Purpose–Many strategies have been put forward for training deep network models,however,stacking of several layers of non-linearities typically results in poor propagation of gradients and activations.The purpose of t...Purpose–Many strategies have been put forward for training deep network models,however,stacking of several layers of non-linearities typically results in poor propagation of gradients and activations.The purpose of this paper is to explore the use of two steps strategy where initial deep learning model is obtained first by unsupervised learning and then optimizing the initial deep learning model by fine tuning.A number of fine tuning algorithms are explored in this work for optimizing deep learning models.This includes proposing a new algorithm where Backpropagation with adaptive gain algorithm is integrated with Dropout technique and the authors evaluate its performance in the fine tuning of the pretrained deep network.Design/methodology/approach–The parameters of deep neural networks are first learnt using greedy layer-wise unsupervised pretraining.The proposed technique is then used to perform supervised fine tuning of the deep neural network model.Extensive experimental study is performed to evaluate the performance of the proposed fine tuning technique on three benchmark data sets:USPS,Gisette and MNIST.The authors have tested the approach on varying size data sets which include randomly chosen training samples of size 20,50,70 and 100 percent from the original data set.Findings–Through extensive experimental study,it is concluded that the two steps strategy and the proposed fine tuning technique significantly yield promising results in optimization of deep network models.Originality/value–This paper proposes employing several algorithms for fine tuning of deep network model.A new approach that integrates adaptive gain Backpropagation(BP)algorithm with Dropout technique is proposed for fine tuning of deep networks.Evaluation and comparison of various algorithms proposed for fine tuning on three benchmark data sets is presented in the paper.展开更多
To solve the cosmological constant fine tuning problem,we investigate an(n+1)-dimensional generalized Randall-Sundrum brane world scenario with two(n−1)-branes instead of two 3-branes.Adopting an anisotropic metric an...To solve the cosmological constant fine tuning problem,we investigate an(n+1)-dimensional generalized Randall-Sundrum brane world scenario with two(n−1)-branes instead of two 3-branes.Adopting an anisotropic metric ansatz,we obtain the positive effective cosmological constantΩeff of order 10−124 and only require a solution≃50−80.Meanwhile,both the visible and hidden branes are stable because their tensions are positive.Therefore,the fine tuning problem can be solved quite well.Furthermore,the Hubble parameter H1(z)as a function of redshift z is in good agreement with the cosmic chronometers dataset.The evolution of the universe naturally shifts from deceleration to acceleration.This suggests that the evolution of the universe is intrinsically an extra-dimensional phenomenon.It can be regarded as a dynamic model of dark energy that is driven by the evolution of the extra dimensions on the brane.展开更多
文摘Purpose–Many strategies have been put forward for training deep network models,however,stacking of several layers of non-linearities typically results in poor propagation of gradients and activations.The purpose of this paper is to explore the use of two steps strategy where initial deep learning model is obtained first by unsupervised learning and then optimizing the initial deep learning model by fine tuning.A number of fine tuning algorithms are explored in this work for optimizing deep learning models.This includes proposing a new algorithm where Backpropagation with adaptive gain algorithm is integrated with Dropout technique and the authors evaluate its performance in the fine tuning of the pretrained deep network.Design/methodology/approach–The parameters of deep neural networks are first learnt using greedy layer-wise unsupervised pretraining.The proposed technique is then used to perform supervised fine tuning of the deep neural network model.Extensive experimental study is performed to evaluate the performance of the proposed fine tuning technique on three benchmark data sets:USPS,Gisette and MNIST.The authors have tested the approach on varying size data sets which include randomly chosen training samples of size 20,50,70 and 100 percent from the original data set.Findings–Through extensive experimental study,it is concluded that the two steps strategy and the proposed fine tuning technique significantly yield promising results in optimization of deep network models.Originality/value–This paper proposes employing several algorithms for fine tuning of deep network model.A new approach that integrates adaptive gain Backpropagation(BP)algorithm with Dropout technique is proposed for fine tuning of deep networks.Evaluation and comparison of various algorithms proposed for fine tuning on three benchmark data sets is presented in the paper.
基金Supported by State Key Program of National Natural Science Foundation of China(11535005)the National Natural Science Foundation of China(11647087),the Natural Science Foundation of Yangzhou Polytechnic Institute(201917)the Natural Science Foundation of Changzhou Institute of Technology(YN1509)。
文摘To solve the cosmological constant fine tuning problem,we investigate an(n+1)-dimensional generalized Randall-Sundrum brane world scenario with two(n−1)-branes instead of two 3-branes.Adopting an anisotropic metric ansatz,we obtain the positive effective cosmological constantΩeff of order 10−124 and only require a solution≃50−80.Meanwhile,both the visible and hidden branes are stable because their tensions are positive.Therefore,the fine tuning problem can be solved quite well.Furthermore,the Hubble parameter H1(z)as a function of redshift z is in good agreement with the cosmic chronometers dataset.The evolution of the universe naturally shifts from deceleration to acceleration.This suggests that the evolution of the universe is intrinsically an extra-dimensional phenomenon.It can be regarded as a dynamic model of dark energy that is driven by the evolution of the extra dimensions on the brane.