Supermassive black holes (SMBHs) are ubiquitously found at the centers of most massive galaxies. Measuring SMBH mass is important for understanding the origin and evolution of SMBHs. However, traditional methods require spectroscopic data which is expensive to gather. We present an algorithm that weighs SMBHs using quasar light time series, circumventing the need for expensive spectra. We train, validate, and test neural networks that directly learn from the Sloan Digital Sky Survey (SDSS) Stripe 82 light curves for a sample of $38,939$ spectroscopically confirmed quasars to map out the nonlinear encoding between SMBH mass and multi-color optical light curves. We find a 1$\sigma$ scatter of 0.37 dex between the predicted SMBH mass and the fiducial virial mass estimate based on SDSS single-epoch spectra, which is comparable to the systematic uncertainty in the virial mass estimate. Our results have direct implications for more efficient applications with future observations from the Vera C. Rubin Observatory. Our code, \textsf{AGNet}, is publicly available at \url{https://github.com/snehjp2/AGNet}.
Running faster will only get you so far -- it is generally advisable to first understand where the roads lead, then get a car ... The renaissance of machine learning (ML) and deep learning (DL) over the last decade is accompanied by an unscalable computational cost, limiting its advancement and weighing on the field in practice. In this thesis we take a systematic approach to address the algorithmic and methodological limitations at the root of these costs. We first demonstrate that DL training and pruning are predictable and governed by scaling laws -- for state of the art models and tasks, spanning image classification and language modeling, as well as for state of the art model compression via iterative pruning. Predictability, via the establishment of these scaling laws, provides the path for principled design and trade-off reasoning, currently largely lacking in the field. We then continue to analyze the sources of the scaling laws, offering an approximation-theoretic view and showing through the exploration of a noiseless realizable case that DL is in fact dominated by error sources very far from the lower error limit. We conclude by building on the gained theoretical understanding of the scaling laws' origins. We present a conjectural path to eliminate one of the current dominant error sources -- through a data bandwidth limiting hypothesis and the introduction of Nyquist learners -- which can, in principle, reach the generalization error lower limit (e.g. 0 in the noiseless case), at finite dataset size.
Deep learning computer vision techniques have achieved many successes in recent years across numerous imaging domains. However, the application of deep learning to spectral data remains a complex task due to the need for augmentation routines, specific architectures for spectral data, and significant memory requirements. Here we present spectrai, an open-source deep learning framework designed to facilitate the training of neural networks on spectral data and enable comparison between different methods. Spectrai provides numerous built-in spectral data pre-processing and augmentation methods, neural networks for spectral data including spectral (image) denoising, spectral (image) classification, spectral image segmentation, and spectral image super-resolution. Spectrai includes both command line and graphical user interfaces (GUI) designed to guide users through model and hyperparameter decisions for a wide range of applications.
Deep learning research has recently witnessed an impressively fast-paced progress in a wide range of tasks including computer vision, natural language processing, and reinforcement learning. The extraordinary performance of these systems often gives the impression that they can be used to revolutionise our lives for the better. However, as recent works point out, these systems suffer from several issues that make them unreliable for use in the real world, including vulnerability to adversarial attacks (Szegedy et al. [248]), tendency to memorise noise (Zhang et al. [292]), being over-confident on incorrect predictions (miscalibration) (Guo et al. [99]), and unsuitability for handling private data (Gilad-Bachrach et al. [88]). In this thesis, we look at each of these issues in detail, investigate their causes, and propose computationally cheap algorithms for mitigating them in practice. To do this, we identify structures in deep neural networks that can be exploited to mitigate the above causes of unreliability of deep learning algorithms.
In cognitive decoding, researchers aim to characterize a brain region's representations by identifying the cognitive states (e.g., accepting/rejecting a gamble) that can be identified from the region's activity. Deep learning (DL) methods are highly promising for cognitive decoding, with their unmatched ability to learn versatile representations of complex data. Yet, their widespread application in cognitive decoding is hindered by their general lack of interpretability as well as difficulties in applying them to small datasets and in ensuring their reproducibility and robustness. We propose to approach these challenges by leveraging recent advances in explainable artificial intelligence and transfer learning, while also providing specific recommendations on how to improve the reproducibility and robustness of DL modeling results.
Recent deep-learning models have achieved impressive predictive performance by learning complex functions of many variables, often at the cost of interpretability. This chapter covers recent work aiming to interpret models by attributing importance to features and feature groups for a single prediction. Importantly, the proposed attributions assign importance to interactions between features, in addition to features in isolation. These attributions are shown to yield insights across real-world domains, including bio-imaging, cosmology image and natural-language processing. We then show how these attributions can be used to directly improve the generalization of a neural network or to distill it into a simple model. Throughout the chapter, we emphasize the use of reality checks to scrutinize the proposed interpretation techniques.
Dropout Regularization, serving to reduce variance, is nearly ubiquitous in Deep Learning models. We explore the relationship between the dropout rate and model complexity by training 2,000 neural networks configured with random combinations of the dropout rate and the number of hidden units in each dense layer, on each of the three data sets we selected. The generated figures, with binary cross entropy loss and binary accuracy on the z-axis, question the common assumption that adding depth to a dense layer while increasing the dropout rate will certainly enhance performance. We also discover a complex correlation between the two hyperparameters that we proceed to quantify by building additional machine learning and Deep Learning models which predict the optimal dropout rate given some hidden units in each dense layer. Linear regression and polynomial logistic regression require the use of arbitrary thresholds to select the cost data points included in the regression and to assign the cost data points a binary classification, respectively. These machine learning models have mediocre performance because their naive nature prevented the modeling of complex decision boundaries. Turning to Deep Learning models, we build neural networks that predict the optimal dropout rate given the number of hidden units in each dense layer, the desired cost, and the desired accuracy of the model. Though, this attempt encounters a mathematical error that can be attributed to the failure of the vertical line test. The ultimate Deep Learning model is a neural network whose decision boundary represents the 2,000 previously generated data points. This final model leads us to devise a promising method for tuning hyperparameters to minimize computational expense yet maximize performance. The strategy can be applied to any model hyperparameters, with the prospect of more efficient tuning in industrial models.
Since its invention, Generative adversarial networks (GANs) have shown outstanding results in many applications. Generative Adversarial Networks are powerful yet, resource-hungry deep-learning models. Their main difference from ordinary deep learning models is the nature of their output. For example, GAN output can be a whole image versus other models detecting objects or classifying images. Thus, the architecture and numeric precision of the network affect the quality and speed of the solution. Hence, accelerating GANs is pivotal. Accelerating GANs can be classified into three main tracks: (1) Memory compression, (2) Computation optimization, and (3) Data-flow optimization. Because data transfer is the main source of energy usage, memory compression leads to the most savings. Thus, in this paper, we survey memory compression techniques for CNN-Based GANs. Additionally, the paper summarizes opportunities and challenges in GANs acceleration and suggests open research problems to be further investigated.
Infrared small target detection plays an important role in the infrared search and tracking applications. In recent years, deep learning techniques were introduced to this task and achieved noteworthy effects. Following general object segmentation methods, existing deep learning methods usually processed the image from the global view. However, the imaging locality of small targets and extreme class-imbalance between the target and background pixels were not well-considered by these deep learning methods, which causes the low-efficiency on training and high-dependence on numerous data. A local patch network (LPNet) with global attention is proposed in this paper to detect small targets by jointly considering the global and local properties of infrared small target images. From the global view, a supervised attention module trained by the small target spread map is proposed to suppress most background pixels irrelevant with small target features. From the local view, local patches are split from global features and share the same convolution weights with each other in a patch net. By leveraging both the global and local properties, the data-driven framework proposed in this paper has fused multi-scale features for small target detection. Extensive synthetic and real data experiments show that the proposed method achieves the state-of-the-art performance compared with existing both conventional and deep learning methods.
Data-intensive applications are becoming commonplace in all science disciplines. They are comprised of a rich set of sub-domains such as data engineering, deep learning, and machine learning. These applications are built around efficient data abstractions and operators that suit the applications of different domains. Often lack of a clear definition of data structures and operators in the field has led to other implementations that do not work well together. The HPTMT architecture that we proposed recently, identifies a set of data structures, operators, and an execution model for creating rich data applications that links all aspects of data engineering and data science together efficiently. This paper elaborates and illustrates this architecture using an end-to-end application with deep learning and data engineering parts working together.
Deep learning has celebrated resounding successes in many application areas of relevance to the Internet of Things (IoT), such as computer vision and machine listening. These technologies must ultimately be brought directly to the edge to fully harness the power of deep learning for the IoT. The obvious challenge is that deep learning techniques can only be implemented on strictly resource-constrained edge devices if the models are radically downsized. This task relies on different model compression techniques, such as network pruning, quantization, and the recent advancement of XNOR-Net. This study examines the suitability of these techniques for audio classification on microcontrollers. We present an application of XNOR-Net for end-to-end raw audio classification and a comprehensive empirical study comparing this approach with pruning-and-quantization methods. We show that raw audio classification with XNOR yields comparable performance to regular full precision networks for small numbers of classes while reducing memory requirements 32-fold and computation requirements 58-fold. However, as the number of classes increases significantly, performance degrades, and pruning-and-quantization based compression techniques take over as the preferred technique being able to satisfy the same space constraints but requiring approximately 8x more computation. We show that these insights are consistent between raw audio classification and image classification using standard benchmark sets. To the best of our knowledge, this is the first study to apply XNOR to end-to-end audio classification and evaluate it in the context of alternative techniques. All codes are publicly available on GitHub.
The two-user interference channel is a model for multi one-to-one communications, where two transmitters wish to communicate with their corresponding receivers via a shared wireless medium. Two most common and simple coding schemes are time division (TD) and treating interference as noise (TIN). Interestingly, it is shown that there exists an asymptotic scheme, called Han-Kobayashi scheme, that performs better than TD and TIN. However, Han-Kobayashi scheme has impractically high complexity and is designed for asymptotic settings, which leads to a gap between information theory and practice. In this paper, we focus on designing practical codes for interference channels. As it is challenging to analytically design practical codes with feasible complexity, we apply deep learning to learn codes for interference channels. We demonstrate that DeepIC, a convolutional neural network-based code with an iterative decoder, outperforms TD and TIN by a significant margin for two-user additive white Gaussian noise channels with moderate amount of interference.
Reconfigurable intelligent surface (RIS) is considered as a revolutionary technology for future wireless communication networks. In this letter, we consider the acquisition of the time-varying cascaded channels, which is a challenging task due to the massive number of passive RIS elements and the small channel coherence time. To reduce the pilot overhead, a deep learning-based channel extrapolation is implemented over both antenna and time domains. We divide the neural network into two parts, i.e., the time-domain and the antenna-domain extrapolation networks, where the neural ordinary differential equations (ODE) are utilized. In the former, ODE accurately describes the dynamics of the RIS channels and improves the recurrent neural network's performance of time series reconstruction. In the latter, ODE is resorted to modify the relations among different data layers in a feedforward neural network. We cascade the two networks and jointly train them. Simulation results show that the proposed scheme can effectively extrapolate the cascaded RIS channels in high mobility scenario.
Eye gaze analysis is an important research problem in the field of Computer Vision and Human-Computer Interaction. Even with notable progress in the last 10 years, automatic gaze analysis still remains challenging due to the uniqueness of eye appearance, eye-head interplay, occlusion, image quality, and illumination conditions. There are several open questions, including what are the important cues to interpret gaze direction in an unconstrained environment without prior knowledge and how to encode them in real-time. We review the progress across a range of gaze analysis tasks and applications to elucidate these fundamental questions, identify effective methods in gaze analysis, and provide possible future directions. We analyze recent gaze estimation and segmentation methods, especially in the unsupervised and weakly supervised domain, based on their advantages and reported evaluation metrics. Our analysis shows that the development of a robust and generic gaze analysis method still needs to address real-world challenges such as unconstrained setup and learning with less supervision. We conclude by discussing future research directions for designing a real-world gaze analysis system that can propagate to other domains including Computer Vision, Augmented Reality (AR), Virtual Reality (VR), and Human Computer Interaction (HCI). Project Page: https://github.com/i-am-shreya/EyeGazeSurvey}{https://github.com/i-am-shreya/EyeGazeSurvey
Plankton are effective indicators of environmental change and ecosystem health in freshwater habitats, but collection of plankton data using manual microscopic methods is extremely labor-intensive and expensive. Automated plankton imaging offers a promising way forward to monitor plankton communities with high frequency and accuracy in real-time. Yet, manual annotation of millions of images proposes a serious challenge to taxonomists. Deep learning classifiers have been successfully applied in various fields and provided encouraging results when used to categorize marine plankton images. Here, we present a set of deep learning models developed for the identification of lake plankton, and study several strategies to obtain optimal performances,which lead to operational prescriptions for users. To this aim, we annotated into 35 classes over 17900 images of zooplankton and large phytoplankton colonies, detected in Lake Greifensee (Switzerland) with the Dual Scripps Plankton Camera. Our best models were based on transfer learning and ensembling, which classified plankton images with 98% accuracy and 93% F1 score. When tested on freely available plankton datasets produced by other automated imaging tools (ZooScan, FlowCytobot and ISIIS), our models performed better than previously used models. Our annotated data, code and classification models are freely available online.
Background and Aim: Recently, deep learning using convolutional neural network has been used successfully to classify the images of breast cells accurately. However, the accuracy of manual classification of those histopathological images is comparatively low. This research aims to increase the accuracy of the classification of breast cancer images by utilizing a Patch-Based Classifier (PBC) along with deep learning architecture. Methodology: The proposed system consists of a Deep Convolutional Neural Network (DCNN) that helps in enhancing and increasing the accuracy of the classification process. This is done by the use of the Patch-based Classifier (PBC). CNN has completely different layers where images are first fed through convolutional layers using hyperbolic tangent function together with the max-pooling layer, drop out layers, and SoftMax function for classification. Further, the output obtained is fed to a patch-based classifier that consists of patch-wise classification output followed by majority voting. Results: The results are obtained throughout the classification stage for breast cancer images that are collected from breast-histology datasets. The proposed solution improves the accuracy of classification whether or not the images had normal, benign, in-situ, or invasive carcinoma from 87% to 94% with a decrease in processing time from 0.45 s to 0.2s on average. Conclusion: The proposed solution focused on increasing the accuracy of classifying cancer in the breast by enhancing the image contrast and reducing the vanishing gradient. Finally, this solution for the implementation of the Contrast Limited Adaptive Histogram Equalization (CLAHE) technique and modified tangent function helps in increasing the accuracy.
Code Smell, similar to a bad smell, is a surface indication of something tainted but in terms of software writing practices. This metric is an indication of a deeper problem lies within the code and is associated with an issue which is prominent to experienced software developers with acceptable coding practices. Recent studies have often observed that codes having code smells are often prone to a higher probability of change in the software development cycle. In this paper, we developed code smell prediction models with the help of features extracted from source code to predict eight types of code smell. Our work also presents the application of data sampling techniques to handle class imbalance problem and feature selection techniques to find relevant feature sets. Previous studies had made use of techniques such as Naive - Bayes and Random forest but had not explored deep learning methods to predict code smell. A total of 576 distinct Deep Learning models were trained using the features and datasets mentioned above. The study concluded that the deep learning models which used data from Synthetic Minority Oversampling Technique gave better results in terms of accuracy, AUC with the accuracy of some models improving from 88.47 to 96.84.
Koopman operator theory shows how nonlinear dynamical systems can be represented as an infinite-dimensional, linear operator acting on a Hilbert space of observables of the system. However, determining the relevant modes and eigenvalues of this infinite-dimensional operator can be difficult. The extended dynamic mode decomposition (EDMD) is one such method for generating approximations to Koopman spectra and modes, but the EDMD method faces its own set of challenges due to the need of user defined observables. To address this issue, we explore the use of autoencoder networks to simultaneously find optimal families of observables which also generate both accurate embeddings of the flow into a space of observables and submersions of the observables back into flow coordinates. This network results in a global transformation of the flow and affords future state prediction via the EDMD and the decoder network. We call this method the deep learning dynamic mode decomposition (DLDMD). The method is tested on canonical nonlinear data sets and is shown to produce results that outperform a standard DMD approach and enable data-driven prediction where the standard DMD fails.
The neuroimage analysis community has neglected the automated segmentation of the olfactory bulb (OB) despite its crucial role in olfactory function. The lack of an automatic processing method for the OB can be explained by its challenging properties. Nonetheless, recent advances in MRI acquisition techniques and resolution have allowed raters to generate more reliable manual annotations. Furthermore, the high accuracy of deep learning methods for solving semantic segmentation problems provides us with an option to reliably assess even small structures. In this work, we introduce a novel, fast, and fully automated deep learning pipeline to accurately segment OB tissue on sub-millimeter T2-weighted (T2w) whole-brain MR images. To this end, we designed a three-stage pipeline: (1) Localization of a region containing both OBs using FastSurferCNN, (2) Segmentation of OB tissue within the localized region through four independent AttFastSurferCNN - a novel deep learning architecture with a self-attention mechanism to improve modeling of contextual information, and (3) Ensemble of the predicted label maps. The OB pipeline exhibits high performance in terms of boundary delineation, OB localization, and volume estimation across a wide range of ages in 203 participants of the Rhineland Study. Moreover, it also generalizes to scans of an independent dataset never encountered during training, the Human Connectome Project (HCP), with different acquisition parameters and demographics, evaluated in 30 cases at the native 0.7mm HCP resolution, and the default 0.8mm pipeline resolution. We extensively validated our pipeline not only with respect to segmentation accuracy but also to known OB volume effects, where it can sensitively replicate age effects.
We presented an optical system to perform imaging interested objects in complex scenes, like the creature easy see the interested prey in the hunt for complex environments. It utilized Deep-learning network to learn the interested objects's vision features and designed the corresponding "imaging matrices", furthermore the learned matrixes act as the measurement matrix to complete compressive imaging with a single-pixel camera, finally we can using the compressed image data to only image the interested objects without the rest objects and backgrounds of the scenes with the previous Deep-learning network. Our results demonstrate that no matter interested object is single feature or rich details, the interference can be successfully filtered out and this idea can be applied in some common applications that effectively improve the performance. This bio-inspired optical system can act as the creature eye to achieve success on interested-based object imaging, object detection, object recognition and object tracking, etc.