16 citations · 73 across the 24 of their papers we have counts for
7 papers · 1 filter
Input Normalized Stochastic Gradient Descent Training of Deep Neural Networks
Salih Atici, Hongyi Pan, Ahmet Enis Cetin
In this paper, we propose a novel optimization algorithm for training machine learning models called Input Normalized Stochastic Gradient Descent (INSGD), inspired by the Normalize…
DCT Perceptron Layer: A Transform Domain Approach for Convolution Layer
Hongyi Pan, Xin Zhu, Salih Atici +1
In this paper, we propose a novel Discrete Cosine Transform (DCT)-based neural network layer which we call DCT-perceptron to replace the Conv2D layers in the Residual ne…
Classification of the Cervical Vertebrae Maturation (CVM) stages Using the Tripod Network
Salih Atici, Hongyi Pan, Mohammed H. Elnagar +4
We present a novel deep learning method for fully automated detection and classification of the Cervical Vertebrae Maturation (CVM) stages. The deep convolutional neural network co…
Real-time Wireless ECG-derived Respiration Rate Estimation Using an Autoencoder with a DCT Layer
Hongyi Pan, Xin Zhu, Zhilu Ye +2
In this paper, we present a wireless ECG-derived Respiration Rate (RR) estimation using an autoencoder with a DCT Layer. The wireless wearable system records the ECG data of the su…
Multipod Convolutional Network
Hongyi Pan, Salih Atici, Ahmet Enis Cetin
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 par…
Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks
Hongyi Pan, Diaa Badawi, Ahmet Enis Cetin
Convolution has been the core operation of modern deep neural networks. It is well-known that convolutions can be implemented in the Fourier Transform domain. In this paper, we pro…
Detecting Anomaly in Chemical Sensors via L1-Kernels based Principal Component Analysis
Hongyi Pan, Diaa Badawi, Ishaan Bassi +2
We propose a kernel-PCA based method to detect anomaly in chemical sensors. We use temporal signals produced by chemical sensors to form vectors to perform the Principal Component…