Multiplication free neural network for cancer stem cell detection in H-and-E stained liver images

Badawi, Diaa; Akhan, Ece; Mallah, Maen; Üner, Ayşegül; Çetin-Atalay, Rengül; Çetin, A. Enis

doi:10.1117/12.2262338

Cited by 6 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al. introduced multiplication-free (MF) kernel to replace regular convolution in CNNs [38,39,40,41,42]. The MF kernel requires no multiplication but only additions and sign operations.…”

Section: Multiplication-free Depthwise Separable "Convolutions" (Mf-d...mentioning

confidence: 99%

“…In a regular neuron we multiply x by w to determine the contribution of the input value. In some binary networks and additive networks [38,39,40,41,42], the sign of the multiplication w × x is used as the basic operation of the neuron. In addition, we will scale the sign(w × x) by the 1 norm of the vector y = [w + x w − x] T which is the 2×2 WH transform of the vector [w x] T and define the following basic operation…”

Section: Multiplication-free Depthwise Separable "Convolutions" (Mf-d...mentioning

confidence: 99%

“…In this paper, we introduce a binary layer based on the fast Walsh-Hadamard transform to slim and speed up deep neural networks with 1 × 1 convolutions. Moreover, the recent literature [38,39,40,41,42] developed an energy-efficient neuron called multiplication-free (MF) kernel, which does not require any multiplications. We establish the relation between the MF operator and 2-by-2 Hadamard transform, and we fuse this idea to propose the depthwise separable multiplication-free convolution layer.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks

Pan¹,

Dabawi²,

Çetin³

2021

Preprint

View full text Add to dashboard Cite

In this paper, we propose a novel layer based on fast Walsh-Hadamard transform (WHT) and smooththresholding to replace 1 × 1 convolution layers in deep neural networks.In the WHT domain, we denoise the transform domain coefficients using the new smooththresholding non-linearity, a smoothed version of the wellknown soft-thresholding operator. We also introduce a family of multiplication-free operators from the basic 2×2 Hadamard transform to implement 3 × 3 depthwise separable convolution layers. Using these two types of layers, we replace the bottleneck layers in MobileNet-V2 to reduce the network's number of parameters with a slight loss in accuracy. For example, by replacing the final third bottleneck layers, we reduce the number of parameters from 2.270M to 947K. This reduces the accuracy from 95.21% to 92.88% on the CIFAR-10 dataset. Our approach significantly improves the speed of data processing. The fast Walsh-Hadamard transform has a computational complexity of O(m log 2 m). As a result, it is computationally more efficient than the 1 × 1 convolution layer. The fast Walsh-Hadamard layer processes a tensor in R 10×32×32×1024 about 2 times faster than 1 × 1 convolution layer on NVIDIA Jetson Nano computer board.

show abstract

“…al. introduced multiplication-free (MF) kernel to replace regular convolution in CNNs [38,39,40,41,42]. The MF kernel requires no multiplication but only additions and sign operations.…”

Section: Multiplication-free Depthwise Separable "Convolutions" (Mf-d...mentioning

confidence: 99%

Section: Multiplication-free Depthwise Separable "Convolutions" (Mf-d...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks

Pan¹,

Dabawi²,

Çetin³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This is because x = sgn(x)|x|. One key property of the md operation is that it preserves the sign of regular multiplication operations [24], [25]. We define the vector version of the md operation as follows.…”

Section: B Additive Neural Network (Addnet)mentioning

confidence: 99%

Detecting Gas Vapor Leaks Using Uncalibrated Sensors

et al. 2019

Self Cite

View full text Add to dashboard Cite

Chemical and infra-red sensors generate distinct responses under similar conditions because of sensor drift, noise or resolution errors. In this work, we use different time-series data sets obtained by infra-red and E-nose sensors in order to detect Volatile Organic Compounds (VOCs) and Ammonia vapor leaks. We process time-series sensor signals using deep neural networks (DNN). Three neural network algorithms are utilized for this purpose. Additive neural networks (termed AddNet) are based on a multiplication-devoid operator and consequently exhibit energy-efficiency compared to regular neural networks. The second algorithm uses generative adversarial neural networks so as to expose the classifying neural network to more realistic data points in order to help the classifier network to deliver improved generalization. Finally, we use conventional convolutional neural networks as a baseline method and compare their performance with the two aforementioned deep neural network algorithms in order to evaluate their effectiveness empirically.

show abstract

“…This multiplier-less operator is first used in image processing tasks such as cancer cell detection and licence plate recognition in [7,8]. Multiplication-free neural networks (MFNN) based on this operator are studied in [9][10][11]. This operator achieved promising performance especially at image classification on MNIST dataset with multi-layer perceptron (MLP) models [10].…”

Section: Introductionmentioning

confidence: 99%

Energy Efficient Hadamard Neural Networks

Deveci,

Cakir,

Cetin

2018

Preprint

View full text Add to dashboard Cite

Deep learning has made significant improvements at many image processing tasks in recent years, such as image classification, object recognition and object detection. Convolutional neural networks (CNN), which is a popular deep learning architecture designed to process data in multiple array form, show great success to almost all detection & recognition problems and computer vision tasks. However, the number of parameters in a CNN is too high such that the computers require more energy and larger memory size. In order to solve this problem, we propose a novel energy efficient model Binary Weight and Hadamard-transformed Image Network (BWHIN), which is a combination of Binary Weight Network (BWN) and Hadamard-transformed Image Network (HIN). It is observed that energy efficiency is achieved with a slight sacrifice at classification accuracy. Among all energy efficient networks, our novel ensemble model outperforms other energy efficient models.

show abstract

Multiplication free neural network for cancer stem cell detection in H-and-E stained liver images

Cited by 6 publications

References 6 publications

Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks

Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks

Detecting Gas Vapor Leaks Using Uncalibrated Sensors

Energy Efficient Hadamard Neural Networks

Contact Info

Product

Resources

About