research
∙
05/27/2023
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 n...
share
research
∙
03/13/2023
Orthogonal Transform Domain Approaches for the Convolutional Layer
In this paper, we propose a set of transform-based neural network layers...
research
∙
12/20/2022
Normalized Stochastic Gradient Descent Training of Deep Neural Networks
In this paper, we introduce a novel optimization algorithm for machine l...
research
∙
11/15/2022
DCT Perceptron Layer: A Transform Domain Approach for Convolution Layer
In this paper, we propose a novel Discrete Cosine Transform (DCT)-based ...
research
∙
10/03/2022
Multipod Convolutional Network
In this paper, we introduce a convolutional network which we call MultiP...
research
∙
01/07/2022
Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks
Convolution has been the core operation of modern deep neural networks. ...
research
∙
10/22/2021
Multiplication-Avoiding Variant of Power Iteration with Applications
Power iteration is a fundamental algorithm in data analysis. It extracts...
research
∙
04/14/2021
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 tra...
research
∙
01/29/2021
MF-Net: Compute-In-Memory SRAM for Multibit Precision Inference using Memory-immersed Data Conversion and Multiplication-free Operators
We propose a co-design approach for compute-in-memory inference for deep...
research
∙
10/30/2019
Robust and Computationally-Efficient Anomaly Detection using Powers-of-Two Networks
Robust and computationally efficient anomaly detection in videos is a pr...
research
∙
05/22/2019
Improved EEG Classification by factoring in sensor topography
Electroencephalography (EEG) serves as an effective diagnostic tool for ...
research
∙
12/07/2018