.org/pdf/1907.00211v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-linear-discriminant-analysis-using |
| Repo | |
| Framework | |
Conditional Response Generation Using Variational Alignment
| Title | Conditional Response Generation Using Variational Alignment |
| Authors | Kashif Khan, Gaurav Sahu, Vikash Balasubramanian, Lili Mou, Olga Vechtomova |
| Abstract | Generating relevant/conditioned responses in dialog is challenging, and requires not only proper modelling of context in the conversation, but also the ability to generate fluent sentences during inference. In this paper, we propose a two-step framework based on generative adversarial nets for generating conditioned responses. Our model first learns meaningful representations of sentences, and then uses a generator to \textit{match} the query with the response distribution. Latent codes from the latter are then used to generate responses. Both quantitative and qualitative evaluations show that our model generates more fluent, relevant and diverse responses than the existing state-of-the-art methods. |
| Tasks | |
| Published | 2019-11-10 |
| URL | https://arxiv.org/abs/1911.03817v1 |
| https://arxiv.org/pdf/1911.03817v1.pdf | |
| PWC | https://paperswithcode.com/paper/conditional-response-generation-using |
| Repo | |
| Framework | |
Medical Imaging with Deep Learning: MIDL 2019 – Extended Abstract Track
| Title | Medical Imaging with Deep Learning: MIDL 2019 – Extended Abstract Track |
| Authors | M. Jorge Cardoso, Aasa Feragen, Ben Glocker, Ender Konukoglu, Ipek Oguz, Gozde Unal, Tom Vercauteren |
| Abstract | This compendium gathers all the accepted extended abstracts from the Second International Conference on Medical Imaging with Deep Learning (MIDL 2019), held in London, UK, 8-10 July 2019. Note that only accepted extended abstracts are listed here, the Proceedings of the MIDL 2019 Full Paper Track are published as Volume 102 of the Proceedings of Machine Learning Research (PMLR) http://proceedings.mlr.press/v102/. |
| Tasks | |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1907.08612v2 |
| https://arxiv.org/pdf/1907.08612v2.pdf | |
| PWC | https://paperswithcode.com/paper/medical-imaging-with-deep-learning-midl-2019 |
| Repo | |
| Framework | |
Planning with Abstract Learned Models While Learning Transferable Subtasks
| Title | Planning with Abstract Learned Models While Learning Transferable Subtasks |
| Authors | John Winder, Stephanie Milani, Matthew Landen, Erebus Oh, Shane Parr, Shawn Squire, Marie desJardins, Cynthia Matuszek |
| Abstract | We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with Abstract Learned Models (PALM). By representing subtasks symbolically using a new formal structure, the lifted abstract Markov decision process (L-AMDP), PALM learns models that are independent and modular. Through our experiments, we show how PALM integrates planning and execution, facilitating a rapid and efficient learning of abstract, hierarchical models. We also demonstrate the increased potential for learned models to be transferred to new and related tasks. |
| Tasks | Hierarchical Reinforcement Learning |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07544v1 |
| https://arxiv.org/pdf/1912.07544v1.pdf | |
| PWC | https://paperswithcode.com/paper/planning-with-abstract-learned-models-while |
| Repo | |
| Framework | |
Gradient Scheduling with Global Momentum for Non-IID Data Distributed Asynchronous Training
| Title | Gradient Scheduling with Global Momentum for Non-IID Data Distributed Asynchronous Training |
| Authors | Chengjie Li, Ruixuan Li, Haozhao Wang, Yuhua Li, Pan Zhou, Song Guo, Keqin Li |
| Abstract | Distributed asynchronous offline training has received widespread attention in recent years because of its high performance on large-scale data and complex models. As data are distributed from cloud-centric to edge nodes, a big challenge for distributed machine learning systems is how to handle native and natural non-independent and identically distributed (non-IID) data for training. Previous asynchronous training methods do not have a satisfying performance on non-IID data because it would result in that the training process fluctuates greatly which leads to an abnormal convergence. We propose a gradient scheduling algorithm with partly averaged gradients and global momentum (GSGM) for non-IID data distributed asynchronous training. Our key idea is to apply global momentum and local average to the biased gradient after scheduling, in order to make the training process steady. Experimental results show that for non-IID data training under the same experimental conditions, GSGM on popular optimization algorithms can achieve a 20% increase in training stability with a slight improvement in accuracy on Fashion-Mnist and CIFAR-10 datasets. Meanwhile, when expanding distributed scale on CIFAR-100 dataset that results in sparse data distribution, GSGM can perform a 37% improvement on training stability. Moreover, only GSGM can converge well when the number of computing nodes grows to 30, compared to the state-of-the-art distributed asynchronous algorithms. At the same time, GSGM is robust to different degrees of non-IID data. |
| Tasks | |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.07848v3 |
| http://arxiv.org/pdf/1902.07848v3.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-scheduling-with-global-momentum-for |
| Repo | |
| Framework | |
On the Weaknesses of Reinforcement Learning for Neural Machine Translation
| Title | On the Weaknesses of Reinforcement Learning for Neural Machine Translation |
| Authors | Leshem Choshen, Lior Fox, Zohar Aizenbud, Omri Abend |
| Abstract | Reinforcement learning (RL) is frequently used to increase performance in text generation tasks, including machine translation (MT), notably through the use of Minimum Risk Training (MRT) and Generative Adversarial Networks (GAN). However, little is known about what and how these methods learn in the context of MT. We prove that one of the most common RL methods for MT does not optimize the expected reward, as well as show that other methods take an infeasibly long time to converge. In fact, our results suggest that RL practices in MT are likely to improve performance only where the pre-trained parameters are already close to yielding the correct translation. Our findings further suggest that observed gains may be due to effects unrelated to the training signal, but rather from changes in the shape of the distribution curve. |
| Tasks | Machine Translation, Text Generation |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.01752v4 |
| https://arxiv.org/pdf/1907.01752v4.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-weaknesses-of-reinforcement-learning |
| Repo | |
| Framework | |
Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples
| Title | Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples |
| Authors | Marcus Soll, Tobias Hinz, Sven Magg, Stefan Wermter |
| Abstract | Adversarial examples are artificially modified input samples which lead to misclassifications, while not being detectable by humans. These adversarial examples are a challenge for many tasks such as image and text classification, especially as research shows that many adversarial examples are transferable between different classifiers. In this work, we evaluate the performance of a popular defensive strategy for adversarial examples called defensive distillation, which can be successful in hardening neural networks against adversarial examples in the image domain. However, instead of applying defensive distillation to networks for image classification, we examine, for the first time, its performance on text classification tasks and also evaluate its effect on the transferability of adversarial text examples. Our results indicate that defensive distillation only has a minimal impact on text classifying neural networks and does neither help with increasing their robustness against adversarial examples nor prevent the transferability of adversarial examples between neural networks. |
| Tasks | Adversarial Text, Image Classification, Text Classification |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.07899v1 |
| https://arxiv.org/pdf/1908.07899v1.pdf | |
| PWC | https://paperswithcode.com/paper/190807899 |
| Repo | |
| Framework | |
Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation
| Title | Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation |
| Authors | Aran Sena, Brendan Michael, Matthew Howard |
| Abstract | Learning from Demonstration depends on a robot learner generalising its learned model to unseen conditions, as it is not feasible for a person to provide a demonstration set that accounts for all possible variations in non-trivial tasks. While there are many learning methods that can handle interpolation of observed data effectively, extrapolation from observed data offers a much greater challenge. To address this problem of generalisation, this paper proposes a modified Task-Parameterised Gaussian Mixture Regression method that considers the relevance of task parameters during trajectory generation, as determined by variance in the data. The benefits of the proposed method are first explored using a simulated reaching task data set. Here it is shown that the proposed method offers far-reaching, low-error extrapolation abilities that are different in nature to existing learning methods. Data collected from novice users for a real-world manipulation task is then considered, where it is shown that the proposed method is able to effectively reduce grasping performance errors by ${\sim30%}$ and extrapolate to unseen grasp targets under real-world conditions. These results indicate the proposed method serves to benefit novice users by placing less reliance on the user to provide high quality demonstration data sets. |
| Tasks | |
| Published | 2019-03-04 |
| URL | http://arxiv.org/abs/1903.01240v1 |
| http://arxiv.org/pdf/1903.01240v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-task-parameterised-movement |
| Repo | |
| Framework | |
Learning Only from Relevant Keywords and Unlabeled Documents
| Title | Learning Only from Relevant Keywords and Unlabeled Documents |
| Authors | Nontawat Charoenphakdee, Jongyeong Lee, Yiping Jin, Dittaya Wanvarie, Masashi Sugiyama |
| Abstract | We consider a document classification problem where document labels are absent but only relevant keywords of a target class and unlabeled documents are given. Although heuristic methods based on pseudo-labeling have been considered, theoretical understanding of this problem has still been limited. Moreover, previous methods cannot easily incorporate well-developed techniques in supervised text classification. In this paper, we propose a theoretically guaranteed learning framework that is simple to implement and has flexible choices of models, e.g., linear models or neural networks. We demonstrate how to optimize the area under the receiver operating characteristic curve (AUC) effectively and also discuss how to adjust it to optimize other well-known evaluation metrics such as the accuracy and F1-measure. Finally, we show the effectiveness of our framework using benchmark datasets. |
| Tasks | Document Classification, Text Classification |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04385v2 |
| https://arxiv.org/pdf/1910.04385v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-only-from-relevant-keywords-and |
| Repo | |
| Framework | |
SemEval-2013 Task 2: Sentiment Analysis in Twitter
| Title | SemEval-2013 Task 2: Sentiment Analysis in Twitter |
| Authors | Preslav Nakov, Zornitsa Kozareva, Alan Ritter, Sara Rosenthal, Veselin Stoyanov, Theresa Wilson |
| Abstract | In recent years, sentiment analysis in social media has attracted a lot of research interest and has been used for a number of applications. Unfortunately, research has been hindered by the lack of suitable datasets, complicating the comparison between approaches. To address this issue, we have proposed SemEval-2013 Task 2: Sentiment Analysis in Twitter, which included two subtasks: A, an expression-level subtask, and B, a message-level subtask. We used crowdsourcing on Amazon Mechanical Turk to label a large Twitter training dataset along with additional test sets of Twitter and SMS messages for both subtasks. All datasets used in the evaluation are released to the research community. The task attracted significant interest and a total of 149 submissions from 44 teams. The best-performing team achieved an F1 of 88.9% and 69% for subtasks A and B, respectively. |
| Tasks | Sentiment Analysis |
| Published | 2019-12-14 |
| URL | https://arxiv.org/abs/1912.06806v1 |
| https://arxiv.org/pdf/1912.06806v1.pdf | |
| PWC | https://paperswithcode.com/paper/semeval-2013-task-2-sentiment-analysis-in-1 |
| Repo | |
| Framework | |
Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization
| Title | Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization |
| Authors | Diego Antognini, Boi Faltings |
| Abstract | Linking facts across documents is a challenging task, as the language used to express the same information in a sentence can vary significantly, which complicates the task of multi-document summarization. Consequently, existing approaches heavily rely on hand-crafted features, which are domain-dependent and hard to craft, or additional annotated data, which is costly to gather. To overcome these limitations, we present a novel method, which makes use of two types of sentence embeddings: universal embeddings, which are trained on a large unrelated corpus, and domain-specific embeddings, which are learned during training. To this end, we develop SemSentSum, a fully data-driven model able to leverage both types of sentence embeddings by building a sentence semantic relation graph. SemSentSum achieves competitive results on two types of summary, consisting of 665 bytes and 100 words. Unlike other state-of-the-art models, neither hand-crafted features nor additional annotated data are necessary, and the method is easily adaptable for other tasks. To our knowledge, we are the first to use multiple sentence embeddings for the task of multi-document summarization. |
| Tasks | Document Summarization, Multi-Document Summarization, Sentence Embeddings |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.12231v1 |
| https://arxiv.org/pdf/1909.12231v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-create-sentence-semantic-relation |
| Repo | |
| Framework | |
Effective Scheduling Function Design in SDN through Deep Reinforcement Learning
| Title | Effective Scheduling Function Design in SDN through Deep Reinforcement Learning |
| Authors | Huang Victoria, Chen Gang, Fu Qiang |
| Abstract | Recent research on Software-Defined Networking (SDN) strongly promotes the adoption of distributed controller architectures. To achieve high network performance, designing a scheduling function (SF) to properly dispatch requests from each switch to suitable controllers becomes critical. However, existing literature tends to design the SF targeted at specific network settings. In this paper, a reinforcement-learning-based (RL) approach is proposed with the aim to automatically learn a general, effective, and efficient SF. In particular, a new dispatching system is introduced in which the SF is represented as a neural network that determines the priority of each controller. Based on the priorities, a controller is selected using our proposed probability selection scheme to balance the trade-off between exploration and exploitation during learning. In order to train a general SF, we first formulate the scheduling function design problem as an RL problem. Then a new training approach is developed based on a state-of-the-art deep RL algorithm. Our simulation results show that our RL approach can rapidly design (or learn) SFs with optimal performance. Apart from that, the trained SF can generalize well and outperforms commonly used scheduling heuristics under various network settings. |
| Tasks | |
| Published | 2019-04-12 |
| URL | http://arxiv.org/abs/1904.06039v1 |
| http://arxiv.org/pdf/1904.06039v1.pdf | |
| PWC | https://paperswithcode.com/paper/effective-scheduling-function-design-in-sdn |
| Repo | |
| Framework | |
To regulate or not: a social dynamics analysis of the race for AI supremacy
| Title | To regulate or not: a social dynamics analysis of the race for AI supremacy |
| Authors | The Anh Han, Luis Moniz Pereira, Francisco C. Santos, Tom Lenaerts |
| Abstract | Rapid technological advancements in AI as well as the growing deployment of intelligent technologies in new application domains are currently driving the competition between businesses, nations and regions. This race for technological supremacy creates a complex ecology of choices that may lead to negative consequences, in particular, when ethical and safety procedures are underestimated or even ignored. As a consequence, different actors are urging to consider both the normative and social impact of these technological advancements. As there is no easy access to data describing this AI race, theoretical models are necessary to understand its dynamics, allowing for the identification of when, how and which procedures need to be put in place to favour outcomes beneficial for all. We show that, next to the risks of setbacks and being reprimanded for unsafe behaviour, the time-scale in which AI supremacy can be achieved plays a crucial role. When this supremacy can be achieved in a short term, those who completely ignore the safety precautions are bound to win the race but at a cost to society, apparently requiring regulatory actions. Our analysis reveals that blindly imposing regulations may not have anticipated effect as only for specific conditions a dilemma arises between what individually preferred and globally beneficial. Similar observations can be made for the long-term development case. Yet different from the short term situation, certain conditions require the promotion of risk-taking as opposed to compliance to safety regulations in order to improve social welfare. These results remain robust when two or several actors are involved in the race and when collective rather than individual setbacks are produced by risk-taking behaviour. When defining codes of conduct and regulatory policies for AI, a clear understanding about the time-scale of the race is required. |
| Tasks | |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.12393v2 |
| https://arxiv.org/pdf/1907.12393v2.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-the-safety-and-surveillance-of-the |
| Repo | |
| Framework | |
