scholarly journals Freely scalable and reconfigurable optical hardware for deep learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Liane Bernstein ◽  
Alexander Sludds ◽  
Ryan Hamerly ◽  
Vivienne Sze ◽  
Joel Emer ◽  
...  
Keyword(s):  
Neural Network ◽  
Energy Consumption ◽  
Data Transfer ◽  
Power Delivery ◽  
Optical Data ◽  
Optical Multicast ◽  
Optical Neural Network ◽  
Fully Connected ◽  
Management Power

AbstractAs deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available compute power; however, efforts to continue to scale electronic processors are impeded by the costs of communication, thermal management, power delivery and clocking. To improve scalability, we propose a digital optical neural network (DONN) with intralayer optical interconnects and reconfigurable input values. The path-length-independence of optical energy consumption enables information locality between a transmitter and a large number of arbitrarily arranged receivers, which allows greater flexibility in architecture design to circumvent scaling limitations. In a proof-of-concept experiment, we demonstrate optical multicast in the classification of 500 MNIST images with a 3-layer, fully-connected network. We also analyze the energy consumption of the DONN and find that digital optical data transfer is beneficial over electronics when the spacing of computational units is on the order of $$>10\,\upmu $$ > 10 μ m.

scholarly journals Classification of Brain Tumor using Convolutional Neural Networks

2020 ◽  
Vol 9 (3) ◽  
pp. 2841-2845
Keyword(s):  
Neural Network ◽  
Brain Tumor ◽  
Convolutional Neural Network ◽  
Medical Science ◽  
Activation Functions ◽  
Case Scenario ◽  
Aggressive Disease ◽  
Fully Connected ◽  
The Brain

In medical science, brain tumor is the most common and aggressive disease and is known to be risk factors that have been confirmed by research. A brain tumor is the anomalous development of cell inside the brain. One conventional strategy to separate brain tumors is by reviewing the MRI pictures of the patient's mind. In this paper, we have designed a Convolutional Neural Network (CNN) to perceive whether the image contains tumor or not. We have designed 5 different CNN and examined each design on the basis of convolution layers, max-pooling, and flattening layers and activation functions. In each design we have made some changes on layers i.e. using different pooling layers in design 2 and 4, using different activation functions in design 2 and 3, and adding more Fully Connected layers in design 5. We examine their results and compare it with other designs. After comparing their results we find a best design out of 5 based on their accuracy. Utilizing our Convolutional neural network, we could accomplish a training accuracy and validation accuracy of design 3 at 100 epochs is 99.99% and 92.34%, best case scenario.

scholarly journals Neural networks for classification of strokes in electrical impedance tomography on a 3D head model

2022 ◽  
Vol 4 (4) ◽  
pp. 1-22
Author(s):  
Valentina Candiani ◽  
◽  
Matteo Santacesaria ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Electrical Impedance Tomography ◽  
Electrical Impedance ◽  
Network Architectures ◽  
Impedance Tomography ◽  
Average Accuracy ◽  
Neural Network Architectures ◽  
Fully Connected

<abstract><p>We consider the problem of the detection of brain hemorrhages from three-dimensional (3D) electrical impedance tomography (EIT) measurements. This is a condition requiring urgent treatment for which EIT might provide a portable and quick diagnosis. We employ two neural network architectures - a fully connected and a convolutional one - for the classification of hemorrhagic and ischemic strokes. The networks are trained on a dataset with $ 40\, 000 $ samples of synthetic electrode measurements generated with the complete electrode model on realistic heads with a 3-layer structure. We consider changes in head anatomy and layers, electrode position, measurement noise and conductivity values. We then test the networks on several datasets of unseen EIT data, with more complex stroke modeling (different shapes and volumes), higher levels of noise and different amounts of electrode misplacement. On most test datasets we achieve $ \geq 90\% $ average accuracy with fully connected neural networks, while the convolutional ones display an average accuracy $ \geq 80\% $. Despite the use of simple neural network architectures, the results obtained are very promising and motivate the applications of EIT-based classification methods on real phantoms and ultimately on human patients.</p></abstract>

scholarly journals A Novel Architecture to Classify Histopathology Images Using Convolutional Neural Networks

2020 ◽  
Vol 10 (8) ◽  
pp. 2929 ◽  
Author(s):  
Ibrahem Kandel ◽  
Mauro Castelli
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
State Of The Art ◽  
Treatment Plan ◽  
Tissue Structure ◽  
Activation Functions ◽  
Proposed Model ◽  
Histopathology Images ◽  
Fully Connected

Histopathology is the study of tissue structure under the microscope to determine if the cells are normal or abnormal. Histopathology is a very important exam that is used to determine the patients’ treatment plan. The classification of histopathology images is very difficult to even an experienced pathologist, and a second opinion is often needed. Convolutional neural network (CNN), a particular type of deep learning architecture, obtained outstanding results in computer vision tasks like image classification. In this paper, we propose a novel CNN architecture to classify histopathology images. The proposed model consists of 15 convolution layers and two fully connected layers. A comparison between different activation functions was performed to detect the most efficient one, taking into account two different optimizers. To train and evaluate the proposed model, the publicly available PatchCamelyon dataset was used. The dataset consists of 220,000 annotated images for training and 57,000 unannotated images for testing. The proposed model achieved higher performance compared to the state-of-the-art architectures with an AUC of 95.46%.

scholarly journals Image Classification of Beef and Pork Using Convolutional Neural Network in Keras Framework

2021 ◽  
Vol 5 (02) ◽  
pp. 245-248
Author(s):  
Salsa Bila ◽  
Anwar Fitrianto ◽  
Bagus Sartono
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Activation Function ◽  
Food Ingredient ◽  
Model Classification ◽  
Regularization Techniques ◽  
The Difference ◽  
Fully Connected ◽  
Selection Of

Beef is a food ingredient that has a high selling value. Such high prices make some people manipulate sales in markets or other shopping venues, such as mixing beef and pork. The difference between pork and beef is actually from the color and texture of the meat. However, many people do not understand these differences yet. In addition to socialization related to understanding the differences between the two types of meat, another solution is to create a technology that can recognize and differentiate pork and beef. That is what underlies this research to build a system that can classify the two types of meat. Convolutional Neural Network (CNN) is one of the Deep Learning methods and the development of Artificial Intelligence science that can be applied to classify images. Several regularization techniques include Dropout, L2, and Max-Norm were applied to the model and compared to obtain the best classification results and may predict new data accurately. It has known that the highest accuracy of 97.56% obtained from the CNN model by applying the Dropout technique using 0.7 supported by hyperparameters such as Adam's optimizer, 128 neurons in the fully connected layer, ReLu activation function, and 3 fully connected layers. The reason that also underlies the selection of the model is the low error rate of the model, which is only 0.111.Keywords: Beef and Pork, Model, Classification, CNN

Deep learning for quark–gluon plasma detection in the CBM experiment

2020 ◽  
Vol 35 (33) ◽  
pp. 2043002 ◽  
Author(s):  
Fedor Sergeev ◽  
Elena Bratkovskaya ◽  
Ivan Kisel ◽  
Iouri Vassiliev
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Quark Gluon Plasma ◽  
Heavy Ion ◽  
Gluon Plasma ◽  
Ion Collisions ◽  
Validation Set ◽  
Fully Connected

Classification of processes in heavy-ion collisions in the CBM experiment (FAIR/GSI, Darmstadt) using neural networks is investigated. Fully-connected neural networks and a deep convolutional neural network are built to identify quark–gluon plasma simulated within the Parton-Hadron-String Dynamics (PHSD) microscopic off-shell transport approach for central Au+Au collision at a fixed energy. The convolutional neural network outperforms fully-connected networks and reaches 93% accuracy on the validation set, while the remaining only 7% of collisions are incorrectly classified.

scholarly journals Classification of tectonic and non-tectonic seismicity based on convolutional neural network

2020 ◽  
Vol 224 (1) ◽  
pp. 191-198
Author(s):  
Xinliang Liu ◽  
Tao Ren ◽  
Hongfeng Chen ◽  
Yufeng Chen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Proposed Model ◽  
Single Station ◽  
Using Data ◽  
Fully Connected

SUMMARY In this paper, convolutional neural networks (CNNs) were used to distinguish between tectonic and non-tectonic seismicity. The proposed CNNs consisted of seven convolutional layers with small kernels and one fully connected layer, which only relied on the acoustic waveform without extracting features manually. For a single station, the accuracy of the model was 0.90, and the event accuracy could reach 0.93. The proposed model was tested using data from January 2019 to August 2019 in China. The event accuracy could reach 0.92, showing that the proposed model could distinguish between tectonic and non-tectonic seismicity.

scholarly journals A Novel Deep Neural Network for Robust Detection of Seizures Using EEG Signals

2020 ◽  
Vol 2020 ◽  
pp. 1-9 ◽  
Author(s):  
Wei Zhao ◽  
Wenbing Zhao ◽  
Wenfeng Wang ◽  
Xiaolu Jiang ◽  
Xiaodong Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Model Performance ◽  
Classification Problem ◽  
Automatic Identification ◽  
Robust Detection ◽  
Heavy Burden ◽  
The University ◽  
Fully Connected

The detection of recorded epileptic seizure activity in electroencephalogram (EEG) segments is crucial for the classification of seizures. Manual recognition is a time-consuming and laborious process that places a heavy burden on neurologists, and hence, the automatic identification of epilepsy has become an important issue. Traditional EEG recognition models largely depend on artificial experience and are of weak generalization ability. To break these limitations, we propose a novel one-dimensional deep neural network for robust detection of seizures, which composes of three convolutional blocks and three fully connected layers. Thereinto, each convolutional block consists of five types of layers: convolutional layer, batch normalization layer, nonlinear activation layer, dropout layer, and max-pooling layer. Model performance is evaluated on the University of Bonn dataset, which achieves the accuracy of 97.63%∼99.52% in the two-class classification problem, 96.73%∼98.06% in the three-class EEG classification problem, and 93.55% in classifying the complicated five-class problem.

scholarly journals Classification of Heart Sounds Using Convolutional Neural Network

2020 ◽  
Vol 10 (11) ◽  
pp. 3956 ◽  
Author(s):  
Fan Li ◽  
Hong Tang ◽  
Shang Shang ◽  
Klaus Mathiak ◽  
Fengyu Cong
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Signal To Noise Ratio ◽  
Class Imbalance ◽  
Heart Sounds ◽  
Feature Maps ◽  
Objective Classification ◽  
Sensitivity Specificity ◽  
Fully Connected

Heart sounds play an important role in the diagnosis of cardiac conditions. Due to the low signal-to-noise ratio (SNR), it is problematic and time-consuming for experts to discriminate different kinds of heart sounds. Thus, objective classification of heart sounds is essential. In this study, we combined a conventional feature engineering method with deep learning algorithms to automatically classify normal and abnormal heart sounds. First, 497 features were extracted from eight domains. Then, we fed these features into the designed convolutional neural network (CNN), in which the fully connected layers that are usually used before the classification layer were replaced with a global average pooling layer to obtain global information about the feature maps and avoid overfitting. Considering the class imbalance, the class weights were set in the loss function during the training process to improve the classification algorithm’s performance. Stratified five-fold cross-validation was used to evaluate the performance of the proposed method. The mean accuracy, sensitivity, specificity and Matthews correlation coefficient observed on the PhysioNet/CinC Challenge 2016 dataset were 86.8%, 87%, 86.6% and 72.1% respectively. The proposed algorithm’s performance achieves an appropriate trade-off between sensitivity and specificity.

Sign in / Sign up

Export Citation Format

Share Document