This course is an applied introduction to deep learning for business students. We will cover the basics of deep learning, including its foundations, tensors, typical architectures, and applications. We will also discuss the different training paradigms and tooling used in deep learning.
In the first half of the course, we will focus on different classical neural network architectures, including artificial neural networks (ANNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks. In the second half of the course, we will introduce students to transformer models, the core idea of attention, and milestone transformer architectures. We will also cover the tooling used in the transformer ecosystem, including libraries like sbert, transformers, and simpletransformers.
Throughout the course, we will apply transformers to real-world business problems. This will include using sbert for sentence and image embedding, finetuning and inference of common transformer-based language models like BERT, and training timeseries transformers for time-sensitive business applications.
Likewise, we will use real-world business examples to illustrate the concepts and techniques covered in the lectures. By the end of the course, students will have a solid understanding of deep learning and its current applications in business. We will have frequent opportunities to work in groups on four mini-projects. These projects will involve applying the concepts and techniques learned in the lectures to real-world business examples. The goal of these projects is to give you hands-on experience with deep learning and help them build a portfolio of work to showcase your skills..