Improving Classification Neural Networks by using Absolute activation function (MNIST/LeNET-5 example)
This is an incremental improvement for neural network practitioners seeking more stable activations in classification tasks.
The paper tackles the problem of vanishing/exploding gradients in deep neural networks by proposing the Absolute activation function, showing it reduces parameter count by 15% while improving MNIST accuracy from 99.2% to 99.4% compared to ReLU/Tanh baselines.
The paper discusses the use of the Absolute activation function in classification neural networks. An examples are shown of using this activation function in simple and more complex problems. Using as a baseline LeNet-5 network for solving the MNIST problem, the efficiency of Absolute activation function is shown in comparison with the use of Tanh, ReLU and SeLU activations. It is shown that in deep networks Absolute activation does not cause vanishing and exploding gradients, and therefore Absolute activation can be used in both simple and deep neural networks. Due to high volatility of training networks with Absolute activation, a special modification of ADAM training algorithm is used, that estimates lower bound of accuracy at any test dataset using validation dataset analysis at each training epoch, and uses this value to stop/decrease learning rate, and re-initializes ADAM algorithm between these steps. It is shown that solving the MNIST problem with the LeNet-like architectures based on Absolute activation allows to significantly reduce the number of trained parameters in the neural network with improving the prediction accuracy.