[RCAC Workshop]
📅 Date: October 10th, 2025 ⏰ Time: 10am-11am EST 💻 Location: Virtual 🏫 Instructor: Christina Joslin
This session provides an introduction to two of the most widely used deep learning frameworks, PyTorch and TensorFlow. We will begin with a comparison of their core architectures and programming styles, highlighting how PyTorch’s dynamic computation graph differs from TensorFlow’s static graph approach. Next, we will cover the fundamentals of tensors as the building blocks for both frameworks and explore how PyTorch and TensorFlow handle them. We will then walk through the basics of automatic differentiation (autograd) and demonstrate how it enables gradient-based optimization for training models. Finally, we will build and train simple neural networks in both frameworks, showing the step-by-step process from defining layers to running training loops. The session combines conceptual explanations with hands-on code examples in both a slideshow and a Jupyter notebook, which will also be shared with participants afterward for further practice.