Machine learning has become a hot topic these days, but in their haste to adopt, many fail to understand the vast conceptual foundation that underpins the technology.

In this session, we’ll address that by going back to basics to explore Deep Learning and Artificial Neural Networks from the ground up. We’ll cover the various input, output, and hidden layers that go into constructing an ANN and look at activation functions, weights, epochs, error correction, and backpropagation. We’ll show you how to use Python-based libraries and tools such as TensorFlow, NumPy, and Pandas. For the hands-on part, we will build a simple banking app that predicts customer retention.

Prerequisites:

—Very basic knowledge of machine learning concepts & data science fundamentals
—Google Colab to write and execute Python code