arXiv research

DL/FBF improves GPSR solutions by selecting compact, generalising expressions.

Deep learning aids in autism diagnosis and rehabilitation using neuroimaging data.

Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffe…

A multiple instance dictionary learning method using functions of multiple instances (DL-FUMI) is proposed to address target detection and two-class classification problems with inaccurate training labels. Given inaccurate training labels, DL-FUMI learns a set of target dictionary atoms that describe the most distincti…

A multiple instance dictionary learning approach, Dictionary Learning using Functions of Multiple Instances (DL-FUMI), is used to perform beat-to-beat heart rate estimation and to characterize heartbeat signatures from ballistocardiogram (BCG) signals collected with a hydraulic bed sensor. DL-FUMI estimates a "heartbea…

This paper clarifies deep learning for IS scholars.

A new DL framework preserves geometric structures for causal predictions.

A recent trend observed in traditionally challenging fields such as computer vision and natural language processing has been the significant performance gains shown by deep learning (DL). In many different research fields, DL models have been evolving rapidly and become ubiquitous. Despite researchers' excitement, unfo…

AugLoss combines data augmentation and robust loss functions for robust DL models.

Frameworks for writing, compiling, and optimizing deep learning (DL) models have recently enabled progress in areas like computer vision and natural language processing. Extending these frameworks to accommodate the rapidly diversifying landscape of DL models and hardware platforms presents challenging tradeoffs betwee…

In this survey paper, we systematically summarize existing literature on bearing fault diagnostics with machine learning (ML) and data mining techniques. While conventional ML methods, including artificial neural network (ANN), principal component analysis (PCA), support vector machines (SVM), etc., have been successfu…

DLBricks automates DL benchmarking on CPUs, reducing effort and time.

Survey of integrating domain knowledge into DL models.

A review of ML and DL for ecological data analysis.

Comparison of AutoML and DL shows AutoML outperforms simple DL for binary classification.

Reliability is a critical consideration to DL-based systems. But the statistical nature of DL makes it quite vulnerable to invalid inputs, i.e., those cases that are not considered in the training phase of a DL model. This paper proposes to perform data sanity check to identify invalid inputs, so as to enhance the reli…

Deep learning improves automated detection of epileptic seizures.

A scalable DL benchmarking platform for evaluating and comparing models, frameworks, and hardware.

Deep learning enhances smart fish farming through automated feature extraction.

Bayesian Deep Learning tackles inverse problems with neural networks and approximate computations.

Recent breakthroughs in Deep Learning (DL) applications have made DL models a key component in almost every modern computing system. The increased popularity of DL applications deployed on a wide-spectrum of platforms have resulted in a plethora of design challenges related to the constraints introduced by the hardware…

Deep learning (DL), a new-generation of artificial neural network research, has transformed industries, daily lives and various scientific disciplines in recent years. DL represents significant progress in the ability of neural networks to automatically engineer problem-relevant features and capture highly complex data…

Benchmark for DL inference on embedded HWAs, focusing on autonomous driving.

Deep learning (DL) is a high dimensional data reduction technique for constructing high-dimensional predictors in input-output models. DL is a form of machine learning that uses hierarchical layers of latent features. In this article, we review the state-of-the-art of deep learning from a modeling and algorithmic persp…

Deep Huber QRNs predict Huber quantiles for house prices.

Review of deep learning methods in medical image registration.

Diestel-Leader graphs are neither hyperbolic nor CAT(0), so their visual boundaries may be pathological. Indeed, we show that for $d>2$, $\partial\text{DL}_d(q)$ carries the indiscrete topology. On the other hand, $\partial\text{DL}_2(q)$, while not Hausdorff, is $T_1$, totally disconnected, and compact. Since $\text{D…

Improved DL models robust against adversarial attacks for wireless signal classification.

Defense against DL-based lithographic hotspot detectors backdooring attacks reduces success rate from 84% to ~0%

The application of deep learning (DL) models to the decoding of cognitive states from whole-brain functional Magnetic Resonance Imaging (fMRI) data is often hindered by the small sample size and high dimensionality of these datasets. Especially, in clinical settings, where patient data are scarce. In this work, we demo…

This paper introduces a new metric for deep learning networks based on their classification performance.

More and more companies have deployed machine learning (ML) clusters, where deep learning (DL) models are trained for providing various AI-driven services. Efficient resource scheduling is essential for maximal utilization of expensive DL clusters. Existing cluster schedulers either are agnostic to ML workload characte…

Understanding the global optimality in deep learning (DL) has been attracting more and more attention recently. Conventional DL solvers, however, have not been developed intentionally to seek for such global optimality. In this paper we propose a novel approximation algorithm, BPGrad, towards optimizing deep models glo…

Teaches deep learning to statisticians.

Paper improves candlestick classification model's resistance to adversarial attacks.

A new method approximates deep neural networks using Kalman Filters.

We explore how Deep Learning (DL) can be utilized to predict prognosis of acute myeloid leukemia (AML). Out of TCGA (The Cancer Genome Atlas) database, 94 AML cases are used in this study. Input data include age, 10 common cytogenetic and 23 most common mutation results; output is the prognosis (diagnosis to death, DTD…

Develops deep probabilistic graphical modeling for better flexibility and interpretability.

Deep Learning (DL) methods have emerged as one of the most powerful tools for functional approximation and prediction. While the representation properties of DL have been well studied, uncertainty quantification remains challenging and largely unexplored. Data augmentation techniques are a natural approach to provide u…

The study compares DLS method with machine learning for cricket match result prediction.

Deep learning (DL) based autoencoder has shown great potential to significantly enhance the physical layer performance. In this paper, we present a DL based autoencoder for interference channel. Based on a characterization of a k-user Gaussian interference channel, where the interferences are classified as different le…

Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. With the wide-spread usage of DL in critical and time-sensitive applications, including unmanned vehicles, drones, and video surveillance systems, onli…

DL improves precipitation nowcasting from radar images.

Machine Learning (ML) and Deep Learning (DL) innovations are being introduced at such a rapid pace that model owners and evaluators are hard-pressed analyzing and studying them. This is exacerbated by the complicated procedures for evaluation. The lack of standard systems and efficient techniques for specifying and pro…

Survey of deep learning models in finance.

Proposes a novel deep DL approach for inference tasks.

Deep learning (DL) is one of the most prominent branches of machine learning. Due to the immense computational cost of DL workloads, industry and academia have developed DL libraries with highly-specialized kernels for each workload/architecture, leading to numerous, complex code-bases that strive for performance, yet …

A new method detects hallucinations in medical image restoration using Fourier Ring Correlation.