The use of neural networks in parallel software systems

1989 ◽  
Vol 31 (4-5) ◽  
pp. 485-495 ◽  
Author(s):  
G. Fox ◽  
W. Furmanski ◽  
J. Koller
Keyword(s):  
Neural Networks ◽  
Software Systems ◽  
Parallel Software

Guest Editor’s Introduction: Software Mathematical Models for Human Understanding

2020 ◽  
Vol 30 (10) ◽  
pp. 1371-1374
Author(s):  
Iaakov Exman
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Systems Design ◽  
Difficult Problem ◽  
The Other ◽  
Software Systems ◽  
Special Issue ◽  
Software Developers ◽  
Human Understanding ◽  
Introductory Paper

The unrelenting trend of larger and larger sizes of Software Systems and data has made software comprehensibility an increasingly difficult problem. However, a tacit consensus that human understanding of software is essential for most software related activities, stimulated software developers to embed comprehensibility in their systems’ design. On the other hand, recent empirical successes of Deep Learning neural networks, in several application areas, seem to challenge the tacit consensus: is software comprehensibility a necessity, or just superfluous? This introductory paper, to the 2020 special issue on Theoretical Software Engineering, offers reasons justifying our standpoint on the referred controversy. This paper also points out to specific techniques enabling Human Understanding of software systems relevant to this issue’s papers.

scholarly journals A Model Reduction Method for Parallel Software Testing

2013 ◽  
Vol 2013 ◽  
pp. 1-13 ◽  
Author(s):  
Tao Sun ◽  
Xinming Ye
Keyword(s):  
Model Reduction ◽  
Reduction Method ◽  
Formal Model ◽  
Equivalent Model ◽  
Scale Model ◽  
Parallel Structure ◽  
Software Systems ◽  
System Specification ◽  
Parallel Software ◽  
Coloured Petri Net

Modeling and testing for parallel software systems are very difficult, because the number of states and execution sequences expands significantly caused by parallel behaviors. In this paper, a model reduction method based on Coloured Petri Net (CPN) is shown, which could generate a functionality-equivalent and trace-equivalent model with smaller scale. Model-based testing for parallel software systems becomes much easier after the model is reduced by the reduction method. Specifically, a formal model for software system specification is constructed based on CPN. Then the places in the model are divided into input places, output places, and internal places; the transitions in the model are divided into input transitions, output transitions, and internal transitions. Internal places and internal transitions could be reduced if preconditions are matching, and some other operations should be done for functionality equivalence and trace equivalence. If the place and the transition are in a parallel structure, then many execution sequences will be removed from the state space. We have proved the equivalence and have analyzed the reduction effort, so that we could get the same testing result with much lower testing workload. Finally, some practices and a performance analysis show that the method is effective.

Demand Forecasting of Short Life Span Products

2011 ◽  
pp. 124-143
Author(s):  
Narendra S. Chaudhari ◽  
Xue-Ming Yuan
Keyword(s):  
Neural Networks ◽  
Life Span ◽  
Optimization Problems ◽  
Demand Forecasting ◽  
Small World ◽  
Software Systems ◽  
Short Life ◽  
Short Life Span ◽  
Typical Data ◽  
Forecasting System

This chapter briefly reviews forecasting features of typical data mining software, and then presents the salient features of SIMForecaster, a forecasting system developed at the Singapore Institute of Manufacturing Technology. SIMForecaster has successfully been used for many important forecasting problems in industry. Demand forecasting of short life span products involves unique issues and challenges that cannot be fully tackled in existing software systems like SIMForecaster. To introduce these problems, we give three case studies for short life span products, and identify the issues and problems for demand forecasting of short life span products. We identify specific soft computing techniques, namely small world theory, memes theory, and neural networks with special structures, such as binary neural networks (BNNs), bidirectional segmented memory (BSM) recurrent neural networks, and longshort- term-memory (LSTM) networks for solving these problems. We suggest that, in addition to these neural network techniques, integrated demand forecasting systems for handling optimization problems involved in short life span products would also need some techniques in evolutionary computing as well as genetic algorithms.

scholarly journals An SMT-Based Approach for Verifying Binarized Neural Networks

2021 ◽  
pp. 203-222
Author(s):  
Guy Amir ◽  
Haoze Wu ◽  
Clark Barrett ◽  
Guy Katz
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Formal Verification ◽  
Software Systems ◽  
Network Architectures ◽  
Security Issues ◽  
The Neural Network ◽  
Network Verification ◽  
Promising Avenue

AbstractDeep learning has emerged as an effective approach for creating modern software systems, with neural networks often surpassing hand-crafted systems. Unfortunately, neural networks are known to suffer from various safety and security issues. Formal verification is a promising avenue for tackling this difficulty, by formally certifying that networks are correct. We propose an SMT-based technique for verifying binarized neural networks — a popular kind of neural network, where some weights have been binarized in order to render the neural network more memory and energy efficient, and quicker to evaluate. One novelty of our technique is that it allows the verification of neural networks that include both binarized and non-binarized components. Neural network verification is computationally very difficult, and so we propose here various optimizations, integrated into our SMT procedure as deduction steps, as well as an approach for parallelizing verification queries. We implement our technique as an extension to the Marabou framework, and use it to evaluate the approach on popular binarized neural network architectures.

Sign in / Sign up

Export Citation Format

Share Document