Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations. However, training CNNs relies heavily on the availability of exhaustive training data annotations, limiting significantly their deployment and scalability in many application scenarios. In this work, we introduce a generic unsupervised deep learning approach to training deep models without the need for any manual label supervision. Specifically, we progressively discover sample anchored/centred neighbourhoods to reason and learn the underlying class decision boundaries iteratively and accumulatively. Every single neighbourhood is specially formulated so that all the member samples can share the same unseen class labels at high probability for facilitating the extraction of class discriminative feature representations during training. Experiments on image classification show the performance advantages of the proposed method over the state-of-the-art unsupervised learning models on six benchmarks including both coarse-grained and fine-grained object image categorisation.
Distributed Acoustic Sensing (DAS) using fiber optic cables is a promising new technology for pipeline monitoring and protection. In this work, we applied and compared two approaches for event detection using DAS: Classic machine learning approach and the approach based on image processing and deep learning. Although with both approaches acceptable performance can be achieved, the preliminary results show that image based deep learning is more promising approach, offering six times lower event detection delay and twelve times lower execution time.
Probabilistic atlas priors have been commonly used to derive adaptive and robust brain MRI segmentation algorithms. Widely-used neuroimage analysis pipelines rely heavily on these techniques, which are often computationally expensive. In contrast, there has been a recent surge of approaches that leverage deep learning to implement segmentation tools that are computationally efficient at test time. However, most of these strategies rely on learning from manually annotated images. These supervised deep learning methods are therefore sensitive to the intensity profiles in the training dataset. To develop a deep learning-based segmentation model for a new image dataset (e.g., of different contrast), one usually needs to create a new labeled training dataset, which can be prohibitively expensive, or rely on suboptimal ad hoc adaptation or augmentation approaches. In this paper, we propose an alternative strategy that combines a conventional probabilistic atlas-based segmentation with deep learning, enabling one to train a segmentation model for new MRI scans without the need for any manually segmented images. Our experiments include thousands of brain MRI scans and demonstrate that the proposed method achieves good accuracy for a brain MRI segmentation task for different MRI contrasts, requiring only approximately 15 seconds at test time on a GPU. The code is freely available at http://voxelmorph.mit.edu.
In the recent time deep learning has achieved huge popularity due to its performance in various machine learning algorithms. Deep learning as hierarchical or structured learning attempts to model high level abstractions in data by using a group of processing layers. The foundation of deep learning architectures is inspired by the understanding of information processing and neural responses in human brain. The architectures are created by stacking multiple linear or non-linear operations. The article mainly focuses on the state-of-art deep learning models and various real world applications specific training methods. Selecting optimal architecture for specific problem is a challenging task, at a closing stage of the article we proposed optimal approach to deep convolutional architecture for the application of image recognition.
When analyzing the spread of viruses, epidemiologists often need to identify the location of infected hosts. This information can be found in public databases, such as GenBank, however, information provided in these databases are usually limited to the country or state level. More fine-grained localization information requires phylogeographers to manually read relevant scientific articles. In this work we propose an approach to automate the process of place name identification from medical (epidemiology) articles. The focus of this paper is to propose a deep learning based model for toponym detection and experiment with the use of external linguistic features and domain specific information. The model was evaluated using a collection of 105 epidemiology articles from PubMed Central provided by the recent SemEval task 12. Our best detection model achieves an F1 score of $80.13\%$, a significant improvement compared to the state of the art of $69.84\%$. These results underline the importance of domain specific embedding as well as specific linguistic features in toponym detection in medical journals.
One major challenge in the medication of Parkinson's disease is that the severity of the disease, reflected in the patients' motor state, cannot be measured using accessible biomarkers. Therefore, we develop and examine a variety of statistical models to detect the motor state of such patients based on sensor data from a wearable device. We find that deep learning models consistently outperform a classical machine learning model applied on hand-crafted features in this time series classification task. Furthermore, our results suggest that treating this problem as a regression instead of an ordinal regression or a classification task is most appropriate. For consistent model evaluation and training, we adopt the leave-one-subject-out validation scheme to the training of deep learning models. We also employ a class-weighting scheme to successfully mitigate the problem of high multi-class imbalances in this domain. In addition, we propose a customized performance measure that reflects the requirements of the involved medical staff on the model. To solve the problem of limited availability of high quality training data, we propose a transfer learning technique which helps to improve model performance substantially. Our results suggest that deep learning techniques offer a high potential to autonomously detect motor states of patients with Parkinson's disease.
A challenging problem in deep learning-based machine listening field is the degradation of the performance when using data from unseen conditions. In this paper we focus on the acoustic scene classification (ASC) task and propose an adversarial deep learning method to allow adapting an acoustic scene classification system to deal with a new acoustic channel resulting from data captured with a different recording device. We build upon the theoretical model of H{\Delta}H-distance and previous adversarial discriminative deep learning method for ASC unsupervised domain adaptation, and we present an adversarial training based method using the Wasserstein distance. We improve the state-of-the-art mean accuracy on the data from the unseen conditions from 32% to 45%, using the TUT Acoustic Scenes dataset.
In recent years, deep learning techniques revolutionized the way remote sensing data are processed. Classification of hyperspectral data is no exception to the rule, but has intrinsic specificities which make application of deep learning less straightforward than with other optical data. This article presents a state of the art of previous machine learning approaches, reviews the various deep learning approaches currently proposed for hyperspectral classification, and identifies the problems and difficulties which arise to implement deep neural networks for this task. In particular, the issues of spatial and spectral resolution, data volume, and transfer of models from multimedia images to hyperspectral data are addressed. Additionally, a comparative study of various families of network architectures is provided and a software toolbox is publicly released to allow experimenting with these methods. 1 This article is intended for both data scientists with interest in hyperspectral data and remote sensing experts eager to apply deep learning techniques to their own dataset.
Efficient deep learning computing requires algorithm and hardware co-design to enable specialization: we usually need to change the algorithm to reduce memory footprint and improve energy efficiency. However, the extra degree of freedom from the algorithm makes the design space much larger: it's not only about designing the hardware but also about how to tweak the algorithm to best fit the hardware. Human engineers can hardly exhaust the design space by heuristics. It's labor consuming and sub-optimal. We propose design automation techniques for efficient neural networks. We investigate automatically designing specialized fast models, auto channel pruning, and auto mixed-precision quantization. We demonstrate such learning-based, automated design achieves superior performance and efficiency than rule-based human design. Moreover, we shorten the design cycle by 200x than previous work, so that we can afford to design specialized neural network models for different hardware platforms.
We present an algorithm for learning a latent variable generative model via generative adversarial learning where the canonical uniform noise input is replaced by samples from a graphical model. This graphical model is learned by a Boltzmann machine which learns low-dimensional feature representation of data extracted by the discriminator. A quantum annealer, the D-Wave 2000Q, is used to sample from this model. This algorithm joins a growing family of algorithms that use a quantum annealing subroutine in deep learning, and provides a framework to test the advantages of quantum-assisted learning in GANs. Fully connected, symmetric bipartite and Chimera graph topologies are compared on a reduced stochastically binarized MNIST dataset, for both classical and quantum annealing sampling methods. The quantum-assisted associative adversarial network successfully learns a generative model of the MNIST dataset for all topologies, and is also applied to the LSUN dataset bedrooms class for the Chimera topology. Evaluated using the Fr\'{e}chet inception distance and inception score, the quantum and classical versions of the algorithm are found to have equivalent performance for learning an implicit generative model of the MNIST dataset.
The Oxford Nanopore Technologies's MinION is the first portable DNA sequencing device. It is capable of producing long reads, over 100 kBp were reported. However, it has significantly higher error rate than other methods. In this study, we present MinCall, an end2end basecaller model for the MinION. The model is based on deep learning and uses convolutional neural networks (CNN) in its implementation. For extra performance, it uses cutting edge deep learning techniques and architectures, batch normalization and Connectionist Temporal Classification (CTC) loss. The best performing deep learning model achieves 91.4% median match rate on E. Coli dataset using R9 pore chemistry and 1D reads.
In this paper, we propose a semi-supervised deep learning method for detecting the specific types of reads that impede the de novo genome assembly process. Instead of dealing directly with sequenced reads, we analyze their coverage graphs converted to 1D-signals. We noticed that specific signal patterns occur in each relevant class of reads. Semi-supervised approach is chosen because manually labelling the data is a very slow and tedious process, so our goal was to facilitate the assembly process with as little labeled data as possible. We tested two models to learn patterns in the coverage graphs: M1+M2 and semi-GAN. We evaluated the performance of each model based on a manually labeled dataset that comprises various reads from multiple reference genomes with respect to the number of labeled examples that were used during the training process. In addition, we embedded our detection in the assembly process which improved the quality of assemblies.
Hand gestures form an intuitive means of interaction in Mixed Reality (MR) applications. However, accurate gesture recognition can be achieved only through state-of-the-art deep learning models or with the use of expensive sensors. Despite the robustness of these deep learning models, they are generally computationally expensive and obtaining real-time performance on-device is still a challenge. To this end, we propose a novel lightweight hand gesture recognition framework that works in First Person View for wearable devices. The models are trained on a GPU machine and ported on an Android smartphone for its use with frugal wearable devices such as the Google Cardboard and VR Box. The proposed hand gesture recognition framework is driven by a cascade of state-of-the-art deep learning models: MobileNetV2 for hand localisation, our custom fingertip regression architecture followed by a Bi-LSTM model for gesture classification. We extensively evaluate the framework on our EgoGestAR dataset. The overall framework works in real-time on mobile devices and achieves a classification accuracy of 80% on EgoGestAR video dataset with an average latency of only 0.12 s.
Image registration is a key technique in medical image analysis to estimate deformations between image pairs. A good deformation model is important for high-quality estimates. However, most existing approaches use ad-hoc deformation models chosen for mathematical convenience rather than to capture observed data variation. Recent deep learning approaches learn deformation models directly from data. However, they provide limited control over the spatial regularity of transformations. Instead of learning the entire registration approach, we learn a spatially-adaptive regularizer within a registration model. This allows controlling the desired level of regularity and preserving structural properties of a registration model. For example, diffeomorphic transformations can be attained. Our approach is a radical departure from existing deep learning approaches to image registration by embedding a deep learning model in an optimization-based registration algorithm to parameterize and data-adapt the registration model itself.
Radio signal classification has a very wide range of applications in the field of wireless communications and electromagnetic spectrum management. In recent years, deep learning has been used to solve the problem of radio signal classification and has achieved good results. However, the radio signal data currently used is very limited in scale. In order to verify the performance of the deep learning-based radio signal classification on real-world radio signal data, in this paper we conduct experiments on large-scale real-world ACARS and ADS-B signal data with sample sizes of 900,000 and 13,000,000, respectively, and with categories of 3,143 and 5,157 respectively. We use the same Inception-Residual neural network model structure for ACARS signal classification and ADS-B signal classification to verify the ability of a single basic deep neural network model structure to process different types of radio signals, i.e., communication bursts in ACARS and pulse bursts in ADS-B. We build an experimental system for radio signal deep learning experiments. Experimental results show that the signal classification accuracy of ACARS and ADS-B is 98.1% and 96.3%, respectively. When the signal-to-noise ratio (with injected additive white Gaussian noise) is greater than 9 dB, the classification accuracy is greater than 92%. These experimental results validate the ability of deep learning to classify large-scale real-world radio signals. The results of the transfer learning experiment show that the model trained on large-scale ADS-B datasets is more conducive to the learning and training of new tasks than the model trained on small-scale datasets.
We introduce DeepMoD, a Deep learning based Model Discovery algorithm. DeepMoD discovers the partial differential equation underlying a spatio-temporal data set using sparse regression on a library of possible functions and their derivatives. A neural network approximates the data and constructs the function library, but it also performs the sparse regression. This construction makes it extremely robust to noise, applicable to small data sets, and, contrary to other deep learning methods, does not require a training set. We benchmark our approach on several physical problems such as the Burgers', Korteweg-de Vries and Keller-Segel equations, and find that it requires as few as $\mathcal{O}(10^2)$ samples and works at noise levels up to $75\%$. Motivated by these results, we apply DeepMoD directly on noisy experimental time-series data from a gel electrophoresis experiment and find that it discovers the advection-diffusion equation describing this system.
We propose and evaluate a new MRI reconstruction method named LORAKI that trains an autocalibrated scan-specific recurrent neural network (RNN) to recover missing k-space data. Methods like GRAPPA, SPIRiT, and AC-LORAKS assume that k-space data has shift-invariant autoregressive structure, and that the scan-specific autoregression relationships needed to recover missing samples can be learned from fully-sampled autocalibration (ACS) data. Recently, the structure of the linear GRAPPA method has been translated into a nonlinear deep learning method named RAKI. RAKI uses ACS data to train an artificial neural network to interpolate missing k-space samples, and often outperforms GRAPPA. In this work, we apply a similar principle to translate the linear AC-LORAKS method (simultaneously incorporating support, phase, and parallel imaging constraints) into a nonlinear deep learning method named LORAKI. Since AC-LORAKS is iterative and convolutional, LORAKI takes the form of a convolutional RNN. This new architecture admits a wide range of sampling patterns, and even calibrationless patterns are possible if synthetic ACS data is generated. The performance of LORAKI was evaluated with retrospectively undersampled brain datasets, with comparisons against other related reconstruction methods. Results suggest that LORAKI can provide improved reconstruction compared to other scan-specific autocalibrated reconstruction methods like GRAPPA, RAKI, and AC-LORAKS. LORAKI offers a new deep-learning approach to MRI reconstruction based on RNNs in k-space, and enables improved image quality and enhanced sampling flexibility.
In this paper, we will provide an introduction to the derivative-free optimization algorithms which can be potentially applied to train deep learning models. Existing deep learning model training is mostly based on the back propagation algorithm, which updates the model variables layers by layers with the gradient descent algorithm or its variants. However, the objective functions of deep learning models to be optimized are usually non-convex and the gradient descent algorithms based on the first-order derivative can get stuck into the local optima very easily. To resolve such a problem, various local or global optimization algorithms have been proposed, which can help improve the training of deep learning models greatly. The representative examples include the Bayesian methods, Shubert-Piyavskii algorithm, Direct, LIPO, MCS, GA, SCE, DE, PSO, ES, CMA-ES, hill climbing and simulated annealing, etc. This is a follow-up paper of [18], and we will introduce the population based optimization algorithms, e.g., GA, SCE, DE, PSO, ES and CMA-ES, and random search algorithms, e.g., hill climbing and simulated annealing, in this paper. For the introduction to the other derivative-free optimization algorithms, please refer to [18] for more information.
In this paper, we will provide an introduction to the derivative-free optimization algorithms which can be potentially applied to train deep learning models. Existing deep learning model training is mostly based on the back propagation algorithm, which updates the model variables layers by layers with the gradient descent algorithm or its variants. However, the objective functions of deep learning models to be optimized are usually non-convex and the gradient descent algorithms based on the first-order derivative can get stuck into the local optima very easily. To resolve such a problem, various local or global optimization algorithms have been proposed, which can help improve the training of deep learning models greatly. The representative examples include the Bayesian methods, Shubert-Piyavskii algorithm, Direct, LIPO, MCS, GA, SCE, DE, PSO, ES, CMA-ES, hill climbing and simulated annealing, etc. One part of these algorithms will be introduced in this paper (including the Bayesian method and Lipschitzian approaches, e.g., Shubert-Piyavskii algorithm, Direct, LIPO and MCS), and the remaining algorithms (including the population based optimization algorithms, e.g., GA, SCE, DE, PSO, ES and CMA-ES, and random search algorithms, e.g., hill climbing and simulated annealing) will be introduced in the follow-up paper [18] in detail.
Pitch or fundamental frequency (f0) extraction is a fundamental problem studied extensively for its potential applications in speech and clinical applications. In literature, explicit mode specific (modal speech or singing voice or emotional/ expressive speech or noisy speech) signal processing and deep learning f0 extraction methods that exploit the quasi periodic nature of the signal in time, harmonic property in spectral or combined form to extract the pitch is developed. Hence, there is no single unified method which can reliably extract the pitch from various modes of the acoustic signal. In this work, we propose a hybrid f0 extraction method which seamlessly extracts the pitch across modes of speech production with very high accuracy required for many applications. The proposed hybrid model exploits the advantages of deep learning and signal processing methods to minimize the pitch detection error and adopts to various modes of acoustic signal. Specifically, we propose an ordinal regression convolutional neural networks to map the periodicity rich input representation to obtain the nominal pitch classes which drastically reduces the number of classes required for pitch detection unlike other deep learning approaches. Further, the accurate f0 is estimated from the nominal pitch class labels by filtering and autocorrelation. We show that the proposed method generalizes to the unseen modes of voice production and various noises for large scale datasets. Also, the proposed hybrid model significantly reduces the learning parameters required to train the deep model compared to other methods. Furthermore,the evaluation measures showed that the proposed method is significantly better than the state-of-the-art signal processing and deep learning approaches.