Search Results for author:
Found 20 papers, 4 papers with code
The Blind Normalized Stein Variational Gradient Descent-Based Detection for Intelligent Massive Random Access
Furthermore, with the assistance of the block MHT layer, the proposed blind normalized SVGD algorithm achieves a higher preamble detection accuracy and throughput than other state-of-the-art detection methods.
A Probabilistic Hadamard U-Net for MRI Bias Field Correction
Random samples drawn from latent space are then incorporated with a prototypical corrected image to generate multiple plausible images.
A novel asymmetrical autoencoder with a sparsifying discrete cosine Stockwell transform layer for gearbox sensor data compression
In comparison to the linear layer, the DCST layer reduces the number of trainable parameters and improves the accuracy of data reconstruction.
Domain Generalization with Fourier Transform and Soft Thresholding
However, it neglects background interference in the amplitude spectrum.
Electroencephalogram Sensor Data Compression Using An Asymmetrical Sparse Autoencoder With A Discrete Cosine Transform Layer
The latent space data is transmitted to the receiver.
Stein Variational Gradient Descent-based Detection For Random Access With Preambles In MTC
Traditional preamble detection algorithms have low accuracy in the grant-based random access scheme in massive machine-type communication (mMTC).
A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer
In this paper, we propose a novel Hadamard Transform (HT)-based neural network layer for hybrid quantum-classical computing.
Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets
Trainable soft-thresholding layers, that remove noise in the transform domain, bring nonlinearity to the transform domain layers.
Input Normalized Stochastic Gradient Descent Training of Deep Neural Networks
We evaluate the efficiency of our training algorithm on benchmark datasets using ResNet-18, WResNet-20, ResNet-50, and a toy neural network.
Real-time Wireless ECG-derived Respiration Rate Estimation Using an Autoencoder with a DCT Layer
To improve the estimation precision, we propose a neural network that uses a novel Discrete Cosine Transform (DCT) layer to denoise and decorrelates the data.
DCT Perceptron Layer: A Transform Domain Approach for Convolution Layer
In this paper, we propose a novel Discrete Cosine Transform (DCT)-based neural network layer which we call DCT-perceptron to replace the $3\times3$ Conv2D layers in the Residual neural Network (ResNet).
Classification of the Cervical Vertebrae Maturation (CVM) stages Using the Tripod Network
They also have a built-in set of novel directional filters that highlight the Cervical Verte edges in X-ray images.
Multipod Convolutional Network
In this paper, we introduce a convolutional network which we call MultiPodNet consisting of a combination of two or more convolutional networks which process the input image in parallel to achieve the same goal.
Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks
In both 1-D and 2-D layers, we compute the binary WHT of the input feature map and denoise the WHT domain coefficients using a nonlinearity which is obtained by combining soft-thresholding with the tanh function.
Detecting Anomaly in Chemical Sensors via L1-Kernels based Principal Component Analysis
We propose a kernel-PCA based method to detect anomaly in chemical sensors.
Multiplication-Avoiding Variant of Power Iteration with Applications
In this paper, we introduce multiplication-avoiding power iteration (MAPI), which replaces the standard $\ell_2$-inner products that appear at the regular power iteration (RPI) with multiplication-free vector products which are Mercer-type kernel operations related with the $\ell_1$ norm.
Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks
In this paper, we propose a novel layer based on fast Walsh-Hadamard transform (WHT) and smooth-thresholding to replace $1\times 1$ convolution layers in deep neural networks.
Robust and Computationally-Efficient Anomaly Detection using Powers-of-Two Networks
We propose a technique to increase robustness and reduce computational complexity in a Convolutional Neural Network (CNN) based anomaly detector that utilizes the optical flow information of video data.
EEG Classification by factoring in Sensor Configuration
Performance of two classification models - model 1 that ignores the sensor layout and model 2 that factors it in - is investigated and found to achieve consistently higher detection accuracy.
EEG Classification based on Image Configuration in Social Anxiety Disorder
The problem of detecting the presence of Social Anxiety Disorder (SAD) using Electroencephalography (EEG) for classification has seen limited study and is addressed with a new approach that seeks to exploit the knowledge of EEG sensor spatial configuration.
