In this study, we propose a novel approach of nowcasting and forecasting the macroeconomic status of a country using deep learning techniques. We focus particularly on the US economy but the methodology can be applied also to other economies. Specifically US economy has suffered a severe recession from 2008 to 2010 which practically breaks out conventional econometrics model attempts. Deep learning has the advantage that it models all macro variables simultaneously taking into account all interdependencies among them and detecting non-linear patterns which cannot be easily addressed under a univariate modelling framework. Our empirical results indicate that the deep learning methods have a superior out-of-sample performance when compared to traditional econometric techniques such as Bayesian Model Averaging (BMA). Therefore our results provide a concise view of a more robust method for assessing sovereign risk which is a crucial component in investment and monetary decisions.
One of the current key challenges in Explainable AI is in correctly interpreting activations of hidden neurons. It seems evident that accurate interpretations thereof would provide insights into the question what a deep learning system has internally \emph{detected} as relevant on the input, thus lifting some of the black box character of deep learning systems. The state of the art on this front indicates that hidden node activations appear to be interpretable in a way that makes sense to humans, at least in some cases. Yet, systematic automated methods that would be able to first hypothesize an interpretation of hidden neuron activations, and then verify it, are mostly missing. In this paper, we provide such a method and demonstrate that it provides meaningful interpretations. It is based on using large-scale background knowledge -- a class hierarchy of approx. 2 million classes curated from the Wikipedia Concept Hierarchy -- together with a symbolic reasoning approach called \emph{concept induction} based on description logics that was originally developed for applications in the Semantic Web field. Our results show that we can automatically attach meaningful labels from the background knowledge to individual neurons in the dense layer of a Convolutional Neural Network through a hypothesis and verification process.
Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks. Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of deep neural networks. In this article, we present a relatively new mathematical framework that provides the beginning of a deeper understanding of deep learning. This framework precisely characterizes the functional properties of neural networks that are trained to fit to data. The key mathematical tools which support this framework include transform-domain sparse regularization, the Radon transform of computed tomography, and approximation theory, which are all techniques deeply rooted in signal processing. This framework explains the effect of weight decay regularization in neural network training, the use of skip connections and low-rank weight matrices in network architectures, the role of sparsity in neural networks, and explains why neural networks can perform well in high-dimensional problems.
This is a master's thesis concerning the theoretical ideas of geometric deep learning. Geometric deep learning aims to provide a structured characterization of neural network architectures, specifically focused on the ideas of invariance and equivariance of data with respect to given transformations. This thesis aims to provide a theoretical evaluation of geometric deep learning, compiling theoretical results that characterize the properties of invariant neural networks with respect to learning performance.
Heart sound auscultation has been applied in clinical usage for early screening of cardiovascular diseases. Due to the high demand for auscultation expertise, automatic auscultation can help with auxiliary diagnosis and reduce the burden of training professional clinicians. Nevertheless, there is a limit to classic machine learning's performance improvement in the era of big data. Deep learning has outperformed classic machine learning in many research fields, as it employs more complex model architectures with a stronger capability of extracting effective representations. Moreover, it has been successfully applied to heart sound analysis in the past years. As most review works about heart sound analysis were carried out before 2017, the present survey is the first to work on a comprehensive overview to summarise papers on heart sound analysis with deep learning published in 2017--2022. This work introduces both classic machine learning and deep learning for comparison, and further offer insights about the advances and future research directions in deep learning for heart sound analysis. Our repository is publicly available at \url{https://github.com/zhaoren91/awesome-heart-sound-analysis}.
Distributed deep learning (DDL) training systems are designed for cloud and data-center environments that assumes homogeneous compute resources, high network bandwidth, sufficient memory and storage, as well as independent and identically distributed (IID) data across all nodes. However, these assumptions don't necessarily apply on the edge, especially when training neural networks on streaming data in an online manner. Computing on the edge suffers from both systems and statistical heterogeneity. Systems heterogeneity is attributed to differences in compute resources and bandwidth specific to each device, while statistical heterogeneity comes from unbalanced and skewed data on the edge. Different streaming-rates among devices can be another source of heterogeneity when dealing with streaming data. If the streaming rate is lower than training batch-size, device needs to wait until enough samples have streamed in before performing a single iteration of stochastic gradient descent (SGD). Thus, low-volume streams act like stragglers slowing down devices with high-volume streams in synchronous training. On the other hand, data can accumulate quickly in the buffer if the streaming rate is too high and the devices can't train at line-rate. In this paper, we introduce ScaDLES to efficiently train on streaming data at the edge in an online fashion, while also addressing the challenges of limited bandwidth and training with non-IID data. We empirically show that ScaDLES converges up to 3.29 times faster compared to conventional distributed SGD.
Mental health counseling remains a major challenge in modern society due to cost, stigma, fear, and unavailability. We posit that generative artificial intelligence (AI) models designed for mental health counseling could help improve outcomes by lowering barriers to access. To this end, we have developed a deep learning (DL) dialogue system called Serena. The system consists of a core generative model and post-processing algorithms. The core generative model is a 2.7 billion parameter Seq2Seq Transformer fine-tuned on thousands of transcripts of person-centered-therapy (PCT) sessions. The series of post-processing algorithms detects contradictions, improves coherency, and removes repetitive answers. Serena is implemented and deployed on \url{https://serena.chat}, which currently offers limited free services. While the dialogue system is capable of responding in a qualitatively empathetic and engaging manner, occasionally it displays hallucination and long-term incoherence. Overall, we demonstrate that a deep learning mental health dialogue system has the potential to provide a low-cost and effective complement to traditional human counselors with less barriers to access.
Mention detection is an important component of coreference resolution system, where mentions such as name, nominal, and pronominals are identified. These mentions can be purely coreferential mentions or singleton mentions (non-coreferential mentions). Coreferential mentions are those mentions in a text that refer to the same entities in a real world. Whereas, singleton mentions are mentioned only once in the text and do not participate in the coreference as they are not mentioned again in the following text. Filtering of these singleton mentions can substantially improve the performance of a coreference resolution process. This paper proposes a singleton mention detection module based on a fully connected network and a Convolutional neural network for Hindi text. This model utilizes a few hand-crafted features and context information, and word embedding for words. The coreference annotated Hindi dataset comprising of 3.6K sentences, and 78K tokens are used for the task. In terms of Precision, Recall, and F-measure, the experimental findings obtained are excellent.
Cerebral Microbleeds (CMBs), typically captured as hypointensities from susceptibility-weighted imaging (SWI), are particularly important for the study of dementia, cerebrovascular disease, and normal aging. Recent studies on COVID-19 have shown an increase in CMBs of coronavirus cases. Automatic detection of CMBs is challenging due to the small size and amount of CMBs making the classes highly imbalanced, lack of publicly available annotated data, and similarity with CMB mimics such as calcifications, irons, and veins. Hence, the existing deep learning methods are mostly trained on very limited research data and fail to generalize to unseen data with high variability and cannot be used in clinical setups. To this end, we propose an efficient 3D deep learning framework that is actively trained on multi-domain data. Two public datasets assigned for normal aging, stroke, and Alzheimer's disease analysis as well as an in-house dataset for COVID-19 assessment are used to train and evaluate the models. The obtained results show that the proposed method is robust to low-resolution images and achieves 78% recall and 80% precision on the entire test set with an average false positive of 1.6 per scan.
Recent developments in deep learning have led to great success in various natural language processing (NLP) tasks. However, these applications may involve data that contain sensitive information. Therefore, how to achieve good performance while also protecting the privacy of sensitive data is a crucial challenge in NLP. To preserve privacy, Differential Privacy (DP), which can prevent reconstruction attacks and protect against potential side knowledge, is becoming a de facto technique for private data analysis. In recent years, NLP in DP models (DP-NLP) has been studied from different perspectives, which deserves a comprehensive review. In this paper, we provide the first systematic review of recent advances in DP deep learning models in NLP. In particular, we first discuss some differences and additional challenges of DP-NLP compared with the standard DP deep learning. Then, we investigate some existing work on DP-NLP and present its recent developments from three aspects: gradient perturbation based methods, embedding vector perturbation based methods, and ensemble model based methods. We also discuss some challenges and future directions.
Since last 2 decades, High Frequency Oscillations (HFOs) are studied as a promising biomarker to localize the epileptogenic zone of patients with refractory focal epilepsy. As HFOs visual detection is time consuming and subjective, automatization of HFO detection is required. Most HFO detectors were developed on invasive electroencephalograms (iEEG) whereas scalp electroencephalograms (EEG) are used in clinical routine. In order HFO detection can benefit to more patients, scalp HFO detectors has to be developed. However, HFOs identification in scalp EEG is more challenging than in iEEG since scalp HFOs are of lower rate, lower amplitude and more likely to be corrupted by several sources of artifacts than iEEG HFOs. The main goal of this study is to explore the ability of deep learning architecture to identify scalp HFOs from the remaining EEG signal. Hence, a binary classification Convolutional Neural Network (CNN) is learned to analyze High Density Electroencephalograms (HD-EEG). EEG signals are first mapped into a 2D time-frequency image, several color definitions are then used as an input for the CNN. Experimental results show that deep learning allows simple end-to-end learning of preprocessing, feature extraction and classification modules while reaching competitive performance.
Over the last several years, use cases for robotics based solutions have diversified from factory floors to domestic applications. In parallel, Deep Learning approaches are replacing traditional techniques in Computer Vision, Natural Language Processing, Speech processing, etc. and are delivering robust results. Our goal is to survey a number of research internship projects in the broad area of 'Deep Learning as applied to Robotics' and present a concise view for the benefit of aspiring student interns. In this paper, we survey the research work done by Robotic Institute Summer Scholars (RISS), CMU. We particularly focus on papers that use deep learning to solve core robotic problems and also robotic solutions. We trust this would be useful particularly for internship aspirants for the Robotics Institute, CMU
Parkinson's Disease (PD) is the second most common neurodegenerative disease in humans. PD is characterized by the gradual loss of dopaminergic neurons in the Substantia Nigra (SN). Counting the number of dopaminergic neurons in the SN is one of the most important indexes in evaluating drug efficacy in PD animal models. Currently, analyzing and quantifying dopaminergic neurons is conducted manually by experts through analysis of digital pathology images which is laborious, time-consuming, and highly subjective. As such, a reliable and unbiased automated system is demanded for the quantification of dopaminergic neurons in digital pathology images. Recent years have seen a surge in adopting deep learning solutions in medical image processing. However, developing high-performing deep learning models hinges on the availability of large-scale, high-quality annotated data, which can be expensive to acquire, especially in applications like digital pathology image analysis. To this end, we propose an end-to-end deep learning framework based on self-supervised learning for the segmentation and quantification of dopaminergic neurons in PD animal models. To the best of our knowledge, this is the first deep learning model that detects the cell body of dopaminergic neurons, counts the number of dopaminergic neurons, and provides characteristics of individual dopaminergic neurons as a numerical output. Extensive experiments demonstrate the effectiveness of our model in quantifying neurons with high precision, which can provide a faster turnaround for drug efficacy studies, better understanding of dopaminergic neuronal health status, and unbiased results in PD pre-clinical research. As part of our contributions, we also provide the first publicly available dataset of histology digital images along with expert annotations for the segmentation of TH-positive DA neuronal soma.
Physics-based optimization problems are generally very time-consuming, especially due to the computational complexity associated with the forward model. Recent works have demonstrated that physics-modelling can be approximated with neural networks. However, there is always a certain degree of error associated with this learning, and we study this aspect in this paper. We demonstrate through experiments on popular mathematical benchmarks, that neural network approximations (NN-proxies) of such functions when plugged into the optimization framework, can lead to erroneous results. In particular, we study the behavior of particle swarm optimization and genetic algorithm methods and analyze their stability when coupled with NN-proxies. The correctness of the approximate model depends on the extent of sampling conducted in the parameter space, and through numerical experiments, we demonstrate that caution needs to be taken when constructing this landscape with neural networks. Further, the NN-proxies are hard to train for higher dimensional functions, and we present our insights for 4D and 10D problems. The error is higher for such cases, and we demonstrate that it is sensitive to the choice of the sampling scheme used to build the NN-proxy. The code is available at https://github.com/Fa-ti-ma/NN-proxy-in-optimization.
Automatic segmentation of curvilinear objects in medical images plays an important role in the diagnosis and evaluation of human diseases, yet it is a challenging uncertainty in the complex segmentation tasks due to different issues such as various image appearances, low contrast between curvilinear objects and their surrounding backgrounds, thin and uneven curvilinear structures, and improper background illumination conditions. To overcome these challenges, we present a unique curvilinear structure segmentation framework based on an oriented derivative of stick (ODoS) filter and a deep learning network for curvilinear object segmentation in medical images. Currently, a large number of deep learning models emphasize developing deep architectures and ignore capturing the structural features of curvilinear objects, which may lead to unsatisfactory results. Consequently, a new approach that incorporates an ODoS filter as part of a deep learning network is presented to improve the spatial attention of curvilinear objects. Specifically, the input image is transfered into four-channel image constructed by the ODoS filter. In which, the original image is considered the principal part to describe various image appearance and complex background illumination conditions, a multi-step strategy is used to enhance the contrast between curvilinear objects and their surrounding backgrounds, and a vector field is applied to discriminate thin and uneven curvilinear structures. Subsequently, a deep learning framework is employed to extract various structural features for curvilinear object segmentation in medical images. The performance of the computational model is validated in experiments conducted on the publicly available DRIVE, STARE and CHASEDB1 datasets. The experimental results indicate that the presented model yields surprising results compared with those of some state-of-the-art methods.
Deep learning based pipelines for semantic segmentation often ignore structural information available on annotated images used for training. We propose a novel post-processing module enforcing structural knowledge about the objects of interest to improve segmentation results provided by deep learning. This module corresponds to a "many-to-one-or-none" inexact graph matching approach, and is formulated as a quadratic assignment problem. Our approach is compared to a CNN-based segmentation (for various CNN backbones) on two public datasets, one for face segmentation from 2D RGB images (FASSEG), and the other for brain segmentation from 3D MRIs (IBSR). Evaluations are performed using two types of structural information (distances and directional relations, , this choice being a hyper-parameter of our generic framework). On FASSEG data, results show that our module improves accuracy of the CNN by about 6.3% (the Hausdorff distance decreases from 22.11 to 20.71). On IBSR data, the improvement is of 51% (the Hausdorff distance decreases from 11.01 to 5.4). In addition, our approach is shown to be resilient to small training datasets that often limit the performance of deep learning methods: the improvement increases as the size of the training dataset decreases.
Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks. In this paper, we propose a novel model backdoor forensics technique. Given a few attack samples such as inputs with backdoor triggers, which may represent different types of backdoors, our technique automatically decomposes them to clean inputs and the corresponding triggers. It then clusters the triggers based on their properties to allow automatic attack categorization and summarization. Backdoor scanners can then be automatically synthesized to find other instances of the same type of backdoor in other models. Our evaluation on 2,532 pre-trained models, 10 popular attacks, and comparison with 9 baselines show that our technique is highly effective. The decomposed clean inputs and triggers closely resemble the ground truth. The synthesized scanners substantially outperform the vanilla versions of existing scanners that can hardly generalize to different kinds of attacks.
There are many computer vision applications including object segmentation, classification, object detection, and reconstruction for which machine learning (ML) shows state-of-the-art performance. Nowadays, we can build ML tools for such applications with real-world accuracy. However, each tool works well within the domain in which it has been trained and developed. Often, when we train a model on a dataset in one specific domain and test on another unseen domain known as an out of distribution (OOD) dataset, models or ML tools show a decrease in performance. For instance, when we train a simple classifier on real-world images and apply that model on the same classes but with a different domain like cartoons, paintings or sketches then the performance of ML tools disappoints. This presents serious challenges of domain generalisation (DG), domain adaptation (DA), and domain shifting. To enhance the power of ML tools, we can rebuild and retrain models from scratch or we can perform transfer learning. In this paper, we present a comparison study between vision-based technologies for domain-specific and domain-generalised methods. In this research we highlight that simple convolutional neural network (CNN) based deep learning methods perform poorly when they have to tackle domain shifting. Experiments are conducted on two popular vision-based benchmarks, PACS and Office-Home. We introduce an implementation pipeline for domain generalisation methods and conventional deep learning models. The outcome confirms that CNN-based deep learning models show poor generalisation compare to other extensive methods.
The accurate detection of sperms and impurities is a very challenging task, facing problems such as the small size of targets, indefinite target morphologies, low contrast and resolution of the video, and similarity of sperms and impurities. So far, the detection of sperms and impurities still largely relies on the traditional image processing and detection techniques which only yield limited performance and often require manual intervention in the detection process, therefore unfavorably escalating the time cost and injecting the subjective bias into the analysis. Encouraged by the successes of deep learning methods in numerous object detection tasks, here we report a deep learning model based on Double Branch Feature Extraction Network (DBFEN) and Cross-conjugate Feature Pyramid Networks (CCFPN).DBFEN is designed to extract visual features from tiny objects with a double branch structure, and CCFPN is further introduced to fuse the features extracted by DBFEN to enhance the description of position and high-level semantic information. Our work is the pioneer of introducing deep learning approaches to the detection of sperms and impurities. Experiments show that the highest AP50 of the sperm and impurity detection is 91.13% and 59.64%, which lead its competitors by a substantial margin and establish new state-of-the-art results in this problem.
With 1.3 billion users, Instagram (IG) has also become a business tool. IG influencer marketing, expected to generate $33.25 billion in 2022, encourages companies and influencers to create trending content. Various methods have been proposed for predicting a post's popularity, i.e., how much engagement (e.g., Likes) it will generate. However, these methods are limited: first, they focus on forecasting the likes, ignoring the number of comments, which became crucial in 2021. Secondly, studies often use biased or limited data. Third, researchers focused on Deep Learning models to increase predictive performance, which are difficult to interpret. As a result, end-users can only estimate engagement after a post is created, which is inefficient and expensive. A better approach is to generate a post based on what people and IG like, e.g., by following guidelines. In this work, we uncover part of the underlying mechanisms driving IG engagement. To achieve this goal, we rely on statistical analysis and interpretable models rather than Deep Learning (black-box) approaches. We conduct extensive experiments using a worldwide dataset of 10 million posts created by 34K global influencers in nine different categories. With our simple yet powerful algorithms, we can predict engagement up to 94% of F1-Score, making us comparable and even superior to Deep Learning-based method. Furthermore, we propose a novel unsupervised algorithm for finding highly engaging topics on IG. Thanks to our interpretable approaches, we conclude by outlining guidelines for creating successful posts.