scholarly journals DNNV: A Framework for Deep Neural Network Verification

2021 ◽  
pp. 137-150
Author(s):  
David Shriver ◽  
Sebastian Elbaum ◽  
Matthew B. Dwyer
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Application Development ◽  
Input And Output ◽  
Verification Algorithms ◽  
The Many ◽  
The One ◽  
Network Verification ◽  
Input Format

AbstractDespite the large number of sophisticated deep neural network (DNN) verification algorithms, DNN verifier developers, users, and researchers still face several challenges. First, verifier developers must contend with the rapidly changing DNN field to support new DNN operations and property types. Second, verifier users have the burden of selecting a verifier input format to specify their problem. Due to the many input formats, this decision can greatly restrict the verifiers that a user may run. Finally, researchers face difficulties in re-using benchmarks to evaluate and compare verifiers, due to the large number of input formats required to run different verifiers. Existing benchmarks are rarely in formats supported by verifiers other than the one for which the benchmark was introduced. In this work we present DNNV, a framework for reducing the burden on DNN verifier researchers, developers, and users. DNNV standardizes input and output formats, includes a simple yet expressive DSL for specifying DNN properties, and provides powerful simplification and reduction operations to facilitate the application, development, and comparison of DNN verifiers. We show how DNNV increases the support of verifiers for existing benchmarks from 30% to 74%.

scholarly journals Novel Deep Neural Network Model for Handwritten Digit Classification and Recognition

2021 ◽  
pp. 30-35
Author(s):  
Ayush Kumar Agrawal ◽  
Vineet Kumar Awasthi
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
Research Work ◽  
Training Sample ◽  
Output Layer ◽  
Input And Output ◽  
Handwritten Digit

Deep neural network is a technique of deep learning, where deep neural network model have multiple hidden layers with input and output layer, but artificial neural network have single hidden layer between input and output layer. The use of multiple hidden layers in deep neural network is to improve the performance of model and achieving the higher accuracy compare to machine learning models and their accuracy. The field of pattern recognition is mostly used by the researchers for their research work. There are lots of pattern are available in the field of pattern recognition like: handwritten digits, characters, images, faces, sound, speech etc. In this paper we have concentrated on handwritten digits classification and recognition. For handwritten digit datasets, we have used commonly known Arkiv Digital Sweden (ARDIS) [1] dataset and United State postal service (USPS) [7] dataset. ARDIS dataset is a collection of 7600 samples, where 6600 used as training samples and 1000 used as testing samples. USPS dataset is a collection of 10000 image samples where 7291 samples are used as training sample and 2007 samples are used as testing samples. In this paper we have implemented the proposed deep neural network technique for the classification and recognition of the ARDIS and USPS dataset. The proposed model has collection of 6 layers with relu and softmax activation function. After implementing model, 98.70% testing and 99.76% training accuracy for ARDIS samples achieved, which is higher than previous research accuracy. Also 98.22% training and 93.01%testing accuracy with USPS samples dataset has been achieved. The results represents the performance of deep neural networks have been outstanding compare to other previous techniques.

Building on prior knowledge without building it in

2017 ◽  
Vol 40 ◽  
Author(s):  
Steven S. Hansen ◽  
Andrew K. Lampinen ◽  
Gaurav Suri ◽  
James L. McClelland
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Prior Knowledge ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Network Models ◽  
Causal Models ◽  
Neural Network Models ◽  
Start Up ◽  
The Many

AbstractLake et al. propose that people rely on “start-up software,” “causal models,” and “intuitive theories” built using compositional representations to learn new tasks more efficiently than some deep neural network models. We highlight the many drawbacks of a commitment to compositional representations and describe our continuing effort to explore how the ability to build on prior knowledge and to learn new tasks efficiently could arise through learning in deep neural networks.

scholarly journals Using Deep Neural Network to Diagnose Thyroid Nodules on Ultrasound in Patients With Hashimoto’s Thyroiditis

2021 ◽  
Vol 11 ◽  
Author(s):  
Yiqing Hou ◽  
Chao Chen ◽  
Lu Zhang ◽  
Wei Zhou ◽  
Qinyang Lu ◽  
...  
Keyword(s):  
Neural Network ◽  
Hashimoto’S Thyroiditis ◽  
High Performance ◽  
Deep Neural Network ◽  
Thyroid Nodules ◽  
Hashimoto's Thyroiditis ◽  
Training Set ◽  
Test Set ◽  
The One ◽  
Benign Nodules

ObjectiveThe aim of this study is to develop a model using Deep Neural Network (DNN) to diagnose thyroid nodules in patients with Hashimoto’s Thyroiditis.MethodsIn this retrospective study, we included 2,932 patients with thyroid nodules who underwent thyroid ultrasonogram in our hospital from January 2017 to August 2019. 80% of them were included as training set and 20% as test set. Nodules suspected for malignancy underwent FNA or surgery for pathological results. Two DNN models were trained to diagnose thyroid nodules, and we chose the one with better performance. The features of nodules as well as parenchyma around nodules will be learned by the model to achieve better performance under diffused parenchyma. 10-fold cross-validation and an independent test set were used to evaluate the performance of the algorithm. The performance of the model was compared with that of the three groups of radiologists with clinical experience of <5 years, 5–10 years, >10 years respectively.ResultsIn total, 9,127 images were collected from 2,932 patients with 7,301 images for the training set and 1,806 for the test set. 56% of the patients enrolled had Hashimoto’s Thyroiditis. The model achieved an AUC of 0.924 for distinguishing malignant and benign nodules in the test set. It showed similar performance under diffused thyroid parenchyma and normal parenchyma with sensitivity of 0.881 versus 0.871 (p = 0.938) and specificity of 0.846 versus 0.822 (p = 0.178). In patients with HT, the model achieved an AUC of 0.924 to differentiate malignant and benign nodules which was significantly higher than that of the three groups of radiologists (AUC = 0.824, 0.857, 0.863 respectively, p < 0.05).ConclusionThe model showed high performance in diagnosing thyroid nodules under both normal and diffused parenchyma. In patients with Hashimoto’s Thyroiditis, the model showed a better performance compared to radiologists with various years of experience.

Costumes and Choreography from Bodenwieser's Trunk: The Coat as Affective Memory

2019 ◽  
Vol 37 (1) ◽  
pp. 89-110
Author(s):  
Rachel Fensham
Keyword(s):  
Modern Dance ◽  
Human Condition ◽  
Personal Life ◽  
Creative Thought ◽  
Cain And Abel ◽  
Embodied Research ◽  
The Many ◽  
The One ◽  
Material Evidence ◽  
Selection Of

The Viennese modern choreographer Gertrud Bodenwieser's black coat leads to an analysis of her choreography in four main phases – the early European career; the rise of Nazism; war's brutality; and postwar attempts at reconciliation. Utilising archival and embodied research, the article focuses on a selection of Bodenwieser costumes that survived her journey from Vienna, or were remade in Australia, and their role in the dramaturgy of works such as Swinging Bells (1926), The Masks of Lucifer (1936, 1944), Cain and Abel (1940) and The One and the Many (1946). In addition to dance history, costume studies provides a distinctive way to engage with the question of what remains of performance, and what survives of the historical conditions and experience of modern dance-drama. Throughout, Hannah Arendt's book The Human Condition (1958) provides a critical guide to the acts of reconstruction undertaken by Bodenwieser as an émigré choreographer in the practice of her craft, and its ‘materializing reification’ of creative thought. As a study in affective memory, information regarding Bodenwieser's personal life becomes interwoven with the author's response to the material evidence of costumes, oral histories and documents located in various Australian archives. By resurrecting the ‘dead letters’ of this choreography, the article therefore considers how dance costumes offer the trace of an artistic resistance to totalitarianism.

Estimating Pigment Concentrations from Spectral Images Using an Encoder‐Decoder Neural Network

2020 ◽  
Vol 64 (3) ◽  
pp. 30502-1-30502-15
Author(s):  
Kensuke Fukumoto ◽  
Norimichi Tsumura ◽  
Roy Berns
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Absorption Coefficient ◽  
Spectral Data ◽  
High Accuracy ◽  
Pigment Concentration ◽  
Scattering Coefficient ◽  
A Value ◽  
Input And Output ◽  
Pigment Concentrations

Abstract A method is proposed to estimate the concentration of pigments mixed in a painting, using the encoder‐decoder model of neural networks. The model is trained to output a value that is the same as its input, and its middle output extracts a certain feature as compressed information about the input. In this instance, the input and output are spectral data of a painting. The model is trained with pigment concentration as the middle output. A dataset containing the scattering coefficient and absorption coefficient of each of 19 pigments was used. The Kubelka‐Munk theory was applied to the coefficients to obtain many patterns of synthetic spectral data, which were used for training. The proposed method was tested using spectral images of 33 paintings, which showed that the method estimates, with high accuracy, the concentrations that have a similar spectrum of the target pigments.

AFRICAN WOMEN AND FORBIDDEN GROUNDS: FEMALE SEXUALITY AND SELF-DETERMINATION IN AFRICAN LITERATURE

Imbizo ◽  
2017 ◽  
Vol 7 (1) ◽  
pp. 40-54
Author(s):  
Oyeh O. Otu
Keyword(s):  
Female Sexuality ◽  
Sense Of Self ◽  
African Literature ◽  
The Other ◽  
Self Determination ◽  
African Women ◽  
The Core ◽  
The Many ◽  
The One ◽  
Sexual Repression

This article examines how female conditioning and sexual repression affect the woman’s sense of self, womanhood, identity and her place in society. It argues that the woman’s body is at the core of the many sites of gender struggles/ politics. Accordingly, the woman’s body must be decolonised for her to attain true emancipation. On the one hand, this study identifies the grave consequences of sexual repression, how it robs women of their freedom to choose whom to love or marry, the freedom to seek legal redress against sexual abuse and terror, and how it hinders their quest for self-determination. On the other hand, it underscores the need to give women sexual freedom that must be respected and enforced by law for the overall good of society.

Sign in / Sign up

Export Citation Format

Share Document