The existed models work well only with the input values between theminimum and the maximum values

The existed models are less performant

We can’t model all the problems linearly

To create new type of artificial intelligence

Sigmoid

Cubic

Convex

Affine

Sinusoïdal

bias

avoidable bias

variance

human-level error

Pose estimation

Image classification

YOLO

Faster R-CNN

Dense neural networks

Siamese neural networks

Generative Adversarial Networks

Hopfield Networks

Second-order optimization methods

Grid Search

Gradient Descent

Fast Fourier Transform

Gradient Vanishing

Overfitting

Out-Of-Vocabulary (OOV) words

Limited generalization