Generation of Two-Layer Monotonic Functions

نویسندگان

  • Yukihiro Kamada
  • Kiyonori Miyasaki
چکیده

The problem of implementing a class of functions with particular conditions by using monotonic multilayer functions is considered. A genetic algorithm is used to create monotonic functions of a certain class, and these are implemented with two-layer monotonic functions. The existence of a solution to the given problem suggests that from two monotone functions, a monotonic function with the same dimensions can be created. A new algorithm based on the genetic algorithm is proposed, which easily implemented two-layer monotonic functions of a specific class for up to six variables.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Numerical Investigation on the Unstable Flow in a Single Stage of an Axial Compressor

An unsteady two-dimensional finite-volume solver was developed based on Van Leer’s flux splitting algorithm in conjunction with “Monotonic Upstream Scheme for Conservation Laws (MUSCL)” limiters to improve the order of accuracy and the two-layer Baldwin-Lomax turbulence model was also implemented. Two test cases were prepared to validate the solver. The computed results were compared with the e...

متن کامل

Generation of Love Wave in a Media with Temperature Dependent Properties Over a Heterogeneous Substratum

The present paper deals with the generation of Love waves in a layer of finite thickness over an initially stressed heterogeneous semi-infinite media. The rigidity and density of the layer are functions of temperature, i.e. they are temperature dependent.  The lower substratum is an initially stressed medium and its rigidity and density vary linearly with the depth. The frequency relation of Lo...

متن کامل

GENERATION OF ENDURANCE TIME ACCELERATION FUNCTIONS USING THE WAVELET TRANSFORM

Endurance Time Acceleration Functions are specially predesigned intensifying excitation functions that their amplitude increases with time. On the other hand, wavelet transform is a mathematical tool that indicates time variations of frequency in a signal. In this paper, an approach is presented for generating endurance time acceleration functions (ETAFs) whose response spectrum is compatible w...

متن کامل

Handwritten Digit Recognition Using Multi-Layer Feedforward Neural Networks with Periodic and Monotonic Activation Functions

The problem of handwritten digit recognition is tackled by multi-layer feedforward neural networks with different types of neuronal activation functions. Three types of activation functions are adopted in the network, namely, the traditional sigmoid function, the sinusoidal function and a periodic function that can be considered as a combination of the first two functions. To speed up the learn...

متن کامل

Output Reachable Set Estimation and Verification for Multi-Layer Neural Networks

In this paper, the output reachable estimation and safety verification problems for multi-layer perceptron neural networks are addressed. First, a conception called maximum sensitivity in introduced and, for a class of multi-layer perceptrons whose activation functions are monotonic functions, the maximum sensitivity can be computed via solving convex optimization problems. Then, using a simula...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1211.0660  شماره 

صفحات  -

تاریخ انتشار 2012