PyTorchKR Papers

최신 논문

총 2,063편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1906.07319공식 코드 · Papers with Code

Deep Xi as a Front-End for Robust Automatic Speech Recognition

Current front-ends for robust automatic speech recognition(ASR) include masking- and mapping-based deep learning approaches to speech enhancement. A recently proposed deep learning approach toa prioriSNR estimation, called DeepXi, was able to produce enhanced speech at a higher quality and intelligibility than current masking- and mapping-based approaches. Motivated by this, we investigate Deep Xi as a front-end for robust ASR. Deep Xi is evaluated using real-world non-stationary and coloured noise sources at multiple SNR levels. Our experimental investigation shows that DeepXi as a front-end is able to produce a lower word error rate than recent masking- and mapping-based deep learning front-ends. The results presented in this work show that Deep Xi is a viable front-end, and is able to significantly increase the robustness of an ASR system. Availability: Deep Xi is available at:https://github.com/anicolson/DeepXi

arXiv:2012.01141공식 코드 · Papers with Code

Algebraically-Informed Deep Networks (AIDN): A Deep Learning Approach to Represent Algebraic Structures

One of the central problems in the interface of deep learning and mathematics is that of building learning systems that can automatically uncover underlying mathematical laws from observed data. In this work, we make one step towards building a bridge between algebraic structures and deep learning, and introduce \textbf{AIDN}, \textit{Algebraically-Informed Deep Networks}. \textbf{AIDN} is a deep learning algorithm to represent any finitely-presented algebraic object with a set of deep neural networks. The deep networks obtained via \textbf{AIDN} are \textit{algebraically-informed} in the sense that they satisfy the algebraic relations of the presentation of the algebraic structure that serves as the input to the algorithm. Our proposed network can robustly compute linear and non-linear representations of most finitely-presented algebraic structures such as groups, associative algebras, and Lie algebras. We evaluate our proposed approach and demonstrate its applicability to algebraic and geometric objects that are significant in low-dimensional topology. In particular, we study solutions for the Yang-Baxter equations and their applications on braid groups. Further, we study the representations of the Temperley-Lieb algebra. Finally, we show, using the Reshetikhin-Turaev construction, how our proposed deep learning approach can be utilized to construct new link invariants. We believe the proposed approach would tread a path toward a promising future research in deep learning applied to algebraic and geometric structures.

arXiv:2012.00900공식 코드 · Papers with Code

Deploying deep learning in OpenFOAM with TensorFlow

We outline the development of a data science module within OpenFOAM which allows for the in-situ deployment of trained deep learning architectures for general-purpose predictive tasks. This module is constructed with the TensorFlow C API and is integrated into OpenFOAM as an application that may be linked at run time. Notably, our formulation precludes any restrictions related to the type of neural network architecture (i.e., convolutional, fully-connected, etc.). This allows for potential studies of complicated neural architectures for practical CFD problems. In addition, the proposed module outlines a path towards an open-source, unified and transparent framework for computational fluid dynamics and machine learning.

arXiv:2012.00634공식 코드 · Papers with Code

Deep dynamic modeling with just two time points: Can we still allow for individual trajectories?

Longitudinal biomedical data are often characterized by a sparse time grid and individual-specific development patterns. Specifically, in epidemiological cohort studies and clinical registries we are facing the question of what can be learned from the data in an early phase of the study, when only a baseline characterization and one follow-up measurement are available. Inspired by recent advances that allow to combine deep learning with dynamic modeling, we investigate whether such approaches can be useful for uncovering complex structure, in particular for an extreme small data setting with only two observations time points for each individual. Irregular spacing in time could then be used to gain more information on individual dynamics by leveraging similarity of individuals. We provide a brief overview of how variational autoencoders (VAEs), as a deep learning approach, can be linked to ordinary differential equations (ODEs) for dynamic modeling, and then specifically investigate the feasibility of such an approach that infers individual-specific latent trajectories by including regularity assumptions and individuals' similarity. We also provide a description of this deep learning approach as a filtering task to give a statistical perspective. Using simulated data, we show to what extent the approach can recover individual trajectories from ODE systems with two and four unknown parameters and infer groups of individuals with similar trajectories, and where it breaks down. The results show that such dynamic deep learning approaches can be useful even in extreme small data settings, but need to be carefully adapted.

arXiv:2011.14439공식 코드 · Papers with Code

Scaling Down Deep Learning with MNIST-1D

Although deep learning models have taken on commercial and political relevance, key aspects of their training and operation remain poorly understood. This has sparked interest in science of deep learning projects, many of which require large amounts of time, money, and electricity. But how much of this research really needs to occur at scale? In this paper, we introduce MNIST-1D: a minimalist, procedurally generated, low-memory, and low-compute alternative to classic deep learning benchmarks. Although the dimensionality of MNIST-1D is only 40 and its default training set size only 4000, MNIST-1D can be used to study inductive biases of different deep architectures, find lottery tickets, observe deep double descent, metalearn an activation function, and demonstrate guillotine regularization in self-supervised learning. All these experiments can be conducted on a GPU or often even on a CPU within minutes, allowing for fast prototyping, educational use cases, and cutting-edge research on a low budget.

arXiv:2011.13062공식 코드 · Papers with Code

Can GAN originate new electronic dance music genres? -- Generating novel rhythm patterns using GAN with Genre Ambiguity Loss

Since the introduction of deep learning, researchers have proposed content generation systems using deep learning and proved that they are competent to generate convincing content and artistic output, including music. However, one can argue that these deep learning-based systems imitate and reproduce the patterns inherent within what humans have created, instead of generating something new and creative. This paper focuses on music generation, especially rhythm patterns of electronic dance music, and discusses if we can use deep learning to generate novel rhythms, interesting patterns not found in the training dataset. We extend the framework of Generative Adversarial Networks(GAN) and encourage it to diverge from the dataset's inherent distributions by adding additional classifiers to the framework. The paper shows that our proposed GAN can generate rhythm patterns that sound like music rhythms but do not belong to any genres in the training dataset. The source code, generated rhythm patterns, and a supplementary plugin software for a popular Digital Audio Workstation software are available on our website.

arXiv:2011.12737공식 코드 · Papers with Code

Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs

Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task. In this work, we propose exploiting Latent Geometry Graphs (LGGs) to represent the latent spaces of trained DNN architectures. Such graphs are obtained by connecting samples that yield similar latent representations at a given layer of the considered DNN. We then obtain a generalization score by looking at how strongly connected are samples of distinct classes in LGGs. This score allowed us to rank 3rd on the NeurIPS 2020 Predicting Generalization in Deep Learning (PGDL) competition.

arXiv:2011.11728공식 코드 · Papers with Code

End-to-End Framework for Efficient Deep Learning Using Metasurfaces Optics

Deep learning using Convolutional Neural Networks (CNNs) has been shown to significantly out-performed many conventional vision algorithms. Despite efforts to increase the CNN efficiency both algorithmically and with specialized hardware, deep learning remains difficult to deploy in resource-constrained environments. In this paper, we propose an end-to-end framework to explore optically compute the CNNs in free-space, much like a computational camera. Compared to existing free-space optics-based approaches which are limited to processing single-channel (i.e., grayscale) inputs, we propose the first general approach, based on nanoscale meta-surface optics, that can process RGB data directly from the natural scenes. Our system achieves up to an order of magnitude energy saving, simplifies the sensor design, all the while sacrificing little network accuracy.

arXiv:2011.10834공식 코드 · Papers with Code

The complementarity of a diverse range of deep learning features extracted from video content for video recommendation

Following the popularisation of media streaming, a number of video streaming services are continuously buying new video content to mine the potential profit from them. As such, the newly added content has to be handled well to be recommended to suitable users. In this paper, we address the new item cold-start problem by exploring the potential of various deep learning features to provide video recommendations. The deep learning features investigated include features that capture the visual-appearance, audio and motion information from video content. We also explore different fusion methods to evaluate how well these feature modalities can be combined to fully exploit the complementary information captured by them. Experiments on a real-world video dataset for movie recommendations show that deep learning features outperform hand-crafted features. In particular, recommendations generated with deep learning audio features and action-centric deep learning features are superior to MFCC and state-of-the-art iDT features. In addition, the combination of various deep learning features with hand-crafted features and textual metadata yields significant improvement in recommendations compared to combining only the former.

arXiv:2011.10577공식 코드 · Papers with Code

Deep learning insights into cosmological structure formation

The evolution of linear initial conditions present in the early universe into extended halos of dark matter at late times can be computed using cosmological simulations. However, a theoretical understanding of this complex process remains elusive; in particular, the role of anisotropic information in the initial conditions in establishing the final mass of dark matter halos remains a long-standing puzzle. Here, we build a deep learning framework to investigate this question. We train a three-dimensional convolutional neural network (CNN) to predict the mass of dark matter halos from the initial conditions, and quantify in full generality the amounts of information in the isotropic and anisotropic aspects of the initial density field about final halo masses. We find that anisotropies add a small, albeit statistically significant amount of information over that contained within spherical averages of the density field about final halo mass. However, the overall scatter in the final mass predictions does not change qualitatively with this additional information, only decreasing from 0.9 dex to 0.7 dex. Given such a small improvement, our results demonstrate that isotropic aspects of the initial density field essentially saturate the relevant information about final halo mass. Therefore, instead of searching for information directly encoded in initial conditions anisotropies, a more promising route to accurate, fast halo mass predictions is to add approximate dynamical information based e.g. on perturbation theory. More broadly, our results indicate that deep learning frameworks can provide a powerful tool for extracting physical insight into cosmological structure formation.

arXiv:2011.10616공식 코드 · Papers with Code

Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems

How can we learn a dynamical system to make forecasts, when some variables are unobserved? For instance, in COVID-19, we want to forecast the number of infected and death cases but we do not know the count of susceptible and exposed people. While mechanics compartment models are widely used in epidemic modeling, data-driven models are emerging for disease forecasting. We first formalize the learning of physics-based models as AutoODE, which leverages automatic differentiation to estimate the model parameters. Through a benchmark study on COVID-19 forecasting, we notice that physics-based mechanistic models significantly outperform deep learning. Our method obtains a 57.4% reduction in mean absolute errors for 7-day ahead COVID-19 forecasting compared with the best deep learning competitor. Such performance differences highlight the generalization problem in dynamical system learning due to distribution shift. We identify two scenarios where distribution shift can occur: changes in data domain and changes in parameter domain (system dynamics). Through systematic experiments on several dynamical systems, we found that deep learning models fail to forecast well under both scenarios. While much research on distribution shift has focused on changes in the data domain, our work calls attention to rethink generalization for learning dynamical systems.

arXiv:2011.10704공식 코드 · Papers with Code

Neural Group Testing to Accelerate Deep Learning

Recent advances in deep learning have made the use of large, deep neural networks with tens of millions of parameters. The sheer size of these networks imposes a challenging computational burden during inference. Existing work focuses primarily on accelerating each forward pass of a neural network. Inspired by the group testing strategy for efficient disease testing, we propose neural group testing, which accelerates by testing a group of samples in one forward pass. Groups of samples that test negative are ruled out. If a group tests positive, samples in that group are then retested adaptively. A key challenge of neural group testing is to modify a deep neural network so that it could test multiple samples in one forward pass. We propose three designs to achieve this without introducing any new parameters and evaluate their performances. We applied neural group testing in an image moderation task to detect rare but inappropriate images. We found that neural group testing can group up to 16 images in one forward pass and reduce the overall computation cost by over 73% while improving detection performance.

arXiv:2011.10697공식 코드 · Papers with Code

Aerial Height Prediction and Refinement Neural Networks with Semantic and Geometric Guidance

Deep learning provides a powerful new approach to many computer vision tasks. Height prediction from aerial images is one of those tasks that benefited greatly from the deployment of deep learning which replaced old multi-view geometry techniques. This letter proposes a two-stage approach, where first a multi-task neural network is used to predict the height map resulting from a single RGB aerial input image. We also include a second refinement step, where a denoising autoencoder is used to produce higher quality height maps. Experiments on two publicly available datasets show that our method is capable of producing state-of-the-art results. Code is available at https://github.com/melhousni/DSMNet.

arXiv:2011.09769공식 코드 · Papers with Code

Data-Driven Robust Optimization using Unsupervised Deep Learning

Robust optimization has been established as a leading methodology to approach decision problems under uncertainty. To derive a robust optimization model, a central ingredient is to identify a suitable model for uncertainty, which is called the uncertainty set. An ongoing challenge in the recent literature is to derive uncertainty sets from given historical data that result in solutions that are robust regarding future scenarios. In this paper we use an unsupervised deep learning method to learn and extract hidden structures from data, leading to non-convex uncertainty sets and better robust solutions. We prove that most of the classical uncertainty classes are special cases of our derived sets and that optimizing over them is strongly NP-hard. Nevertheless, we show that the trained neural networks can be integrated into a robust optimization model by formulating the adversarial problem as a convex quadratic mixed-integer program. This allows us to derive robust solutions through an iterative scenario generation process. In our computational experiments, we compare this approach to a similar approach using kernel-based support vector clustering. We find that uncertainty sets derived by the unsupervised deep learning method find a better description of data and lead to robust solutions that outperform the comparison method both with respect to objective value and feasibility.

arXiv:2011.08461공식 코드 · Papers with Code

Deep Learning Framework From Scratch Using Numpy

This work is a rigorous development of a complete and general-purpose deep learning framework from the ground up. The fundamental components of deep learning - automatic differentiation and gradient methods of optimizing multivariable scalar functions - are developed from elementary calculus and implemented in a sensible object-oriented approach using only Python and the Numpy library. Demonstrations of solved problems using the framework, named ArrayFlow, include a computer vision classification task, solving for the shape of a catenary, and a 2nd order differential equation.

arXiv:2011.08071공식 코드 · Papers with Code

JNLP Team: Deep Learning for Legal Processing in COLIEE 2020

We propose deep learning based methods for automatic systems of legal retrieval and legal question-answering in COLIEE 2020. These systems are all characterized by being pre-trained on large amounts of data before being finetuned for the specified tasks. This approach helps to overcome the data scarcity and achieve good performance, thus can be useful for tackling related problems in information retrieval, and decision support in the legal domain. Besides, the approach can be explored to deal with other domain specific problems.

arXiv:2011.07439공식 코드 · Papers with Code

Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee

Sparse deep learning aims to address the challenge of huge storage consumption by deep neural networks, and to recover the sparse structure of target functions. Although tremendous empirical successes have been achieved, most sparse deep learning algorithms are lacking of theoretical support. On the other hand, another line of works have proposed theoretical frameworks that are computationally infeasible. In this paper, we train sparse deep neural networks with a fully Bayesian treatment under spike-and-slab priors, and develop a set of computationally efficient variational inferences via continuous relaxation of Bernoulli distribution. The variational posterior contraction rate is provided, which justifies the consistency of the proposed variational Bayes method. Notably, our empirical results demonstrate that this variational procedure provides uncertainty quantification in terms of Bayesian predictive distribution and is also capable to accomplish consistent variable selection by training a sparse multi-layer neural network.

arXiv:2011.07280공식 코드 · Papers with Code

Sentiment Analysis for Sinhala Language using Deep Learning Techniques

Due to the high impact of the fast-evolving fields of machine learning and deep learning, Natural Language Processing (NLP) tasks have further obtained comprehensive performances for highly resourced languages such as English and Chinese. However Sinhala, which is an under-resourced language with a rich morphology, has not experienced these advancements. For sentiment analysis, there exists only two previous research with deep learning approaches, which focused only on document-level sentiment analysis for the binary case. They experimented with only three types of deep learning models. In contrast, this paper presents a much comprehensive study on the use of standard sequence models such as RNN, LSTM, Bi-LSTM, as well as more recent state-of-the-art models such as hierarchical attention hybrid neural networks, and capsule networks. Classification is done at document-level but with more granularity by considering POSITIVE, NEGATIVE, NEUTRAL, and CONFLICT classes. A data set of 15059 Sinhala news comments, annotated with these four classes and a corpus consists of 9.48 million tokens are publicly released. This is the largest sentiment annotated data set for Sinhala so far.

arXiv:2011.06796공식 코드 · Papers with Code

Wisdom of the Ensemble: Improving Consistency of Deep Learning Models

Deep learning classifiers are assisting humans in making decisions and hence the user's trust in these models is of paramount importance. Trust is often a function of constant behavior. From an AI model perspective it means given the same input the user would expect the same output, especially for correct outputs, or in other words consistently correct outputs. This paper studies a model behavior in the context of periodic retraining of deployed models where the outputs from successive generations of the models might not agree on the correct labels assigned to the same input. We formally define consistency and correct-consistency of a learning model. We prove that consistency and correct-consistency of an ensemble learner is not less than the average consistency and correct-consistency of individual learners and correct-consistency can be improved with a probability by combining learners with accuracy not less than the average accuracy of ensemble component learners. To validate the theory using three datasets and two state-of-the-art deep learning classifiers we also propose an efficient dynamic snapshot ensemble method and demonstrate its value.

arXiv:2011.03794공식 코드 · Papers with Code

Deep Learning Analysis and Age Prediction from Shoeprints

Human walking and gaits involve several complex body parts and are influenced by personality, mood, social and cultural traits, and aging. These factors are reflected in shoeprints, which in turn can be used to predict age, a problem not systematically addressed using any computational approach. We collected 100,000 shoeprints of subjects ranging from 7 to 80 years old and used the data to develop a deep learning end-to-end model ShoeNet to analyze age-related patterns and predict age. The model integrates various convolutional neural network models together using a skip mechanism to extract age-related features, especially in pressure and abrasion regions from pair-wise shoeprints. The results show that 40.23% of the subjects had prediction errors within 5-years of age and the prediction accuracy for gender classification reached 86.07%. Interestingly, the age-related features mostly reside in the asymmetric differences between left and right shoeprints. The analysis also reveals interesting age-related and gender-related patterns in the pressure distributions on shoeprints; in particular, the pressure forces spread from the middle of the toe toward outside regions over age with gender-specific variations on heel regions. Such statistics provide insight into new methods for forensic investigations, medical studies of gait-pattern disorders, biometrics, and sport studies.