MAX simplifies access to DL models for non-experts.
problem Difficulty for non-experts in adopting latest DL models.
method Proposes MAX, a Python library that wraps DL models and provides RESTful APIs.
result Maximizes ease of using state-of-the-art DL models for inference.
A scalable DL benchmarking platform for evaluating and comparing models, frameworks, and hardware.
problem Lack of a uniform DL benchmarking platform for evaluating and comparing innovations.
method Identified 10 design features for a DL benchmarking platform, proposed MLModelScope, and implemented as an open-source project.
result Demonstrated how model, hardware, and framework selection affect accuracy and performance under different scenarios.
This paper clarifies deep learning for IS scholars.
problem Limited IS contributions in deep learning.
method Systematic review and framework development.
result Clear guidelines for IS scholars to make DL contributions.
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…
A new DL framework preserves geometric structures for causal predictions.
problem Designing deep learning models for geometrically structured data.
method Introduces a universal causal geometric DL framework.
result DL models can approximate any regular map between metric spaces.
Develops deep probabilistic graphical modeling for better flexibility and interpretability.
problem Lack of flexibility in probabilistic graphical models and interpretability in deep learning.
method Combines deep learning and probabilistic graphical modeling to create flexible models with interpretable latent structures.
result Solves problems in probabilistic topic models and introduces new learning algorithms.
DL2 uses deep learning to optimize resource allocation in DL clusters.
problem Efficient resource scheduling for deep learning clusters is challenging.
method DL2 combines supervised learning and reinforcement learning to dynamically allocate resources.
result DL2 reduces average training completion time by 44.1% compared to fairness scheduler.
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…
Benanza speeds up DL model optimization by automatically generating micro-benchmarks and identifying inefficiencies.
problem Slow characterization/optimization cycles for DL models on GPUs.
method Benanza includes a model processor, benchmark generator, database, and analyzer.
result Benanza identifies optimizations in parallel layer execution, cuDNN, framework inefficiency, layer fusion, and Tensor Cores.
Discriminative Dictionary Learning (DL) methods have been widely advocated for image classification problems. To further sharpen their discriminative capabilities, most state-of-the-art DL methods have additional constraints included in the learning stages. These various constraints, however, lead to additional computa…
MLModelScope streamlines ML/DL model evaluation and benchmarking.
problem Challenges in evaluating and benchmarking ML/DL models.
method Open-source, framework/hardware agnostic platform with distributed design.
result Demonstrates the impact of model evaluation pipelines and HW/SW choices.
Dictionary leaning (DL) and dimensionality reduction (DR) are powerful tools to analyze high-dimensional noisy signals. This paper presents a proposal of a novel Riemannian joint dimensionality reduction and dictionary learning (R-JDRDL) on symmetric positive definite (SPD) manifolds for classification tasks. The joint…
Deep learning models can take weeks to train on a single GPU-equipped machine, necessitating scaling out DL training to a GPU-cluster. However, current distributed DL implementations can scale poorly due to substantial parameter synchronization over the network, because the high throughput of GPUs allows more data batc…
DL/FBF improves GPSR solutions by selecting compact, generalising expressions.
problem Overfitting and structural bloat in symbolic regression with genetic programming.
method Description length (DL) and fractional Bayes factor (FBF) criteria for selecting compact, generalising expressions.
result DL/FBF post-selection improves test performance compared to AIC/BIC baseline.
DLBricks automates DL benchmarking on CPUs, reducing effort and time.
problem Lack of representative and up-to-date DL benchmarks on CPUs.
method Decomposes DL models into runnable networks, leveraging layer repetition and auto-generation.
result Accurately estimates DL model performance and speeds up benchmarking time.
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…
Deep learning models struggle with new data in stock price trend prediction.
problem Stock price trend prediction using Deep Learning models.
method Examination of fifteen state-of-the-art DL models on LOB data, using LOBCAST framework.
result All models show significant performance drop with new data, questioning their market applicability.
Z-GCNETs uses topological data to improve time series forecasting.
problem Improving time series forecasting accuracy.
method Integrates topological data into graph convolutional networks (GCNs) using zigzag persistence.
result Z-GCNETs outperforms 13 state-of-the-art methods in traffic forecasting and Ethereum price prediction.
A review of ML and DL for ecological data analysis.
problem Understanding the strengths and limitations of ML and DL in ecological research.
method Historical overview, algorithm families, differences, universal principles, and emerging trends.
result ML and DL excel in prediction tasks but are still debated for causal inference.
Comparison of AutoML and DL shows AutoML outperforms simple DL for binary classification.
problem Choosing between AutoML and DL for binary classification tasks.
method Comparison of AutoML and DL on 6 public datasets, evaluation of a new AutoML tool.
result AutoML outperforms simple DL classifiers but integrating DL into AutoML improves performance further.
The paper proposes a tool to detect invalid inputs in DL models.
problem Vulnerability of DL models to invalid inputs during runtime.
method Design and implementation of a tool that extracts data flow footprints and conducts assertion-based validation.
result The assertion-based data sanity check mechanism effectively identifies invalid input cases.
Deep learning improves automated detection of epileptic seizures.
problem Automated detection of epileptic seizures using traditional methods is limited.
method Deep learning techniques for feature extraction and classification.
result Deep learning enhances accuracy in diagnosing epileptic seizures.
PID-GAN uses physics knowledge to improve deep learning models' reliability.
problem Improving deep learning models' reliability in physics-based applications.
method Physics-informed GAN architecture that incorporates physics knowledge into both generator and discriminator models.
result PID-GAN framework outperforms state-of-the-art in handling gradient imbalance.
Deep learning enhances smart fish farming through automated feature extraction.
problem Challenges in obtaining labeled data limit DL applications in aquaculture.
method Application of DL techniques in aquaculture, including live fish identification, species classification, and feeding decision-making.
result Deep learning's ability to automatically extract features is a significant contribution.
Bayesian Deep Learning tackles inverse problems with neural networks and approximate computations.
problem Solving inverse problems with indirect measurements and uncertainties.
method Bayesian Deep Learning, using neural networks and approximate computations.
result Effective solutions for inverse problems using Bayesian Deep Learning.
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.
problem Lack of comprehensive benchmarks for DL hardware.
method Developed a benchmark for inference on embedded HWAs, focusing on autonomous driving. Proposed new granularity, benchmark procedures, and performance indicators.
result Identifies mismatches between HWAs and DL models.
Parametric approaches to Learning, such as deep learning (DL), are highly popular in nonlinear regression, in spite of their extremely difficult training with their increasing complexity (e.g. number of layers in DL). In this paper, we present an alternative semi-parametric framework which foregoes the ordinarily requi…
We introduce a model-based reconstruction framework with deep learned (DL) and smoothness regularization on manifolds (STORM) priors to recover free breathing and ungated (FBU) cardiac MRI from highly undersampled measurements. The DL priors enable us to exploit the local correlations, while the STORM prior enables us …
Diestel-Leader graphs are neither hyperbolic nor CAT(0), so their visual boundaries may be pathological. Indeed, we show that for d>2, ∂DLd(q) carries the indiscrete topology. On the other hand, ∂DL2(q), while not Hausdorff, is T1, totally disconnected, and compact. Since $\text{D…
Researchers use DL and XAI to evaluate climate downscaling models.
problem Evaluating complex DL models for climate downscaling.
method Intercompare DL models, expand standard evaluation methods with XAI.
result XAI techniques provide new evaluation dimensions and model insights.
Improved DL models robust against adversarial attacks for wireless signal classification.
problem Adversarial attacks on deep learning-based wireless signal classifiers.
method Knowledge distillation and network pruning followed by adversarial training.
result Proposed models achieve better robustness and higher accuracy than standard models.
RE enhances DL by learning model behavior, enabling iterative self-improvement.
problem Static data representations limit DL's potential for evolving models.
method RE uses multiple mappings of data through identical deep architectures, analyzing internal representations and performance signals.
result Models can gain insight from predecessors, leading to iterative self-improvement.
Defense against DL-based lithographic hotspot detectors backdooring attacks reduces success rate from 84% to ~0%
problem DL-based lithographic hotspot detectors are vulnerable to backdoor attacks that can misclassify hotspots.
method Training data augmentation to eliminate intentional biases introduced during training.
result Significant reduction in attack success rate (from 84% to ~0%) using the proposed defense.
This paper introduces a new metric for deep learning networks based on their classification performance.
problem The mystery and black-box nature of deep learning networks.
method Proposes a new distance measure based on the probabilistic performance of deep learning networks.
result The proposed metric space is compact and coincides with the quotient topological space.
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…
Study evaluates information leakage in Polymarket markets, finding limited applicability and resolution ambiguity.
problem Limited applicability of ILS-dl framework across Polymarket markets.
method Scaling from single-case to population-scale evaluation using ILS-dl framework.
result Only 0.7% of candidate markets yield computable ILS-dl values, and resolution semantics are the main obstacle.
Teaches deep learning to statisticians.
problem Statisticians lack expertise in deep learning.
method Developed a program and taught DL to statistics graduate students.
result Provided tips and resources for teaching DL.
Paper improves candlestick classification model's resistance to adversarial attacks.
problem Adversarial attacks on deep learning models for candlestick classification.
method Constructs perturbed examples to enhance model robustness.
result Boosted stability of DL models for candlestick classification.
A new method approximates deep neural networks using Kalman Filters.
problem Approximating deep neural networks with limited data.
method Matrix Ensemble Kalman Filter-based multi-arm ANN (MEnKF-ANN).
result MEnKF-ANN can adequately approximate LSTM networks and provide uncertainty estimates.
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…
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…
The study compares DLS method with machine learning for cricket match result prediction.
problem Improving accuracy of Duckworth-Lewis-Stern method for cricket match result prediction.
method Comparison of Duckworth-Lewis-Stern method with various supervised learning algorithms and optimization of DLS resource table.
result Development of Unpredictability Index to rank nations based on unpredictability in ODI matches.
A new method for causal inference in high-dimensional data using machine learning.
problem Causal inference in high-dimensional observational data.
method Support Points Sample Splitting (SPSS) for efficient double machine learning (DML) in causal inference.
result Deep learning with SPSS and hybrid methods outperform SVM with SPSS in computational efficiency and estimation quality.
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…
SplitEasy trains ML models on mobile devices without server data transfer.
problem Training complex DL models on resource-limited mobile devices.
method Split learning approach where sensitive layers are trained locally, computationally intensive layers on server.
result SplitEasy trains models on mobile devices with minimal data transfer, near-constant time per sample.
DL improves precipitation nowcasting from radar images.
problem Precise short-term precipitation predictions for extreme weather adaptation.
method Image-to-image translation using UNET CNN, compared to optical flow, persistence, and HRRR.
result UNET-based DL outperforms traditional models in 1 km x 1 km, 1 hour precipitation nowcasting.