Week 6

In this chapter, we were introduced to PyTorch, a dynamic and beginner-friendly machine learning library created by Facebook's AI Research Lab. The instructional style focused on hands-on learning, the same style championed by fast.ai, where students were encouraged to get their hands dirty with creating actual tools instead of being bogged down by theory. We began by learning about tensors, multi-dimensional arrays that can be computed on GPUs for speed. We went over basic tensor operations like addition and multiplication, and immediately applied them to a real task: housing price prediction on the Boston Housing dataset. We gradually prepared the data, defined a simple neural network (SimpleNet), trained it using Mean Squared Error (MSE) loss and Stochastic Gradient Descent (SGD) optimizer, and evaluated its performance on unseen test data.

The chapter also included a concise Q&A section that clarified such key concepts as epochs, the need for separate training and test sets, and the functions of loss functions and optimizers. It reassured readers not to be daunted by jargon, insisting it was less important to understand deeply at first and allow it to develop naturally with practice, and instead to prioritize the creation of practical tools. In addition, the chapter encouraged an attitude: rather than simply learning technical material passively, we must think about how AI tools can be leveraged to solve actual problems, perhaps even leading to the creation of useful products or services.

As a major in accounting, the skills learned here can be incredibly valuable. As accounting moves beyond manual bookkeeping into increasingly more areas of financial prediction, fraud analysis, and risk analysis, the ability to develop or at least understand machine learning models can significantly set you apart. You could, for example, build tools that predict cash flow problems for clients, automate auditing procedures, or more precisely estimate the value of assets from various financial metrics. This can make you a valuable asset to any organization. Just like the housing price predictor, you could develop models to help businesses forecast financial outcomes for instance, time, money, and trouble saved. Being able to turn models into simple-to-use web apps could also allow you to deliver novel services that may not even occur to conventional accountants. In short, learning PyTorch and machine learning is a path to becoming a more strategic, tech-savvy accountant in a changing profession.