Search Results for author:
Found 55 papers, 7 papers with code
DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence
We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning for efficiently training and evolving populations of UNIMAL agents.
Memory-Efficient Continual Learning Object Segmentation for Long Video
We propose two novel techniques to reduce the memory requirement of Online VOS methods while improving modeling accuracy and generalization on long videos.
NAS-NeRF: Generative Neural Architecture Search for Neural Radiance Fields
Thus, there is a need to dynamically optimize the neural network component of NeRFs to achieve a balance between computational complexity and specific targets for synthesis quality.
Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge
As such, the design of highly efficient multi-task deep neural network architectures tailored for computer vision tasks for robotic grasping on the edge is highly desired for widespread adoption in manufacturing environments.
High-Throughput, High-Performance Deep Learning-Driven Light Guide Plate Surface Visual Quality Inspection Tailored for Real-World Manufacturing Environments
As such, the proposed deep learning-driven workflow, integrated with the aforementioned LightDefectNet neural network, is highly suited for high-throughput, high-performance light plate surface VQI within real-world manufacturing environments.
Faster Attention Is What You Need: A Fast Self-Attention Neural Network Backbone Architecture for the Edge via Double-Condensing Attention Condensers
With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge.
MAPLE-X: Latency Prediction with Explicit Microprocessor Prior Knowledge
Deep neural network (DNN) latency characterization is a time-consuming process and adds significant cost to Neural Architecture Search (NAS) processes when searching for efficient convolutional neural networks for embedded vision applications.
MAPLE-Edge: A Runtime Latency Predictor for Edge Devices
Neural Architecture Search (NAS) has enabled automatic discovery of more efficient neural network architectures, especially for mobile and embedded vision applications.
CellDefectNet: A Machine-designed Attention Condenser Network for Electroluminescence-based Photovoltaic Cell Defect Inspection
Photovoltaic cells are electronic devices that convert light energy to electricity, forming the backbone of solar energy harvesting systems.
LightDefectNet: A Highly Compact Deep Anti-Aliased Attention Condenser Neural Network Architecture for Light Guide Plate Surface Defect Detection
Light guide plates are essential optical components widely used in a diverse range of applications ranging from medical lighting fixtures to back-lit TV displays.
COVID-Net Biochem: An Explainability-driven Framework to Building Machine Learning Models for Predicting Survival and Kidney Injury of COVID-19 Patients from Clinical and Biochemistry Data
Since the World Health Organization declared COVID-19 a pandemic in 2020, the global community has faced ongoing challenges in controlling and mitigating the transmission of the SARS-CoV-2 virus, as well as its evolving subvariants and recombinants.
MAPLE: Microprocessor A Priori for Latency Estimation
Through this quantitative strategy as the hardware descriptor, MAPLE can generalize to new hardware via a few shot adaptation strategy where with as few as 3 samples it exhibits a 6% improvement over state-of-the-art methods requiring as much as 10 samples.
TinyDefectNet: Highly Compact Deep Neural Network Architecture for High-Throughput Manufacturing Visual Quality Inspection
A critical aspect in the manufacturing process is the visual quality inspection of manufactured components for defects and flaws.
MEDUSA: Multi-scale Encoder-Decoder Self-Attention Deep Neural Network Architecture for Medical Image Analysis
In this work, we explore the concept of self-attention for tackling such subtleties in and between diseases.
Does Form Follow Function? An Empirical Exploration of the Impact of Deep Neural Network Architecture Design on Hardware-Specific Acceleration
In this study, a comprehensive empirical exploration is conducted to investigate the impact of deep neural network architecture design on the degree of inference speedup that can be achieved via hardware-specific acceleration.
Residual Error: a New Performance Measure for Adversarial Robustness
Motivated by this, this study presents the concept of residual error, a new performance measure for not only assessing the adversarial robustness of a deep neural network at the individual sample level, but also can be used to differentiate between adversarial and non-adversarial examples to facilitate for adversarial example detection.
COVID-Net CT-S: 3D Convolutional Neural Network Architectures for COVID-19 Severity Assessment using Chest CT Images
The health and socioeconomic difficulties caused by the COVID-19 pandemic continues to cause enormous tensions around the world.
COVID-Net CXR-S: Deep Convolutional Neural Network for Severity Assessment of COVID-19 Cases from Chest X-ray Images
More specifically, we leveraged transfer learning to transfer representational knowledge gained from over 16, 000 CXR images from a multinational cohort of over 15, 000 patient cases into a custom network architecture for severity assessment.
OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection
Human operators often diagnose industrial machinery via anomalous sounds.
A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning
Adversarial Training (AT) with Projected Gradient Descent (PGD) is an effective approach for improving the robustness of the deep neural networks.
AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers
Based on these promising results, AttendNets illustrate the effectiveness of visual attention condensers as building blocks for enabling various on-device visual perception tasks for TinyML applications.
Vulnerability Under Adversarial Machine Learning: Bias or Variance?
In this study, we investigate the effect of adversarial machine learning on the bias and variance of a trained deep neural network and analyze how adversarial perturbations can affect the generalization of a network.
Deep Neural Network Perception Models and Robust Autonomous Driving Systems
This paper analyzes the robustness of deep learning models in autonomous driving applications and discusses the practical solutions to address that.
Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustness
In this study, we introduce Learn2Perturb, an end-to-end feature perturbation learning approach for improving the adversarial robustness of deep neural networks.
Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms
A comprehensive analysis using this approach was conducted on several state-of-the-art explainability methods (LIME, SHAP, Expected Gradients, GSInquire) on a ResNet-50 deep convolutional neural network using a subset of ImageNet for the task of image classification.
State of Compact Architecture Search For Deep Neural Networks
A particularly interesting class of compact architecture search algorithms are those that are guided by baseline network architectures.
YOLO Nano: a Highly Compact You Only Look Once Convolutional Neural Network for Object Detection
As such, there has been growing research interest in the design of efficient deep neural network architectures catered for edge and mobile usage.
Human-Machine Collaborative Design for Accelerated Design of Compact Deep Neural Networks for Autonomous Driving
The findings of this case study showed that GenSynth is easy to use and can be effective at accelerating the design and production of compact, customized deep neural network.
Dynamic Representations Toward Efficient Inference on Deep Neural Networks by Decision Gates
The proposed d-gate modules can be integrated with any deep neural network and reduces the average computational cost of the deep neural networks while maintaining modeling accuracy.
Efficient Inference on Deep Neural Networks by Dynamic Representations and Decision Gates
The current trade-off between depth and computational cost makes it difficult to adopt deep neural networks for many industrial applications, especially when computing power is limited.
FermiNets: Learning generative machines to generate efficient neural networks via generative synthesis
In this study, we introduce the idea of generative synthesis, which is premised on the intricate interplay between a generator-inquisitor pair that work in tandem to garner insights and learn to generate highly efficient deep neural networks that best satisfies operational requirements.
Unsupervised Feature Learning Toward a Real-time Vehicle Make and Model Recognition
Here, we formulate the vehicle make and model recognition as a fine-grained classification problem and propose a new configurable on-road vehicle make and model recognition framework.
MicronNet: A Highly Compact Deep Convolutional Neural Network Architecture for Real-time Embedded Traffic Sign Classification
The resulting MicronNet possesses a model size of just ~1MB and ~510, 000 parameters (~27x fewer parameters than state-of-the-art) while still achieving a human performance level top-1 accuracy of 98. 9% on the German traffic sign recognition benchmark.
Ranked #3 on
Traffic Sign Recognition
on GTSRB
Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network for Real-time Embedded Object Detection
The resulting Tiny SSD possess a model size of 2. 3MB (~26X smaller than Tiny YOLO) while still achieving an mAP of 61. 3% on VOC 2007 (~4. 2% higher than Tiny YOLO).
StressedNets: Efficient Feature Representations via Stress-induced Evolutionary Synthesis of Deep Neural Networks
The computational complexity of leveraging deep neural networks for extracting deep feature representations is a significant barrier to its widespread adoption, particularly for use in embedded devices.
SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis
While deep neural networks have been shown in recent years to outperform other machine learning methods in a wide range of applications, one of the biggest challenges with enabling deep neural networks for widespread deployment on edge devices such as mobile and other consumer devices is high computational and memory requirements.
Discovery Radiomics via Deep Multi-Column Radiomic Sequencers for Skin Cancer Detection
While skin cancer is the most diagnosed form of cancer in men and women, with more cases diagnosed each year than all other cancers combined, sufficiently early diagnosis results in very good prognosis and as such makes early detection crucial.
Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video
Object detection is considered one of the most challenging problems in this field of computer vision, as it involves the combination of object classification and object localization within a scene.
The Mating Rituals of Deep Neural Networks: Learning Compact Feature Representations through Sexual Evolutionary Synthesis
Evolutionary deep intelligence was recently proposed as a method for achieving highly efficient deep neural network architectures over successive generations.
Exploring the Imposition of Synaptic Precision Restrictions For Evolutionary Synthesis of Deep Neural Networks
A key contributing factor to incredible success of deep neural networks has been the significant rise on massively parallel computing devices allowing researchers to greatly increase the size and depth of deep neural networks, leading to significant improvements in modeling accuracy.
Discovery Radiomics via Evolutionary Deep Radiomic Sequencer Discovery for Pathologically-Proven Lung Cancer Detection
We evaluated the evolved deep radiomic sequencer (EDRS) discovered via the proposed evolutionary deep radiomic sequencer discovery framework against state-of-the-art radiomics-driven and discovery radiomics methods using clinical lung CT data with pathologically-proven diagnostic data from the LIDC-IDRI dataset.
Evolution in Groups: A deeper look at synaptic cluster driven evolution of deep neural networks
In this study, we take a deeper look at the notion of synaptic cluster-driven evolution of deep neural networks which guides the evolution process towards the formation of a highly sparse set of synaptic clusters in offspring networks.
Evolutionary Synthesis of Deep Neural Networks via Synaptic Cluster-driven Genetic Encoding
There has been significant recent interest towards achieving highly efficient deep neural network architectures.
Deep Learning with Darwin: Evolutionary Synthesis of Deep Neural Networks
Taking inspiration from biological evolution, we explore the idea of "Can deep neural networks evolve naturally over successive generations into highly efficient deep neural networks?"
Scene Invariant Crowd Segmentation and Counting Using Scale-Normalized Histogram of Moving Gradients (HoMG)
The problem of automated crowd segmentation and counting has garnered significant interest in the field of video surveillance.
Sparse Reconstruction of Compressive Sensing MRI using Cross-Domain Stochastically Fully Connected Conditional Random Fields
Reducing MRI acquisition time can reduce patient discomfort and as a result reduces motion artifacts from the acquisition process.
Domain Adaptation and Transfer Learning in StochasticNets
Transfer learning is a recent field of machine learning research that aims to resolve the challenge of dealing with insufficient training data in the domain of interest.
Noise-Compensated, Bias-Corrected Diffusion Weighted Endorectal Magnetic Resonance Imaging via a Stochastically Fully-Connected Joint Conditional Random Field Model
Retrospective bias correction approaches are introduced as a more efficient way of bias correction compared to the prospective methods such that they correct for both of the scanner and anatomy-related bias fields in MR imaging.
Efficient Deep Feature Learning and Extraction via StochasticNets
Experimental results show that features learned using deep convolutional StochasticNets, with fewer neural connections than conventional deep convolutional neural networks, can allow for better or comparable classification accuracy than conventional deep neural networks: relative test error decrease of ~4. 5% for classification on the STL-10 dataset and ~1% for classification on the SVHN dataset.
Discovery Radiomics via StochasticNet Sequencers for Cancer Detection
In this study, we introduce a novel discovery radiomics framework where we directly discover custom radiomic features from the wealth of available medical imaging data.
Discovery Radiomics for Multi-Parametric MRI Prostate Cancer Detection
In this study, we propose a novel \textit{discovery radiomics} framework for generating custom radiomic sequences tailored for prostate cancer detection.
Discovery Radiomics for Pathologically-Proven Computed Tomography Lung Cancer Prediction
In this study, we take the idea of radiomics one step further by introducing the concept of discovery radiomics for lung cancer prediction using CT imaging data.
StochasticNet: Forming Deep Neural Networks via Stochastic Connectivity
A pivotal study on the brain tissue of rats found that synaptic formation for specific functional connectivity in neocortical neural microcircuits can be surprisingly well modeled and predicted as a random formation.
Forming A Random Field via Stochastic Cliques: From Random Graphs to Fully Connected Random Fields
However, the issue of computational tractability becomes a significant issue when incorporating such long-range nodal interactions, particularly when a large number of long-range nodal interactions (e. g., fully-connected random fields) are modeled.
A deep-structured fully-connected random field model for structured inference
In this study, we investigate the feasibility of unifying fully-connected and deep-structured models in a computationally tractable manner for the purpose of structured inference.
