PyTorchKR Papers

최신 논문

총 118편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1412.6598

Automatic Discovery and Optimization of Parts for Image Classification

Part-based representations have been shown to be very useful for image classification. Learning part-based models is often viewed as a two-stage problem. First, a collection of informative parts is discovered, using heuristics that promote part distinctiveness and diversity, and then classifiers are trained on the vector of part responses. In this paper we unify the two stages and learn the image classifiers and a set of shared parts jointly. We generate an initial pool of parts by randomly sampling part candidates and selecting a good subset using L1/L2 regularization. All steps are driven "directly" by the same objective namely the classification loss on a training set. This lets us do away with engineered heuristics. We also introduce the notion of "negative parts", intended as parts that are negatively correlated with one or more classes. Negative parts are complementary to the parts discovered by other methods, which look only for positive correlations.

arXiv:1511.02024

Towards a Better Understanding of Predict and Count Models

In a recent paper, Levy and Goldberg pointed out an interesting connection between prediction-based word embedding models and count models based on pointwise mutual information. Under certain conditions, they showed that both models end up optimizing equivalent objective functions. This paper explores this connection in more detail and lays out the factors leading to differences between these models. We find that the most relevant differences from an optimization perspective are (i) predict models work in a low dimensional space where embedding vectors can interact heavily; (ii) since predict models have fewer parameters, they are less prone to overfitting. Motivated by the insight of our analysis, we show how count models can be regularized in a principled manner and provide closed-form solutions for L1 and L2 regularization. Finally, we propose a new embedding model with a convex objective and the additional benefit of being intelligible.

arXiv:1512.05294

Feature Representation for ICU Mortality

Good predictors of ICU Mortality have the potential to identify high-risk patients earlier, improve ICU resource allocation, or create more accurate population-level risk models. Machine learning practitioners typically make choices about how to represent features in a particular model, but these choices are seldom evaluated quantitatively. This study compares the performance of different representations of clinical event data from MIMIC II in a logistic regression model to predict 36-hour ICU mortality. The most common representations are linear (normalized counts) and binary (yes/no). These, along with a new representation termed "hill", are compared using both L1 and L2 regularization. Results indicate that the introduced "hill" representation outperforms both the binary and linear representations, the hill representation thus has the potential to improve existing models of ICU mortality.

arXiv:1608.00250

On Regularization Parameter Estimation under Covariate Shift

This paper identifies a problem with the usual procedure for L2-regularization parameter estimation in a domain adaptation setting. In such a setting, there are differences between the distributions generating the training data (source domain) and the test data (target domain). The usual cross-validation procedure requires validation data, which can not be obtained from the unlabeled target data. The problem is that if one decides to use source validation data, the regularization parameter is underestimated. One possible solution is to scale the source validation data through importance weighting, but we show that this correction is not sufficient. We conclude the paper with an empirical analysis of the effect of several importance weight estimators on the estimation of the regularization parameter.

arXiv:1701.06106공식 코드 · Papers with Code

Neurogenesis-Inspired Dictionary Learning: Online Model Adaption in a Changing World

In this paper, we focus on online representation learning in non-stationary environments which may require continuous adaptation of model architecture. We propose a novel online dictionary-learning (sparse-coding) framework which incorporates the addition and deletion of hidden units (dictionary elements), and is inspired by the adult neurogenesis phenomenon in the dentate gyrus of the hippocampus, known to be associated with improved cognitive function and adaptation to new environments. In the online learning setting, where new input instances arrive sequentially in batches, the neuronal-birth is implemented by adding new units with random initial weights (random dictionary elements); the number of new units is determined by the current performance (representation error) of the dictionary, higher error causing an increase in the birth rate. Neuronal-death is implemented by imposing l1/l2-regularization (group sparsity) on the dictionary within the block-coordinate descent optimization at each iteration of our online alternating minimization scheme, which iterates between the code and dictionary updates. Finally, hidden unit connectivity adaptation is facilitated by introducing sparsity in dictionary elements. Our empirical evaluation on several real-life datasets (images and language) as well as on synthetic data demonstrates that the proposed approach can considerably outperform the state-of-art fixed-size (nonadaptive) online sparse coding of Mairal et al. (2009) in the presence of nonstationary data. Moreover, we identify certain properties of the data (e.g., sparse inputs with nearly non-overlapping supports) and of the model (e.g., dictionary sparsity) associated with such improvements.

arXiv:1703.05422

Large Scale Evolution of Convolutional Neural Networks Using Volunteer Computing

This work presents a new algorithm called evolutionary exploration of augmenting convolutional topologies (EXACT), which is capable of evolving the structure of convolutional neural networks (CNNs). EXACT is in part modeled after the neuroevolution of augmenting topologies (NEAT) algorithm, with notable exceptions to allow it to scale to large scale distributed computing environments and evolve networks with convolutional filters. In addition to multithreaded and MPI versions, EXACT has been implemented as part of a BOINC volunteer computing project, allowing large scale evolution. During a period of two months, over 4,500 volunteered computers on the Citizen Science Grid trained over 120,000 CNNs and evolved networks reaching 98.32% test data accuracy on the MNIST handwritten digits dataset. These results are even stronger as the backpropagation strategy used to train the CNNs was fairly rudimentary (ReLU units, L2 regularization and Nesterov momentum) and these were initial test runs done without refinement of the backpropagation hyperparameters. Further, the EXACT evolutionary strategy is independent of the method used to train the CNNs, so they could be further improved by advanced techniques like elastic distortions, pretraining and dropout. The evolved networks are also quite interesting, showing "organic" structures and significant differences from standard human designed architectures.

arXiv:1701.00573

Robust method for finding sparse solutions to linear inverse problems using an L2 regularization

We analyzed the performance of a biologically inspired algorithm called the Corrected Projections Algorithm (CPA) when a sparseness constraint is required to unambiguously reconstruct an observed signal using atoms from an overcomplete dictionary. By changing the geometry of the estimation problem, CPA gives an analytical expression for a binary variable that indicates the presence or absence of a dictionary atom using an L2 regularizer. The regularized solution can be implemented using an efficient real-time Kalman-filter type of algorithm. The smoother L2 regularization of CPA makes it very robust to noise, and CPA outperforms other methods in identifying known atoms in the presence of strong novel atoms in the signal.

arXiv:1704.06756

Convolutional Neural Networks for Facial Expression Recognition

We have developed convolutional neural networks (CNN) for a facial expression recognition task. The goal is to classify each facial image into one of the seven facial emotion categories considered in this study. We trained CNN models with different depth using gray-scale images. We developed our models in Torch and exploited Graphics Processing Unit (GPU) computation in order to expedite the training process. In addition to the networks performing based on raw pixel data, we employed a hybrid feature strategy by which we trained a novel CNN model with the combination of raw pixel data and Histogram of Oriented Gradients (HOG) features. To reduce the overfitting of the models, we utilized different techniques including dropout and batch normalization in addition to L2 regularization. We applied cross validation to determine the optimal hyper-parameters and evaluated the performance of the developed models by looking at their training histories. We also present the visualization of different layers of a network to show what features of a face can be learned by CNN models.

arXiv:1706.05350

L2 Regularization versus Batch and Weight Normalization

Batch Normalization is a commonly used trick to improve the training of deep neural networks. These neural networks use L2 regularization, also called weight decay, ostensibly to prevent overfitting. However, we show that L2 regularization has no regularizing effect when combined with normalization. Instead, regularization has an influence on the scale of weights, and thereby on the effective learning rate. We investigate this dependence, both in theory, and experimentally. We show that popular optimization methods such as ADAM only partially eliminate the influence of normalization on the learning rate. This leads to a discussion on other ways to mitigate this issue.

arXiv:1707.09920

Regularization techniques for fine-tuning in neural machine translation

We investigate techniques for supervised domain adaptation for neural machine translation where an existing model trained on a large out-of-domain dataset is adapted to a small in-domain dataset. In this scenario, overfitting is a major challenge. We investigate a number of techniques to reduce overfitting and improve transfer learning, including regularization techniques such as dropout and L2-regularization towards an out-of-domain prior. In addition, we introduce tuneout, a novel regularization technique inspired by dropout. We apply these techniques, alone and in combination, to neural machine translation, obtaining improvements on IWSLT datasets for English->German and English->Russian. We also investigate the amounts of in-domain training data needed for domain adaptation in NMT, and find a logarithmic relationship between the amount of training data and gain in BLEU score.

arXiv:1708.01009

Revisiting Activation Regularization for Language RNNs

Recurrent neural networks (RNNs) serve as a fundamental building block for many sequence tasks across natural language processing. Recent research has focused on recurrent dropout techniques or custom RNN cells in order to improve performance. Both of these can require substantial modifications to the machine learning model or to the underlying RNN configurations. We revisit traditional regularization techniques, specifically L2 regularization on RNN activations and slowness regularization over successive hidden states, to improve the performance of RNNs on the task of language modeling. Both of these techniques require minimal modification to existing RNN architectures and result in performance improvements comparable or superior to more complicated regularization techniques or custom cell architectures. These regularization techniques can be used without any modification on optimized LSTM implementations such as the NVIDIA cuDNN LSTM.

arXiv:1709.06262

Compressing Low Precision Deep Neural Networks Using Sparsity-Induced Regularization in Ternary Networks

A low precision deep neural network training technique for producing sparse, ternary neural networks is presented. The technique incorporates hard- ware implementation costs during training to achieve significant model compression for inference. Training involves three stages: network training using L2 regularization and a quantization threshold regularizer, quantization pruning, and finally retraining. Resulting networks achieve improved accuracy, reduced memory footprint and reduced computational complexity compared with conventional methods, on MNIST and CIFAR10 datasets. Our networks are up to 98% sparse and 5 & 11 times smaller than equivalent binary and ternary models, translating to significant resource and speed benefits for hardware implementations.

arXiv:1711.07328

Data Fusion on Motion and Magnetic Sensors embedded on Mobile Devices for the Identification of Activities of Daily Living

Several types of sensors have been available in off-the-shelf mobile devices, including motion, magnetic, vision, acoustic, and location sensors. This paper focuses on the fusion of the data acquired from motion and magnetic sensors, i.e., accelerometer, gyroscope and magnetometer sensors, for the recognition of Activities of Daily Living (ADL) using pattern recognition techniques. The system developed in this study includes data acquisition, data processing, data fusion, and artificial intelligence methods. Artificial Neural Networks (ANN) are included in artificial intelligence methods, which are used in this study for the recognition of ADL. The purpose of this study is the creation of a new method using ANN for the identification of ADL, comparing three types of ANN, in order to achieve results with a reliable accuracy. The best accuracy was obtained with Deep Learning, which, after the application of the L2 regularization and normalization techniques on the sensors data, reports an accuracy of 89.51%.

arXiv:1711.05865

Pricing Football Players using Neural Networks

We designed a multilayer perceptron neural network to predict the price of a football (soccer) player using data on more than 15,000 players from the football simulation video game FIFA 2017. The network was optimized by experimenting with different activation functions, number of neurons and layers, learning rate and its decay, Nesterov momentum based stochastic gradient descent, L2 regularization, and early stopping. Simultaneous exploration of various aspects of neural network training is performed and their trade-offs are investigated. Our final model achieves a top-5 accuracy of 87.2% among 119 pricing categories, and places any footballer within 6.32% of his actual price on average.

arXiv:1801.06792

Attentive Recurrent Tensor Model for Community Question Answering

A major challenge to the problem of community question answering is the lexical and semantic gap between the sentence representations. Some solutions to minimize this gap includes the introduction of extra parameters to deep models or augmenting the external handcrafted features. In this paper, we propose a novel attentive recurrent tensor network for solving the lexical and semantic gap in community question answering. We introduce token-level and phrase-level attention strategy that maps input sequences to the output using trainable parameters. Further, we use the tensor parameters to introduce a 3-way interaction between question, answer and external features in vector space. We introduce simplified tensor matrices with L2 regularization that results in smooth optimization during training. The proposed model achieves state-of-the-art performance on the task of answer sentence selection (TrecQA and WikiQA datasets) while outperforming the current state-of-the-art on the tasks of best answer selection (Yahoo! L4) and answer triggering task (WikiQA).

arXiv:1802.00003

Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Data

Unsupervised feature extractors are known to perform an efficient and discriminative representation of data. Insight into the mappings they perform and human ability to understand them, however, remain very limited. This is especially prominent when multilayer deep learning architectures are used. This paper demonstrates how to remove these bottlenecks within the architecture of Nonnegativity Constrained Autoencoder (NCSAE). It is shown that by using both L1 and L2 regularization that induce nonnegativity of weights, most of the weights in the network become constrained to be nonnegative thereby resulting into a more understandable structure with minute deterioration in classification accuracy. Also, this proposed approach extracts features that are more sparse and produces additional output layer sparsification. The method is analyzed for accuracy and feature interpretation on the MNIST data, the NORB normalized uniform object data, and the Reuters text categorization dataset.

arXiv:1707.07167

Attention-Based End-to-End Speech Recognition on Voice Search

Recently, there has been a growing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. In this paper, we explore the use of attention-based encoder-decoder model for Mandarin speech recognition on a voice search task. Previous attempts have shown that applying attention-based encoder-decoder to Mandarin speech recognition was quite difficult due to the logographic orthography of Mandarin, the large vocabulary and the conditional dependency of the attention model. In this paper, we use character embedding to deal with the large vocabulary. Several tricks are used for effective model training, including L2 regularization, Gaussian weight noise and frame skipping. We compare two attention mechanisms and use attention smoothing to cover long context in the attention model. Taken together, these tricks allow us to finally achieve a character error rate (CER) of 3.58% and a sentence error rate (SER) of 7.43% on the MiTV voice search dataset. While together with a trigram language model, CER and SER reach 2.81% and 5.77%, respectively.

arXiv:1802.07589공식 코드 · Papers with Code

Collaboratively Weighting Deep and Classic Representation via L2 Regularization for Image Classification

Deep convolutional neural networks provide a powerful feature learning capability for image classification. The deep image features can be utilized to deal with many image understanding tasks like image classification and object recognition. However, the robustness obtained in one dataset can be hardly reproduced in the other domain, which leads to inefficient models far from state-of-the-art. We propose a deep collaborative weight-based classification (DeepCWC) method to resolve this problem, by providing a novel option to fully take advantage of deep features in classic machine learning. It firstly performs the L2-norm based collaborative representation on the original images, as well as the deep features extracted by deep CNN models. Then, two distance vectors, obtained based on the pair of linear representations, are fused together via a novel collaborative weight. This collaborative weight enables deep and classic representations to weigh each other. We observed the complementarity between two representations in a series of experiments on 10 facial and object datasets. The proposed DeepCWC produces very promising classification results, and outperforms many other benchmark methods, especially the ones claimed for Fashion-MNIST. The code is going to be published in our public repository.