Adam Optimization Algorithm for Wide and Deep Neural Network

Imran Khan Mohd Jais
Amelia Ritahani Ismail (International Islamic University Malaysia)
Syed Qamrun Nisa

Knowledge Engineering and Data Science
Vol 2, No 1 (2019)

The objective of this research is to evaluate the effects of Adam when used together with a wide and deep neural network. The dataset used was a diagnostic breast cancer dataset taken from UCI Machine Learning. Then, the dataset was fed into a conventional neural network for a benchmark test. Afterwards, the dataset was fed into the wide and deep neural network with and without Adam. It was found that there were improvements in the result of the wide and deep network with Adam. In conclusion, Adam is able to improve the performance of a wide and deep neural network.