Adaptive Rectified Linear Unit (AReLU) for Classification Problems to Solve Dying Problem in Deep Learning

A convolutional neural network (CNN) is a subset of machine learning as well as one of the different types of artificial neural networks that are used for different applications and data types. Activation functions (AFs) are used in this type of network to determine whether or not its neurons are activated. One non-linear AF named as Rectified Linear Units (ReLU) which involves a simple mathematical operations and it gives better performance. It avoids rectifying vanishing gradient problem that inherents older AFs like tanh and sigmoid. Additionally, it has less computational cost. Despite these advantages, it suffers from a problem called Dying problem. Several modifications have been appeared to address this problem, for example; Leaky ReLU (LReLU). The main concept of our algorithm is to improve the current LReLU activation functions in mitigating the dying problem on deep learning by using the readjustment of values (changing and decreasing value) of the loss function or cost function while number of epochs are increased. The model was trained on the MNIST dataset with 20 epochs and achieved lowest misclassification rate by 1.2%. While optimizing our proposed methods, we received comparatively better results in terms of simplicity, low computational cost, and with no hyperparameters.

Automated summary

A convolutional neural network (CNN) is a type of artificial neural network used for various applications. Activation functions, such as Rectified Linear Units (ReLU), are used to determine neuron activation. ReLU overcomes the vanishing gradient problem of older activation functions and has lower computational cost. However, it suffers from the dying problem, which can be mitigated by readjusting the loss function during training.