DropWeak: A novel regularization method of neural networks
نویسندگان
چکیده
منابع مشابه
A Novel Method for Designing and Optimization of Networks
In this paper, system planning network is formulated with mixed-integer programming. Two meta-heuristic procedures are considered for this problem. The cost function of this problem consists of the capital investment cost in discrete form, the cost of transmission losses and the power generation costs. The DC load flow equations for the network are embedded in the constraints of the mathematica...
متن کاملRegularization for Neural Networks
Research into regularization techniques is motivated by the tendency of neural networks to to learn the specifics of the dataset it was trained on rather than learning general features that are applicable to unseen data. This is known as overfitting. The goal of any supervised machine learning task is to approximate a function that maps inputs to outputs, given a dataset of examples and labels....
متن کاملGraphConnect: A Regularization Framework for Neural Networks
Deep neural networks have proved very successful in domains where large training sets are available, but when the number of training samples is small, their performance suffers from overfitting. Prior methods of reducing overfitting such as weight decay, Dropout and DropConnect are data-independent. This paper proposes a new method, GraphConnect, that is data-dependent, and is motivated by the ...
متن کاملConstructive Neural Networks with Regularization
In this paper we present a regularization approach to the training of all the network weights in cascadecorrelation type constructive neural networks. Especially, the case of regularizing the output neuron of the network is presented. In this case, the output weights are trained by employing a regularized objective function containing a penalty term which is proportional to the weight values of...
متن کاملA Novel Method for the Evolution of Artificial Neural Networks
Evolving Artificial Neural Networks (ANN) is a new method that, except of the training, was applied to the structure optimization problem. This method combines ideas from both the evolution and adaptive signal processing techniques. An ANN is considered as a layered array of non-linear systems (the neuron models), each producing on its output a local error. Each of these errors is minimized usi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Procedia Computer Science
سال: 2018
ISSN: 1877-0509
DOI: 10.1016/j.procs.2018.01.103