Inspired by biological neurons, the activation functions play an essential part in learning process of any artificial neural network (ANN) commonly used many real-world problems. Various have been proposed literature for classification as well regression tasks. In this work, we survey that employed past current state-of-the-art. particular, present various developments over years and advantages...

Biophysical models predicting the relaxation of cardiomyocytes1 take into account a lot more variables than regression models analysing the left ventricular relaxation in human and animal hearts. These isochoric (isovolumic) pressure decay curves are often described by an exponential2 or logistic3 time constant. Both these three–parametric regression models are regarded unsatisfactory4, 5. Cons...

We discuss the behaviour of vertices and inflexions of one-parameter families of plane curves which include a singular member. These arise a sections of smooth surfaces by families of planes parallel to the tangent plane at a given point. We cover all the generic cases, namely elliptic (A1), umbilic (A1), hyperbolic (A1), parabolic (A2) and cusp of Gauss (A3) points. This work is preliminary to...

In this paper, we study global stabilization and synchronization of n-scroll chaotic attractors for a modified Chua’s circuit with hyperbolic tangent function using feedback control strategy. In particular, for any given equilibrium point of the modified Chua’s circuit, we design simple and explicit controllers to globally exponentially stabilize the system. Simple controllers are also designed...