Paper Title
Microarray Cancer Data Classification Using Deep Learning

Abstract
The purpose of the project is to use microarray gene expression data to classify cancer using a deep learning feedforward algorithm. Due to the large dimensionality of the data, traditional machine learning algorithms have had difficulty with this task. The input layer, numerous hidden layers, and output layer make up the deep learning algorithm used in this work. In order to enhance accuracy over time, it applies back propagation to modify the weights and biases of the neurons based on the discrepancy between the expected output and the actual output. The preprocessing of the microarray gene expression data include scaling and normalising the expression levels to a range between 0 and 1. Following that, the data is divided into training and validation sets. The deep learning model is trained using the training set, and its performance is assessed using the validation set. To increase the model's accuracy, hyperparameters including the number of hidden layers, the number of neurons in each layer, and the learning rate are optimised. The study's findings show that the deep learning feed-forward algorithm can accurately and efficiently classify cancer using microarray gene expression data. The approach can pinpoint the key genes for cancer classification and shed light on the intricate connections between genes and cancer. The study emphasises the promise of deep learning algorithms in biomedical research as well as their aptitude for managing large-scale data sets and spotting intricate patterns. As a result, it may be possible to create cancer classification models that are more precise and effective, leading to better cancer detection and care. Keywords —Microarray Data, Deep Learning, Cancer, Dimensionality Reduction, Neural Network