Efficient HW and SW Interface Design for Convolutional Neural Networks Using High-Level Synthesis and TensorFlow

2021 ◽  
Author(s):  
Ashish Misra ◽  
Churan He ◽  
Volodymyr Kindratenko
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Interface Design ◽  
High Level Synthesis ◽  
High Level

scholarly journals Interpretation of Swedish Sign Language Using Convolutional Neural Networks and Transfer Learning

2021 ◽  
Vol 2 (3) ◽  
Author(s):  
Gustaf Halvardsson ◽  
Johanna Peterson ◽  
César Soto-Valero ◽  
Benoit Baudry
Keyword(s):  
Neural Networks ◽  
Sign Language ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Web Application ◽  
Training Dataset ◽  
Motion Processing ◽  
Image Perception ◽  
Sign Languages ◽  
High Level

AbstractThe automatic interpretation of sign languages is a challenging task, as it requires the usage of high-level vision and high-level motion processing systems for providing accurate image perception. In this paper, we use Convolutional Neural Networks (CNNs) and transfer learning to make computers able to interpret signs of the Swedish Sign Language (SSL) hand alphabet. Our model consists of the implementation of a pre-trained InceptionV3 network, and the usage of the mini-batch gradient descent optimization algorithm. We rely on transfer learning during the pre-training of the model and its data. The final accuracy of the model, based on 8 study subjects and 9400 images, is 85%. Our results indicate that the usage of CNNs is a promising approach to interpret sign languages, and transfer learning can be used to achieve high testing accuracy despite using a small training dataset. Furthermore, we describe the implementation details of our model to interpret signs as a user-friendly web application.

scholarly journals Fully Automatic Cell Segmentation with Fourier Descriptors

2021 ◽  
Author(s):  
Dominik Hirling ◽  
Peter Horvath
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Fundamental Problem ◽  
Cell Segmentation ◽  
Fourier Descriptors ◽  
Control Points ◽  
Coefficient Vector ◽  
Fully Automatic ◽  
High Level ◽  
And Control

Cell segmentation is a fundamental problem in biology for which convolutional neural networks yield the best results nowadays. In this paper, we present HarmonicNet, a network, which is a modification of the popular StarDist and SplineDist architectures. While StarDist and SplineDist describe an object by the lengths of equiangular rays and control points respectively, our network utilizes Fourier descriptors, predicting a coefficient vector for every pixel on the image, which implicitly define the resulting segmentation. We evaluate our model on three different datasets, and show that Fourier descriptors can achieve a high level of accuracy with a small number of coefficients. HarmonicNet is also capable of accurately segmenting objects that are not star-shaped, a case where StarDist performs suboptimally according to our experiments.

scholarly journals Incorporating Context-Relevant Knowledge into Convolutional Neural Networks for Short Text Classification

2019 ◽  
Vol 33 ◽  
pp. 10067-10068 ◽  
Author(s):  
Jingyun Xu ◽  
Yi Cai
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Text Classification ◽  
Classification Methods ◽  
Short Text ◽  
Proposed Model ◽  
High Level ◽  
Context Features

Some text classification methods don’t work well on short texts due to the data sparsity. What’s more, they don’t fully exploit context-relevant knowledge. In order to tackle these problems, we propose a neural network to incorporate context-relevant knowledge into a convolutional neural network for short text classification. Our model consists of two modules. The first module utilizes two layers to extract concept and context features respectively and then employs an attention layer to extract those context-relevant concepts. The second module utilizes a convolutional neural network to extract high-level features from the word and the contextrelevant concept features. The experimental results on three datasets show that our proposed model outperforms the stateof-the-art models.

scholarly journals CNN2Gate: An Implementation of Convolutional Neural Networks Inference on FPGAs with Automated Design Space Exploration

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 2200
Author(s):  
Alireza Ghaffari ◽  
Yvon Savaria
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Design Space Exploration ◽  
Design Space ◽  
Space Exploration ◽  
Automatic Synthesis ◽  
Software Libraries ◽  
Learning Software ◽  
High Level

Convolutional Neural Networks (CNNs) have a major impact on our society, because of the numerous services they provide. These services include, but are not limited to image classification, video analysis, and speech recognition. Recently, the number of researches that utilize FPGAs to implement CNNs are increasing rapidly. This is due to the lower power consumption and easy reconfigurability that are offered by these platforms. Because of the research efforts put into topics, such as architecture, synthesis, and optimization, some new challenges are arising for integrating suitable hardware solutions to high-level machine learning software libraries. This paper introduces an integrated framework (CNN2Gate), which supports compilation of a CNN model for an FPGA target. CNN2Gate is capable of parsing CNN models from several popular high-level machine learning libraries, such as Keras, Pytorch, Caffe2, etc. CNN2Gate extracts computation flow of layers, in addition to weights and biases, and applies a “given” fixed-point quantization. Furthermore, it writes this information in the proper format for the FPGA vendor’s OpenCL synthesis tools that are then used to build and run the project on FPGA. CNN2Gate performs design-space exploration and fits the design on different FPGAs with limited logic resources automatically. This paper reports results of automatic synthesis and design-space exploration of AlexNet and VGG-16 on various Intel FPGA platforms.

Diagnosis of Brain Tumor Using Nano Segmentation and Advanced-Convolutional Neural Networks Classification

2021 ◽  
Vol 11 (12) ◽  
pp. 2907-2917
Author(s):  
P. V. Deepa ◽  
S. Joseph Jawhar ◽  
J. Merry Geisa
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Brain Tumours ◽  
Malignant Tumour ◽  
Training Data ◽  
Correct Identification ◽  
Imaging Model ◽  
And Performance ◽  
Percent Accuracy ◽  
High Level

The field of nanotechnology has lately acquired prominence according to the raised level of correct identification and performance in the patients using Computer-Aided Diagnosis (CAD). Nano-scale imaging model enables for a high level of precision and accuracy in determining if a brain tumour is malignant or benign. This contributes to people with brain tumours having a better standard of living. In this study, We present a revolutionary Semantic nano-segmentation methodology for the nanoscale classification of brain tumours. The suggested Advanced-Convolutional Neural Networks-based Semantic Nano-segmentation will aid radiologists in detecting brain tumours even when lesions are minor. ResNet-50 was employed in the suggested Advanced-Convolutional Neural Networks (A-CNN) approach. The tumour image is partitioned using Semantic Nano-segmentation, that has averaged dice and SSIM values of 0.9704 and 0.2133, correspondingly. The input is a nano-image, and the tumour image is segmented using Semantic Nano-segmentation, which has averaged dice and SSIM values of 0.9704 and 0.2133, respectively. The suggested Semantic nano segments achieves 93.2 percent and 92.7 percent accuracy for benign and malignant tumour pictures, correspondingly. For malignant or benign pictures, The accuracy of the A-CNN methodology of correct segmentation is 99.57 percent and 95.7 percent, respectively. This unique nano-method is designed to detect tumour areas in nanometers (nm) and hence accurately assess the illness. The suggested technique’s closeness to with regard to True Positive values, the ROC curve implies that it outperforms earlier approaches. A comparison analysis is conducted on ResNet-50 using testing and training data at rates of 90%–10%, 80%–20%, and 70%–30%, corresponding, indicating the utility of the suggested work.

Sign in / Sign up

Export Citation Format

Share Document