Hasil untuk "deep learning"

June-Goo Lee, Sanghoon Jun, Younghoon Cho et al.

The artificial neural network (ANN)–a machine learning technique inspired by the human neuronal synapse system–was introduced in the 1950s. However, the ANN was previously limited in its ability to solve actual problems, due to the vanishing gradient and overfitting problems with training of deep architecture, lack of computing power, and primarily the absence of sufficient data to train the computer system. Interest in this concept has lately resurfaced, due to the availability of big data, enhanced computing power with the current graphics processing units, and novel algorithms to train the deep neural network. Recent studies on this technology suggest its potentially to perform better than humans in some visual and auditory recognition tasks, which may portend its applications in medicine and healthcare, especially in medical imaging, in the foreseeable future. This review article offers perspectives on the history, development, and applications of deep learning technology, particularly regarding its applications in medical imaging.

Sebastian Ruder

Multi-task learning (MTL) has led to successes in many applications of machine learning, from natural language processing and speech recognition to computer vision and drug discovery. This article aims to give a general overview of MTL, particularly in deep neural networks. It introduces the two most common methods for MTL in Deep Learning, gives an overview of the literature, and discusses recent advances. In particular, it seeks to help ML practitioners apply MTL by shedding light on how MTL works and providing guidelines for choosing appropriate auxiliary tasks.

Christof Angermueller, Tanel Pärnamaa, Leopold Parts et al.

Technological advances in genomics and imaging have led to an explosion of molecular and cellular profiling data from large numbers of samples. This rapid increase in biological data dimension and acquisition rate is challenging conventional analysis strategies. Modern machine learning methods, such as deep learning, promise to leverage very large data sets for finding hidden structure within them, and for making accurate predictions. In this review, we discuss applications of this new breed of analysis approaches in regulatory genomics and cellular imaging. We provide background of what deep learning is, and the settings in which it can be successfully applied to derive biological insights. In addition to presenting specific applications and providing tips for practical use, we also highlight possible pitfalls and limitations to guide computational biologists when and how to make the most use of this new technology.

Heba M. Mohsen, E. El-Dahshan, El-Sayed M. El-Horbaty et al.

Abstract Deep Learning is a new machine learning field that gained a lot of interest over the past few years. It was widely applied to several applications and proven to be a powerful machine learning tool for many of the complex problems. In this paper we used Deep Neural Network classifier which is one of the DL architectures for classifying a dataset of 66 brain MRIs into 4 classes e.g. normal, glioblastoma, sarcoma and metastatic bronchogenic carcinoma tumors. The classifier was combined with the discrete wavelet transform (DWT) the powerful feature extraction tool and principal components analysis (PCA) and the evaluation of the performance was quite good over all the performance measures.

Hao Wang, Naiyan Wang, D. Yeung

Collaborative filtering (CF) is a successful approach commonly used by many recommender systems. Conventional CF-based methods use the ratings given to items by users as the sole source of information for learning to make recommendation. However, the ratings are often very sparse in many applications, causing CF-based methods to degrade significantly in their recommendation performance. To address this sparsity problem, auxiliary information such as item content information may be utilized. Collaborative topic regression (CTR) is an appealing recent method taking this approach which tightly couples the two components that learn from two different sources of information. Nevertheless, the latent representation learned by CTR may not be very effective when the auxiliary information is very sparse. To address this problem, we generalize recently advances in deep learning from i.i.d. input to non-i.i.d. (CF-based) input and propose in this paper a hierarchical Bayesian model called collaborative deep learning (CDL), which jointly performs deep representation learning for the content information and collaborative filtering for the ratings (feedback) matrix. Extensive experiments on three real-world datasets from different domains show that CDL can significantly advance the state of the art.

H. F. Nweke, Teh Ying Wah, M. Al-garadi et al.

Abstract Human activity recognition systems are developed as part of a framework to enable continuous monitoring of human behaviours in the area of ambient assisted living, sports injury detection, elderly care, rehabilitation, and entertainment and surveillance in smart home environments. The extraction of relevant features is the most challenging part of the mobile and wearable sensor-based human activity recognition pipeline. Feature extraction influences the algorithm performance and reduces computation time and complexity. However, current human activity recognition relies on handcrafted features that are incapable of handling complex activities especially with the current influx of multimodal and high dimensional sensor data. With the emergence of deep learning and increased computation powers, deep learning and artificial intelligence methods are being adopted for automatic feature learning in diverse areas like health, image classification, and recently, for feature extraction and classification of simple and complex human activity recognition in mobile and wearable sensors. Furthermore, the fusion of mobile or wearable sensors and deep learning methods for feature learning provide diversity, offers higher generalisation, and tackles challenging issues in human activity recognition. The focus of this review is to provide in-depth summaries of deep learning methods for mobile and wearable sensor-based human activity recognition. The review presents the methods, uniqueness, advantages and their limitations. We not only categorise the studies into generative, discriminative and hybrid methods but also highlight their important advantages. Furthermore, the review presents classification and evaluation procedures and discusses publicly available datasets for mobile sensor human activity recognition. Finally, we outline and explain some challenges to open research problems that require further research and improvements.

Volodymyr Kuleshov, Nathan Fenner, Stefano Ermon

Methods for reasoning under uncertainty are a key building block of accurate and reliable machine learning systems. Bayesian methods provide a general framework to quantify uncertainty. However, because of model misspecification and the use of approximate inference, Bayesian uncertainty estimates are often inaccurate -- for example, a 90% credible interval may not contain the true outcome 90% of the time. Here, we propose a simple procedure for calibrating any regression algorithm; when applied to Bayesian and probabilistic models, it is guaranteed to produce calibrated uncertainty estimates given enough data. Our procedure is inspired by Platt scaling and extends previous work on classification. We evaluate this approach on Bayesian linear regression, feedforward, and recurrent neural networks, and find that it consistently outputs well-calibrated credible intervals while improving performance on time series forecasting and model-based reinforcement learning tasks.

Y. R. Tabar, U. Halici

Wei Ma, Feng Cheng, Yongmin Liu

Deep-learning framework has significantly impelled the development of modern machine learning technology by continuously pushing the limit of traditional recognition and processing of images, speech, and videos. In the meantime, it starts to penetrate other disciplines, such as biology, genetics, materials science, and physics. Here, we report a deep-learning-based model, comprising two bidirectional neural networks assembled by a partial stacking strategy, to automatically design and optimize three-dimensional chiral metamaterials with strong chiroptical responses at predesignated wavelengths. The model can help to discover the intricate, nonintuitive relationship between a metamaterial structure and its optical responses from a number of training examples, which circumvents the time-consuming, case-by-case numerical simulations in conventional metamaterial designs. This approach not only realizes the forward prediction of optical performance much more accurately and efficiently but also enables one to inversely retrieve designs from given requirements. Our results demonstrate that such a data-driven model can be applied as a very powerful tool in studying complicated light-matter interactions and accelerating the on-demand design of nanophotonic devices, systems, and architectures for real world applications.

James Zou, M. Huss, Abubakar Abid et al.

Zhixi Li, Yifan He, S. Keel et al.

PURPOSE To assess the performance of a deep learning algorithm for detecting referable glaucomatous optic neuropathy (GON) based on color fundus photographs. DESIGN A deep learning system for the classification of GON was developed for automated classification of GON on color fundus photographs. PARTICIPANTS We retrospectively included 48 116 fundus photographs for the development and validation of a deep learning algorithm. METHODS This study recruited 21 trained ophthalmologists to classify the photographs. Referable GON was defined as vertical cup-to-disc ratio of 0.7 or more and other typical changes of GON. The reference standard was made until 3 graders achieved agreement. A separate validation dataset of 8000 fully gradable fundus photographs was used to assess the performance of this algorithm. MAIN OUTCOME MEASURES The area under receiver operator characteristic curve (AUC) with sensitivity and specificity was applied to evaluate the efficacy of the deep learning algorithm detecting referable GON. RESULTS In the validation dataset, this deep learning system achieved an AUC of 0.986 with sensitivity of 95.6% and specificity of 92.0%. The most common reasons for false-negative grading (n = 87) were GON with coexisting eye conditions (n = 44 [50.6%]), including pathologic or high myopia (n = 37 [42.6%]), diabetic retinopathy (n = 4 [4.6%]), and age-related macular degeneration (n = 3 [3.4%]). The leading reason for false-positive results (n = 480) was having other eye conditions (n = 458 [95.4%]), mainly including physiologic cupping (n = 267 [55.6%]). Misclassification as false-positive results amidst a normal-appearing fundus occurred in only 22 eyes (4.6%). CONCLUSIONS A deep learning system can detect referable GON with high sensitivity and specificity. Coexistence of high or pathologic myopia is the most common cause resulting in false-negative results. Physiologic cupping and pathologic myopia were the most common reasons for false-positive results.

Jingzhou Liu, Wei-Cheng Chang, Yuexin Wu et al.

Ulysse Côté-Allard, C. Fall, Alexandre Drouin et al.

In recent years, deep learning algorithms have become increasingly more prominent for their unparalleled ability to automatically learn discriminant features from large amounts of data. However, within the field of electromyography-based gesture recognition, deep learning algorithms are seldom employed as they require an unreasonable amount of effort from a single person, to generate tens of thousands of examples. This paper’s hypothesis is that general, informative features can be learned from the large amounts of data generated by aggregating the signals of multiple users, thus reducing the recording burden while enhancing gesture recognition. Consequently, this paper proposes applying transfer learning on aggregated data from multiple users while leveraging the capacity of deep learning algorithms to learn discriminant features from large datasets. Two datasets comprised 19 and 17 able-bodied participants, respectively (the first one is employed for pre-training), were recorded for this work, using the Myo armband. A third Myo armband dataset was taken from the NinaPro database and is comprised ten able-bodied participants. Three different deep learning networks employing three different modalities as input (raw EMG, spectrograms, and continuous wavelet transform (CWT)) are tested on the second and third dataset. The proposed transfer learning scheme is shown to systematically and significantly enhance the performance for all three networks on the two datasets, achieving an offline accuracy of 98.31% for 7 gestures over 17 participants for the CWT-based ConvNet and 68.98% for 18 gestures over 10 participants for the raw EMG-based ConvNet. Finally, a use-case study employing eight able-bodied participants suggests that real-time feedback allows users to adapt their muscle activation strategy which reduces the degradation in accuracy normally experienced over time.

Nicolas Papernot, P. Mcdaniel

Deep neural networks (DNNs) enable innovative applications of machine learning like image recognition, machine translation, or malware detection. However, deep learning is often criticized for its lack of robustness in adversarial settings (e.g., vulnerability to adversarial inputs) and general inability to rationalize its predictions. In this work, we exploit the structure of deep learning to enable new learning-based inference and decision strategies that achieve desirable properties such as robustness and interpretability. We take a first step in this direction and introduce the Deep k-Nearest Neighbors (DkNN). This hybrid classifier combines the k-nearest neighbors algorithm with representations of the data learned by each layer of the DNN: a test input is compared to its neighboring training points according to the distance that separates them in the representations. We show the labels of these neighboring points afford confidence estimates for inputs outside the model's training manifold, including on malicious inputs like adversarial examples--and therein provides protections against inputs that are outside the models understanding. This is because the nearest neighbors can be used to estimate the nonconformity of, i.e., the lack of support for, a prediction in the training data. The neighbors also constitute human-interpretable explanations of predictions. We evaluate the DkNN algorithm on several datasets, and show the confidence estimates accurately identify inputs outside the model, and that the explanations provided by nearest neighbors are intuitive and useful in understanding model failures.

Yanghua Peng, Yixin Bao, Yangrui Chen et al.

Andreas Kipf, Thomas Kipf, Bernhard Radke et al.

We describe a new deep learning approach to cardinality estimation. MSCN is a multi-set convolutional network, tailored to representing relational query plans, that employs set semantics to capture query features and true cardinalities. MSCN builds on sampling-based estimation, addressing its weaknesses when no sampled tuples qualify a predicate, and in capturing join-crossing correlations. Our evaluation of MSCN using a real-world dataset shows that deep learning significantly enhances the quality of cardinality estimation, which is the core problem in query optimization.

H. Fujiyoshi, Tsubasa Hirakawa, Takayoshi Yamashita

Abstract Various image recognition tasks were handled in the image recognition field prior to 2010 by combining image local features manually designed by researchers (called handcrafted features) and machine learning method. After entering the 2010, However, many image recognition methods that use deep learning have been proposed. The image recognition methods using deep learning are far superior to the methods used prior to the appearance of deep learning in general object recognition competitions. Hence, this paper will explain how deep learning is applied to the field of image recognition, and will also explain the latest trends of deep learning-based autonomous driving.

Yang-Yang Zheng, Jianlei Kong, Xue-bo Jin et al.

Intelligence has been considered as the major challenge in promoting economic potential and production efficiency of precision agriculture. In order to apply advanced deep-learning technology to complete various agricultural tasks in online and offline ways, a large number of crop vision datasets with domain-specific annotation are urgently needed. To encourage further progress in challenging realistic agricultural conditions, we present the CropDeep species classification and detection dataset, consisting of 31,147 images with over 49,000 annotated instances from 31 different classes. In contrast to existing vision datasets, images were collected with different cameras and equipment in greenhouses, captured in a wide variety of situations. It features visually similar species and periodic changes with more representative annotations, which have supported a stronger benchmark for deep-learning-based classification and detection. To further verify the application prospect, we provide extensive baseline experiments using state-of-the-art deep-learning classification and detection models. Results show that current deep-learning-based methods achieve well performance in classification accuracy over 99%. While current deep-learning methods achieve only 92% detection accuracy, illustrating the difficulty of the dataset and improvement room of state-of-the-art deep-learning models when applied to crops production and management. Specifically, we suggest that the YOLOv3 network has good potential application in agricultural detection tasks.

Po-Wei Wang, P. Donti, Bryan Wilder et al.

Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems. In this paper, we propose a new direction toward this goal by introducing a differentiable (smoothed) maximum satisfiability (MAXSAT) solver that can be integrated into the loop of larger deep learning systems. Our (approximate) solver is based upon a fast coordinate descent approach to solving the semidefinite program (SDP) associated with the MAXSAT problem. We show how to analytically differentiate through the solution to this SDP and efficiently solve the associated backward pass. We demonstrate that by integrating this solver into end-to-end learning systems, we can learn the logical structure of challenging problems in a minimally supervised fashion. In particular, we show that we can learn the parity function using single-bit supervision (a traditionally hard task for deep networks) and learn how to play 9x9 Sudoku solely from examples. We also solve a "visual Sudok" problem that maps images of Sudoku puzzles to their associated logical solutions by combining our MAXSAT solver with a traditional convolutional architecture. Our approach thus shows promise in integrating logical structures within deep learning.

Zhiyuan Li, Sanjeev Arora

Intriguing empirical evidence exists that deep learning can work well with exoticschedules for varying the learning rate. This paper suggests that the phenomenon may be due to Batch Normalization or BN, which is ubiquitous and provides benefits in optimization and generalization across all standard architectures. The following new results are shown about BN with weight decay and momentum (in other words, the typical use case which was not considered in earlier theoretical analyses of stand-alone BN. 1. Training can be done using SGD with momentum and an exponentially increasing learning rate schedule, i.e., learning rate increases by some $(1 +\alpha)$ factor in every epoch for some $\alpha >0$. (Precise statement in the paper.) To the best of our knowledge this is the first time such a rate schedule has been successfully used, let alone for highly successful architectures. As expected, such training rapidly blows up network weights, but the net stays well-behaved due to normalization. 2. Mathematical explanation of the success of the above rate schedule: a rigorous proof that it is equivalent to the standard setting of BN + SGD + StandardRate Tuning + Weight Decay + Momentum. This equivalence holds for other normalization layers as well, Group Normalization, LayerNormalization, Instance Norm, etc. 3. A worked-out toy example illustrating the above linkage of hyper-parameters. Using either weight decay or BN alone reaches global minimum, but convergence fails when both are used.