introduction to deep learning and perceptron
Deep Learning is subset of machine learning which on its own subset of Artificial Intelligence, that has seen boom after 2012 with the increase in amount of data and compute (especially with introduction of GPU for deep learning). Now these networks are part of our daily life. Google searches, Google translate, ChatGPT, Image processing etc. are few examples that uses deep learning in their backend. Like machine learning we learn rules from data, instead of hand code rules to program we make algorithm learn those rule. In this post we will introduce deep learning and explore perceptron along with its implementation. We will also derive perceptron mistake bound and deduce perceptron convergence theorem.