Multilayered artificial neural networks (ANN) have found widespread utility in classification and recognition applications. The scale and complexity of such networks together with the inadequacies of general purpose computing platforms have led to a significant interest in the development of efficient hardware implementations. In this work, we focus on designing energy efficient on-chip storage for the synaptic weights. In order to minimize the power consumption of typical digital CMOS implementations of such large-scale networks, the digital neurons could be operated reliably at scaled voltages by reducing the clock frequency. On the contrary, the on-chip synaptic storage designed using a conventional 6T SRAM is susceptible to bitcell failures at reduced voltages. However, the intrinsic error resiliency of NNs to small synaptic weight perturbations enables us to scale the operating voltage of the 6TSRAM. Our analysis on a widely used digit recognition dataset indicates that the voltage can be scaled by 200mV from the nominal operating voltage (950mV) for practically no loss (less than 0.5%) in accuracy (22nm predictive technology). Scaling beyond that causes substantial performance degradation owing to increased probability of failures in the MSBs of the synaptic weights. We, therefore propose a significance driven hybrid 8T-6T SRAM, wherein the sensitive MSBs are stored in 8T bitcells that are robust at scaled voltages due to decoupled read and write paths. In an effort to further minimize the area penalty, we present a synaptic-sensitivity driven hybrid memory architecture consisting of multiple 8T-6T SRAM banks. Our circuit to system-level simulation framework shows that the proposed synaptic-sensitivity driven architecture provides a 30.91% reduction in the memory access power with a 10.41% area overhead, for less than 1% loss in the classification accuracy.
Systems based on automatic speech recognition (ASR) technology can provide important functionality in computer assisted language learning applications. This is a young but growing area of research motivated by the large number of students studying foreign languages. Here we propose a Hidden Markov Model (HMM)-based method to detect mispronunciations. Exploiting the specific dialog scripting employed in language learning software, HMMs are trained for different pronunciations. New adaptive features have been developed and obtained through an adaptive warping of the frequency scale prior to computing the cepstral coefficients. The optimization criterion used for the warping function is to maximize separation of two major groups of pronunciations (native and non-native) in terms of classification rate. Experimental results show that the adaptive frequency scale yields a better coefficient representation leading to higher classification rates in comparison with conventional HMMs using Mel-frequency cepstral coefficients.
For semi-supervised techniques to be applied safely in practice we at least want methods to outperform their supervised counterparts. We study this question for classification using the well-known quadratic surrogate loss function. Using a projection of the supervised estimate onto a set of constraints imposed by the unlabeled data, we find we can safely improve over the supervised solution in terms of this quadratic loss. Unlike other approaches to semi-supervised learning, the procedure does not rely on assumptions that are not intrinsic to the classifier at hand. It is theoretically demonstrated that, measured on the labeled and unlabeled training data, this semi-supervised procedure never gives a lower quadratic loss than the supervised alternative. To our knowledge this is the first approach that offers such strong, albeit conservative, guarantees for improvement over the supervised solution. The characteristics of our approach are explicated using benchmark datasets to further understand the similarities and differences between the quadratic loss criterion used in the theoretical results and the classification accuracy often considered in practice.
Objective: To treat patients with vascular mild cognitive impairment (VMCI) using TCM, it is necessary to classify the patients into TCM syndrome types and to apply different treatments to different types. We investigate how to properly carry out the classification using a novel data-driven method known as latent tree analysis. Method: A cross-sectional survey on VMCI was carried out in several regions in northern China from 2008 to 2011, which resulted in a data set that involves 803 patients and 93 symptoms. Latent tree analysis was performed on the data to reveal symptom co-occurrence patterns, and the patients were partitioned into clusters in multiple ways based on the patterns. The patient clusters were matched up with syndrome types, and population statistics of the clusters are used to quantify the syndrome types and to establish classification rules. Results: Eight syndrome types are identified: Qi Deficiency, Qi Stagnation, Blood Deficiency, Blood Stasis, Phlegm-Dampness, Fire-Heat, Yang Deficiency, and Yin Deficiency. The prevalence and symptom occurrence characteristics of each syndrome type are determined. Quantitative classification rules are established for determining whether a patient belongs to each of the syndrome types. Conclusions: A solution for the TCM syndrome classification problem associated with VMCI is established based on the latent tree analysis of unlabeled symptom survey data. The results can be used as a reference in clinic practice to improve the quality of syndrome differentiation and to reduce diagnosis variances across physicians. They can also be used for patient selection in research projects aimed at finding biomarkers for the syndrome types and in randomized control trials aimed at determining the efficacy of TCM treatments of VMCI.
One of the challenges in modeling cognitive events from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intra-subject differences, as well as to inherent noise associated with such data. Herein, we propose a novel approach for learning such representations from multi-channel EEG time-series, and demonstrate its advantages in the context of mental load classification task. First, we transform EEG activities into a sequence of topology-preserving multi-spectral images, as opposed to standard EEG analysis techniques that ignore such spatial information. Next, we train a deep recurrent-convolutional network inspired by state-of-the-art video classification to learn robust representations from the sequence of images. The proposed approach is designed to preserve the spatial, spectral, and temporal structure of EEG which leads to finding features that are less sensitive to variations and distortions within each dimension. Empirical evaluation on the cognitive load classification task demonstrated significant improvements in classification accuracy over current state-of-the-art approaches in this field.
For most deep learning algorithms training is notoriously time consuming. Since most of the computation in training neural networks is typically spent on floating point multiplications, we investigate an approach to training that eliminates the need for most of these. Our method consists of two parts: First we stochastically binarize weights to convert multiplications involved in computing hidden states to sign changes. Second, while back-propagating error derivatives, in addition to binarizing the weights, we quantize the representations at each layer to convert the remaining multiplications into binary shifts. Experimental results across 3 popular datasets (MNIST, CIFAR10, SVHN) show that this approach not only does not hurt classification performance but can result in even better performance than standard stochastic gradient descent training, paving the way to fast, hardware-friendly training of neural networks.
Objective: The efficacy of traditional Chinese medicine (TCM) treatments for Western medicine (WM) diseases relies heavily on the proper classification of patients into TCM syndrome types. We develop a data-driven method for solving the classification problem, where syndrome types are identified and quantified based on patterns detected in unlabeled symptom survey data. Method: Latent class analysis (LCA) has been applied in WM research to solve a similar problem, i.e., to identify subtypes of a patient population in the absence of a gold standard. A widely known weakness of LCA is that it makes an unrealistically strong independence assumption. We relax the assumption by first detecting symptom co-occurrence patterns from survey data and use those patterns instead of the symptoms as features for LCA. Results: The result of the investigation is a six-step method: Data collection, symptom co-occurrence pattern discovery, pattern interpretation, syndrome identification, syndrome type identification, and syndrome type classification. A software package called Lantern is developed to support the application of the method. The method is illustrated using a data set on Vascular Mild Cognitive Impairment (VMCI). Conclusions: A data-driven method for TCM syndrome identification and classification is presented. The method can be used to answer the following questions about a Western medicine disease: What TCM syndrome types are there among the patients with the disease? What is the prevalence of each syndrome type? What are the statistical characteristics of each syndrome type in terms of occurrence of symptoms? How can we determine the syndrome type(s) of a patient?
Graph model is emerging as a very effective tool for learning the complex structures and relationships hidden in data. Generally, the critical purpose of graph-oriented learning algorithms is to construct an informative graph for image clustering and classification tasks. In addition to the classical $K$-nearest-neighbor and $r$-neighborhood methods for graph construction, $l_1$-graph and its variants are emerging methods for finding the neighboring samples of a center datum, where the corresponding ingoing edge weights are simultaneously derived by the sparse reconstruction coefficients of the remaining samples. However, the pair-wise links of $l_1$-graph are not capable of capturing the high order relationships between the center datum and its prominent data in sparse reconstruction. Meanwhile, from the perspective of variable selection, the $l_1$ norm sparse constraint, regarded as a LASSO model, tends to select only one datum from a group of data that are highly correlated and ignore the others. To simultaneously cope with these drawbacks, we propose a new elastic net hypergraph learning model, which consists of two steps. In the first step, the Robust Matrix Elastic Net model is constructed to find the canonically related samples in a somewhat greedy way, achieving the grouping effect by adding the $l_2$ penalty to the $l_1$ constraint. In the second step, hypergraph is used to represent the high order relationships between each datum and its prominent samples by regarding them as a hyperedge. Subsequently, hypergraph Laplacian matrix is constructed for further analysis. New hypergraph learning algorithms, including unsupervised clustering and multi-class semi-supervised classification, are then derived. Extensive experiments on face and handwriting databases demonstrate the effectiveness of the proposed method.
The principal component analysis network (PCANet), which is one of the recently proposed deep learning architectures, achieves the state-of-the-art classification accuracy in various databases. However, the explanation of the PCANet is lacked. In this paper, we try to explain why PCANet works well from energy perspective point of view based on a set of experiments. The impact of various parameters on the error rate of PCANet is analyzed in depth. It was found that this error rate is correlated with the logarithm of energy of image. The proposed energy explanation approach can be used as a testing method for checking if every step of the constructed networks is necessary.
Although recent advances in regional Convolutional Neural Networks (CNNs) enable them to outperform conventional techniques on standard object detection and classification tasks, their response time is still slow for real-time performance. To address this issue, we propose a method for region proposal as an alternative to selective search, which is used in current state-of-the art object detection algorithms. We evaluate our Keypoint Density-based Region Proposal (KDRP) approach and show that it speeds up detection and classification on fine-grained tasks by 100% versus the existing selective search region proposal technique without compromising classification accuracy. KDRP makes the application of CNNs to real-time detection and classification feasible.
We consider the problem of learning general-purpose, paraphrastic sentence embeddings based on supervision from the Paraphrase Database (Ganitkevitch et al., 2013). We compare six compositional architectures, evaluating them on annotated textual similarity datasets drawn both from the same distribution as the training data and from a wide range of other domains. We find that the most complex architectures, such as long short-term memory (LSTM) recurrent neural networks, perform best on the in-domain data. However, in out-of-domain scenarios, simple architectures such as word averaging vastly outperform LSTMs. Our simplest averaging model is even competitive with systems tuned for the particular tasks while also being extremely efficient and easy to use. In order to better understand how these architectures compare, we conduct further experiments on three supervised NLP tasks: sentence similarity, entailment, and sentiment classification. We again find that the word averaging models perform well for sentence similarity and entailment, outperforming LSTMs. However, on sentiment classification, we find that the LSTM performs very strongly-even recording new state-of-the-art performance on the Stanford Sentiment Treebank. We then demonstrate how to combine our pretrained sentence embeddings with these supervised tasks, using them both as a prior and as a black box feature extractor. This leads to performance rivaling the state of the art on the SICK similarity and entailment tasks. We release all of our resources to the research community with the hope that they can serve as the new baseline for further work on universal sentence embeddings.
Unsupervised methods have proven effective for discriminative tasks in a single-modality scenario. In this paper, we present a multimodal framework for learning sparse representations that can capture semantic correlation between modalities. The framework can model relationships at a higher level by forcing the shared sparse representation. In particular, we propose the use of joint dictionary learning technique for sparse coding and formulate the joint representation for concision, cross-modal representations (in case of a missing modality), and union of the cross-modal representations. Given the accelerated growth of multimodal data posted on the Web such as YouTube, Wikipedia, and Twitter, learning good multimodal features is becoming increasingly important. We show that the shared representations enabled by our framework substantially improve the classification performance under both unimodal and multimodal settings. We further show how deep architectures built on the proposed framework are effective for the case of highly nonlinear correlations between modalities. The effectiveness of our approach is demonstrated experimentally in image denoising, multimedia event detection and retrieval on the TRECVID dataset (audio-video), category classification on the Wikipedia dataset (image-text), and sentiment classification on PhotoTweet (image-text).
Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been difficult for these to compete with modern classification algorithms in performance and even in feature extraction. In this work, we propose a novel approach explicitly designed to address a number of subtle yet important issues which have stymied earlier DML algorithms. It maintains an explicit model of the distributions of the different classes in representation space. It then employs this knowledge to adaptively assess similarity, and achieve local discrimination by penalizing class distribution overlap. We demonstrate the effectiveness of this idea on several tasks. Our approach achieves state-of-the-art classification results on a number of fine-grained visual recognition datasets, surpassing the standard softmax classifier and outperforming triplet loss by a relative margin of 30-40%. In terms of computational performance, it alleviates training inefficiencies in the traditional triplet loss, reaching the same error in 5-30 times fewer iterations. Beyond classification, we further validate the saliency of the learnt representations via their attribute concentration and hierarchy recovery properties, achieving 10-25% relative gains on the softmax classifier and 25-50% on triplet loss in these tasks.
We present improved methods of using structured SVMs in a large-scale hierarchical classification problem, that is when labels are leaves, or sets of leaves, in a tree or a DAG. We examine the need to normalize both the regularization and the margin and show how doing so significantly improves performance, including allowing achieving state-of-the-art results where unnormalized structured SVMs do not perform better than flat models. We also describe a further extension of hierarchical SVMs that highlight the connection between hierarchical SVMs and matrix factorization models.
Quality assurance in production line demands reliable weld joints. Human made errors is a major cause of faulty production. Promptly Identifying errors in the weld while welding is in progress will decrease the post inspection cost spent on the welding process. Electrical parameters generated during welding, could able to characterize the process efficiently. Parameter values are collected using high speed data acquisition system. Time series analysis tasks such as filtering, pattern recognition etc. are performed over the collected data. Filtering removes the unwanted noisy signal components and pattern recognition task segregate error patterns in the time series based upon similarity, which is performed by Self Organized mapping clustering algorithm. Welder quality is thus compared by detecting and counting number of error patterns appeared in his parametric time series. Moreover, Self Organized mapping algorithm provides the database in which patterns are segregated into two classes either desirable or undesirable. Database thus generated is used to train the classification algorithms, and thereby automating the real time error detection task. Multi Layer Perceptron and Radial basis function are the two classification algorithms used, and their performance has been compared based on metrics such as specificity, sensitivity, accuracy and time required in training.
Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser. Previous research usually makes use of one kind of discourse framework such as PDTB or RST to improve the classification performance on discourse relations. Actually, under different discourse annotation frameworks, there exist multiple corpora which have internal connections. To exploit the combination of different discourse corpora, we design related discourse classification tasks specific to a corpus, and propose a novel Convolutional Neural Network embedded multi-task learning system to synthesize these tasks by learning both unique and shared representations for each task. The experimental results on the PDTB implicit discourse relation classification task demonstrate that our model achieves significant gains over baseline systems.
A variety of real-world tasks involve the classification of images into pre-determined categories. Designing image classification algorithms that exhibit robustness to acquisition noise and image distortions, particularly when the available training data are insufficient to learn accurate models, is a significant challenge. This dissertation explores the development of discriminative models for robust image classification that exploit underlying signal structure, via probabilistic graphical models and sparse signal representations. Probabilistic graphical models are widely used in many applications to approximate high-dimensional data in a reduced complexity set-up. Learning graphical structures to approximate probability distributions is an area of active research. Recent work has focused on learning graphs in a discriminative manner with the goal of minimizing classification error. In the first part of the dissertation, we develop a discriminative learning framework that exploits the complementary yet correlated information offered by multiple representations (or projections) of a given signal/image. Specifically, we propose a discriminative tree-based scheme for feature fusion by explicitly learning the conditional correlations among such multiple projections in an iterative manner. Experiments reveal the robustness of the resulting graphical model classifier to training insufficiency.
We introduce a batched lazy algorithm for supervised classification using decision trees. It avoids unnecessary visits to irrelevant nodes when it is used to make predictions with either eagerly or lazily trained decision trees. A set of experiments demonstrate that the proposed algorithm can outperform both the conventional and lazy decision tree algorithms in terms of computation time as well as memory consumption, without compromising accuracy.
This paper proposes a new probabilistic non-extensive entropy feature for texture characterization, based on a Gaussian information measure. The highlights of the new entropy are that it is bounded by finite limits and that it is non additive in nature. The non additive property of the proposed entropy makes it useful for the representation of information content in the non-extensive systems containing some degree of regularity or correlation. The effectiveness of the proposed entropy in representing the correlated random variables is demonstrated by applying it for the texture classification problem since textures found in nature are random and at the same time contain some degree of correlation or regularity at some scale. The gray level co-occurrence probabilities (GLCP) are used for computing the entropy function. The experimental results indicate high degree of the classification accuracy. The performance of the new entropy function is found superior to other forms of entropy such as Shannon, Renyi, Tsallis and Pal and Pal entropies on comparison. Using the feature based polar interaction maps (FBIM) the proposed entropy is shown to be the best measure among the entropies compared for representing the correlated textures.
The focus of this article is on the detection and classification of patterns based on groupoids. The approach hinges on descriptive proximity of points in a set based on the neighborliness property. This approach lends support to image analysis and understanding and in studying nearness of image segments. A practical application of the approach is in terms of the analysis of natural images for pattern identification and classification.