A Statistician Teaches Deep Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 103 references that are in the map. First posted on arXiv 29 Jan 2021.
Builds on
32 of 103 references.
References · 32
- 2014Going Deeper with Convolutionscited by 4,231
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
- 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 919
- 2017Deep Bayesian Active Learning with Image Datacited by 812
- 2016Universal adversarial perturbationscited by 774
- 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
- 2017Spectrally-normalized margin bounds for neural networkscited by 681
- 2019Deep Double Descent: Where Bigger Models and More Data Hurtcited by 667
- 2017Deep Neural Networks as Gaussian Processescited by 617
- 2017One pixel attack for fooling deep neural networkscited by 579
20 more
- 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
- 2017Size-Independent Sample Complexity of Neural Networkscited by 289
- 2018Scalable and accurate deep learning for electronic health recordscited by 275
- 2019Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Datacited by 261
- 2017High-dimensional dynamics of generalization error in neural networkscited by 238
- 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 202
- 2020Optimal Regularization Can Mitigate Double Descentcited by 107
- 2017Deep Learning for Medical Image Processing: Overview, Challenges and Futurecited by 104
- 2018SparseFool: a few pixels make a big differencecited by 94
- 2018Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantificationcited by 81
- 2018The jamming transition as a paradigm to understand the loss landscape of deep neural networkscited by 61
- 2016Compression of Neural Machine Translation Models via Pruningcited by 43
- 2018An Introduction to Image Synthesis with Generative Adversarial Netscited by 32
- 2016Deep Neural Networks to Enable Real-time Multimessenger Astrophysicscited by 24
- 2016Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Modelscited by 18
- 2015Deep Learning Algorithms with Applications to Video Analytics for A Smart City: A Surveycited by 6
- 2020Bridging Maximum Likelihood and Adversarial Learning via α-Divergencecited by 6
- 2018A Survey on Deep Learning Toolkits and Libraries for Intelligent User Interfacescited by 5
- 2018Adversarial classification: An adversarial risk analysis approachcited by 4
- 2018Understanding Weight Normalized Deep Neural Networks with Rectified Linear Unitscited by 2
Built on by
Not cited yet.