Simulated Annealing Algorithm for Deep Learning

Rere, L. M. Rasdi; Fanany, Mohamad Ivan; Arymurthy, Aniati Murni

doi:10.1016/j.procs.2015.12.114

Cited by 138 publications

(64 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this chapter we will show the experiment result on deep learning method, such as Convolutional Neural Network, Deep Belief Network, and Convolutional Neural Network Optimize with Simulated Annealing (SA) [16] and also compare the performance with proposed method. The experiment use handwritten Digit dataset from MNIST.…”

Section: Experiments Resultsmentioning

confidence: 99%

Particle Swarm Optimization (Pso) for Training Optimization on Convolutional Neural Network (Cnn)

Syulistyo

Purnomo

Rachmadi

et al. 2016

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

Neural network attracts plenty of researchers lately. Substantial number of renowned universities have developed neural network for various both academically and industrially applications. Neural network shows considerable performance on various purposes. Nevertheless, for complex applications, neural network’s accuracy significantly deteriorates. To tackle the aforementioned drawback, lot of researches had been undertaken on the improvement of the standard neural network. One of the most promising modifications on standard neural network for complex applications is deep learning method. In this paper, we proposed the utilization of Particle Swarm Optimization (PSO) in Convolutional Neural Networks (CNNs), which is one of the basic methods in deep learning. The use of PSO on the training process aims to optimize the results of the solution vectors on CNN in order to improve the recognition accuracy. The data used in this research is handwritten digit from MNIST. The experiments exhibited that the accuracy can be attained in 4 epoch is 95.08%. This result was better than the conventional CNN and DBN. The execution time was also almost similar to the conventional CNN. Therefore, the proposed method was a promising method.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Particle Swarm Optimization (Pso) for Training Optimization on Convolutional Neural Network (Cnn)

Syulistyo

Purnomo

Rachmadi

et al. 2016

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

show abstract

“…For general transfer functions h(x f ), (17) is a non-convex and non-linear optimization problem that is commonly solved using stochastic gradient decent, ant-colony optimization, and simulated anealling methods [37], [38], [39].…”

Section: Classic Extreme Learning Machinementioning

confidence: 99%

Risk-Averse Caching Policies for YouTube Content in Femtocell Networks using Density Forecasting

Hoiles

Tanzil

Krishnamurthy

2021

IEEE Trans. Cloud Comput.

View full text Add to dashboard Cite

The paper presents risk-neutral and risk-averse caching policies that can be deployed in a femtocell network with limited storage capacity to reduce the time delay of servicing content requests. The caching policies use a forecasting algorithm to estimate the cumulative distribution function of content requests based on the content features. Given the cumulative distribution function, a mixed-integer linear program is used to compute where to cache content in the femtocell network. The caching policies account for the uncertainty associated with estimating the content requests using the coherent Conditional Value-at-Risk (CVaR) measure. For a large number of content, a risk-neutral caching policy is constructed that accounts for both the content features and routing protocol that only requires the evaluation of a unimodular linear program. Using data from YouTube (comprising 25,000 videos) and the NS-3 simulator, the caching policies reduce the delay of retrieving content in femtocell networks compared with industry standard caching policies. Specifically, a 6% reduction in delay is achieved by accounting for the uncertainty, and a 60% reduction in delay is achieved if both the uncertainty and femtocell routing protocol are accounted for compared to the risk-neutral caching policy that neglects the routing protocol.

show abstract

“…As there are complex forms of logical judgement in the objective function, a conventional gradient based optimization algorithm can hardly meet the calculation conditions [24], so the SA algorithm is chosen to solve the objective function. The algorithm needs to input four parameters: T (initial high temperature), cool (cooling rate), lt (temperature drop threshold), and sampleset (sample database).…”

Section: Optimizing Algorithmmentioning

confidence: 99%

A System to Pre-Evaluate the Suitability of Energy-Saving Technology for Green Buildings

Fan

Zhao

2018

Sustainability

View full text Add to dashboard Cite

Rating systems for green buildings often give assessments from the perspective of the overall performance of a single building or architecture complex but rarely target specific green building technologies. As some of the rating systems are scored according to whether the technologies are used or not, some developers tend to pile up energy-saving technologies blindly just for the sake of certifications without considering their suitability for the application. Such behavior may lead to the failure of achieving the energy goals for green buildings. To solve this problem, a system that pre-evaluates the suitability of green building energy-saving technologies is devised based on modified TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) method, SA (simulated annealing) algorithm and unascertained theory-based data analysis method. By setting indices from technology performance, economy, human satisfaction aspects and by using the building prior information and measured database of technology usage, this system can make a quantifiable and multi-dimensional grading assessment for the target green building energy-saving technologies in the design stage. The system aims at helping the designer choose technologies in the design phase that best enhance the performance of the finished green building. It also helps prevent the sub-optimal performance of unsuitable technologies caused by the “pile up” behavior mentioned earlier. To verify this evaluation system, two building designs which use energy-recovery technology are evaluated, and the predicted performance for both designs matched the actual operation of the technology in the buildings themselves well.

show abstract

Simulated Annealing Algorithm for Deep Learning

Cited by 138 publications

References 9 publications

Particle Swarm Optimization (Pso) for Training Optimization on Convolutional Neural Network (Cnn)

Particle Swarm Optimization (Pso) for Training Optimization on Convolutional Neural Network (Cnn)

Risk-Averse Caching Policies for YouTube Content in Femtocell Networks using Density Forecasting

A System to Pre-Evaluate the Suitability of Energy-Saving Technology for Green Buildings

Contact Info

Product

Resources

About