The complete and updated list of publications can be found in Google Scholar.

• MEDUSA: Multi-scale Encoder-Decoder Self-Attention Deep Neural Network Architecture for Medical Image Analysis, Frontiers in Medicine, section Translational Medicine.
• OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection, Special Issue on Embedded Artificial Intelligence for Smart Sensing and IoT Applications, Sensors.
• TinyDefectNet: Highly Compact Deep Neural Network Architecture for High-Throughput Manufacturing Visual Quality Inspection, Annual Conference on Vision and Intelligent Systems. (Best Paper Award)
• MAPLE: Microprocessor A Priori for Latency Estimation, NewInML Workshop NeurIPS .
• A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning, CVPR Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems and Online Challenges.(Best Paper Award)
• Does Form Follow Function? An Empirical Exploration of the Impact of Deep Neural Network Architecture Design on Hardware-Specific Acceleration, TinyML Research Symposium.
• Residual Error: a New Performance Measure for Adversarial Robustness, CVPR Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems and Online Challenges.
• Adversarial Variance Attacks: Deeper Insights into Adversarial MachineLearning through the Eyes of Bias-Variance Impact, CVPR Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems and Online Challenges.
• COVID-Net CT-S: 3D Convolutional Neural Network Architectures for COVID-19 Severity Assessment using Chest CT Images, ICLR Workshop: Machine Learning for Preventing and Combating Pandemics.

• Deep Neural Networks and Robust Autonomous Driving Systems, IEEE Signal Processing Magazine.
• GenSynth: A generative synthesis approach to learning generative machines to generate efficient neural networks, IET Electronics Letters.
• Learn2Perturb: An End-to-end Feature Perturbation Learning to Improve Adversarial Robustness, Computer Vision & Pattern Recognition (CVPR).
• AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers, NeurIPS Workshop.
• State of Compact Architecture Search for Deep Neural Networks, Workshop on Edge Intelligence.

• Real-time Vehicle Make and Model Recognition Using Unsupervised Feature Learning, IEEE Transaction on Intelligent Transportation Systems.
• Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms, NeurIPS Workshop.
• YOLO Nano: a Highly Compact You Only Look Once Convolutional Neural Network for Object Detection, NeurIPS Workshop.
• Learn2Perturb: Improving Adversarial Robustness on Deep Neural Networks through End-to-end Feature Perturbation Learning, NeurIPS Workshop.
• Dynamic Representations Toward Efficient Inference on Deep Neural Networks by Decision Gates, Computer Vision & Pattern Recognition Workshop (CVPR).
• SANE: Towards Improved Prediction Robustness via Stochastically Activated Network Ensembles, Computer Vision & Pattern Recognition Workshop (CVPR).
• A Random Field Computational Adaptive Optics Framework for Optical Coherence Microscopy, ICAIR.

• StressedNets: Efficient Feature Representations via Stress-induced Evolutionary Synthesis of Deep Neural Networks, Neurocomputing, Elsevier .
• MicronNet: A Highly Compact Deep Convolutional Neural Network Architecture for Real-Time Embedded Traffic Sign Classification, IEEE Access .
• Efficient Inference on Deep Neural Networks by Dynamic Representations and Decision Gates, Neural Information Processing Systems Workshop (NeurIPS).
• FermiNets: Learning generative machines to generate efficient neural networks via generative synthesis, Neural Information Processing Systems Workshop (NeurIPS).

• Discovery Radiomics via Evolutionary Deep Radiomic Sequencer Discovery for Pathologically-Proven Lung Cancer Detection, Journal of Medical Imaging, SPIE .
• Compensated Row-Column Ultrasound Imaging System Using Multilayered Edge Guided Stochastically Fully Connected Random Fields, Nature Scientific Reports .
• Real-Time Embedded Motion Detection via Neural Response Mixture Modeling, Journal of Signal Processing Systems .
• SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis, Neural Information Processing Systems Workshops (NIPS).
• Learning Efficient Deep Feature Representations via Transgenerational Genetic Transmission of Environmental Information during Evolutionary Synthesis of Deep Neural Networks, International Conference on Computer Vision Workshop (ICCV-W).
• The Mating Rituals of Deep Neural Networks: Learning Compact Feature Representations through Sexual Evolutionary Synthesis, International Conference on Computer Vision Workshop (ICCV-W).
• Exploring the Imposition of Synaptic Precision Restrictions For Evolutionary Synthesis of Deep Neural Networks, Conference on Cognitive Computational Neuroscience.
• A Deep Predictive Intelligence Platform for Patient Monitoring, Engineering in Medicine and Biology Society (EMBC).
• Discovery Radiomics for Pathologically-Proven Computed Tomography Lung Cancer Prediction, Machine Learning for Medical Image Computing Workshop, ICIAR.

• Deep Randomly-connected Conditional Random Fields For Image Segmentation, IEEE Access Journal .
• NeRD: a Neural Response Divergence Approach to Visual saliency detection, IEEE Signal Processing Letters .
• Sparse Reconstruction of Compressive Sensing Multi-spectral Data using an Inter-Spectral Multi-layered Conditional Random Field Model, IEEE Access Journal .
• Sparse Reconstruction of Compressive Sensing MRI using Cross-Domain Stochastically Fully Connected Conditional Random Fields, BMC Medical Imaging, Springer Nature .
• Fully Connected Continuous Conditional Random Field With Stochastic Cliques for Dark-Spot Detection In SAR Imagery, IEEE Journal of Selected Topics on Applied Earth Observation and Remote Sensing .
• Estimating oxygen uptake and energy expenditure during treadmill walking by neural network analysis of easy-to-obtain inputs, Journal of Applied Physiology .
• Temporal noise reduction of fluorescence microscopy image sequences using a stochastically-connected random field model, Nature Scientific Reports .
• Compensated Row-Column Ultrasound Imaging System Using Fisher Tippett Multilayered Conditional Random Field Model, PLoS ONE .
• Evolutionary Synthesis of Deep Neural Networks via Synaptic Cluster-driven Genetic Encoding, Neural Information Processing Systems Workshops (NIPS).(Best Paper Award)
• Embedded Motion Detection via Neural Response Mixture Background Modeling, Computer Vision and Pattern Recognition Workshops (CVPRW).
• Efficient Deep Feature Learning and Extraction via StochasticNets, Computer Vision and Pattern Recognition Workshops (CVPRW).
• Real-time, Embedded Scene Invariant Crowd Counting Using Scale-Normalized Histogram of Moving Gradients (HoMG), Computer Vision and Pattern Recognition Workshops (CVPRW).
• Bayesian-based Compensated Magnetic Resonance Imaging, Engineering in Medicine and Biology Society (EMBC).
• Spatio-Temporal Saliency Detection Using Abstracted Fully-Connected Graphical Models, IEEE International Conference on Image Processing (ICIP).
• Random Feature MAPS Via A Layered Random Projection (LARP) Framework For Object Classification, IEEE International Conference on Image Processing (ICIP).

• Document image binarization using a discriminative structural classifie, Pattern Recognition Letter .
• A Deep-Structured Fully-Connected Random Field Model For Structured Inference, IEEE Access Journal .
• A Deep-structured Conditional Random Field Model for Object Silhouette Tracking, PLoS ONE.
• Apparent Ultra-High b-value Diffusion-Weighted Image Reconstruction via Hidden Conditional Random Fields, IEEE Transactions on Medical Imaging .
• Discovery Radiomics for Cancer Detection, Neural Information Processing Systems Workshops (NIPS).
• Improved Fine Structure Modeling via Guided Stochastic Clique Formation in Fully Connected Conditional Random Fields, {IEEE International Conference on Image Processing (ICIP).
• Sparse Reconstruction of Compressed Sensing Multi-spectral Data using Cross-Spectral Multi-layered Conditional Random Field Model, SPIE Optical Engineering+ Applications.
• Virtual Spectral Multiplexing for Applications in In-situ Imaging Microscopy of Transient Phenomena, SPIE Optical Engineering+ Applications.
• PIRM: Fast Background Subtraction Under Sudden, Local Illumination Changes Via Probabilistic Illumination Range Modeling, IEEE International Conference on Image Processing (ICIP).
• Oil Spill Candidate Detection from SAR Imagery Using a Thresholding-Guided Stochastic Fully-Connected Conditional Random Field Model, Computer Vision and Pattern Recognition Workshops (CVPRW).
• Single-click, Semi-Automatic Lung Nodule Contouring Using Hierarchical Conditional Random Fields, International Symposium on Biomedical Imaging (ISBI).