My primary research area is artificial intelligence. There are many fields in artificial intelligence, such as computer vision, neural networks, machine learning, etc. Therefore, I decided to narrow it down to neural networks, since I find them fascinating. If appropriately configured, they can be incredibly effective and accurate at certain tasks, such as predictive analytics, object detection, and classification. A neural network is a network of neurons that together take input and provide output in some fashion. It’s supposed to imitate the human brain. For now, I’m going for predictive analytics, but I might switch to another application of neural networks if I don’t have a concrete idea of what to predict. I find predictive analytics to be interesting to me since the applications of predictive analytics with neural networks are able to be surprisingly accurate. These applications can be stock prediction, COVID projections, health outcomes, etc. The thing is that neural networks have layers, and these layers are supposed to create multiple evaluations of the weights from the input, and then pass them onto another inner layer or the final output layer that represents the overall output. These evaluations can be done in many different ways, and the interesting aspect of neural networks is the tinkering with how data gets evaluated. Tinkering could involve changing how many layers should be in the neural network and how many nodes should be in each layer. For these reasons, that’s why I’ll choose to pursue neural networks for my research. There is so much potential to be had with them.