A Statistician Teaches Deep Learning
arXiv:2102.01194
Abstract
Deep learning (DL) has gained much attention and become increasingly popular in modern data science. Computer scientists led the way in developing deep learning techniques, so the ideas and perspectives can seem alien to statisticians. Nonetheless, it is important that statisticians become involved -- many of our students need this expertise for their careers. In this paper, developed as part of a program on DL held at the Statistical and Applied Mathematical Sciences Institute, we address this culture gap and provide tips on how to teach deep learning to statistics graduate students. After some background, we list ways in which DL and statistical perspectives differ, provide a recommended syllabus that evolved from teaching two iterations of a DL graduate course, offer examples of suggested homework assignments, give an annotated list of teaching resources, and discuss DL in the context of two research areas.
arXiv comment19 pages, accepted by Journal of Statistical Theory and Practice
References in corpus (17)
- A Survey of Deep Learning Techniques for Autonomous Driving
- Improved Training of Wasserstein GANs
- Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
- Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
- Deep Bayesian Active Learning with Image Data
- Deep Neural Networks as Gaussian Processes
- Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
- Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
- Deep Learning in the Automotive Industry: Applications and Tools
- An Introduction to Image Synthesis with Generative Adversarial Nets
- The jamming transition as a paradigm to understand the loss landscape of deep neural networks
- Deep Learning Algorithms with Applications to Video Analytics for A Smart City: A Survey
- Optimal Regularization Can Mitigate Double Descent
- Some Optimizations on Detecting Gravitational Wave Using Convolutional Neural Network
- Adversarial classification: An adversarial risk analysis approach
- On Symplectic Optimization
- A Survey on Deep Learning Toolkits and Libraries for Intelligent User Interfaces