In Artificial Intelligence, we usually train a large network of smaller "nodes" (hence the name neural networks) by looking at some sample of the real-world data. These smaller nodes take micro-decisions which in turn affect the micro-decisions of other nodes and so on till it affects the decision of the whole network. There are several algorithms to make this network training better. One of them is called Dropout. Below are some life lessons from Dropout I have personally learnt.

The neural networks in deep learning are generally considered to be similar to the neural networks we have in our brains, albeit a much simpler versions. This similarity helps comprehend the deep learning neural networks easily. I have always seen the similarity to be used only to comprehend the deep learning neural networks and not to understand our brain from what we learn about the deep learning neural networks. The points below do not have a logical deduction but mostly my observation and intuition. The lessons I learned about life from neural networks are not new.

I am pleased to present to you this Guide to our plans for the upcoming fall semester and reopening of our campuses. In form and in content, this coming semester will be like no other. We will live differently, work differently and learn differently. But in its very difference rests its enormous power. The mission of Yeshiva University is to enrich the moral, intellectual and spiritual development of each of our students, empowering them with the knowledge and abilities to become people of impact and leaders of tomorrow.

In addition to awarding Bachelors, Masters and Ph.D. degrees, the Allen School recognized two 2018 Alumni Impact Award recipients, Yaw Anokwa and Eileen Bjorkman.

It's all exciting stuff, and I've been studying it for my master's degree. But outside of the classroom, outside of computers, what has it taught me about life? This is especially true with neural networks. When a machine learning algorithm correctly identifies a solution, most of the time no adjustments to any of the parameters (called "weights") are made. But if the algorithm is wrong, these weights are nudged so that the next time the algorithm guesses at a solution, it's closer to the right answer.