Foundations of Deep Learning - Part 2
-
- 0 Rating
- 0 Reviews
- 0 Students Enrolled
Foundations of Deep Learning - Part 2
Foundations present neural building blocks and computational graphs, while classification relies on softmax probabilities optimized with cross-entropy. Generalization is improved by regularization, early stopping, and dropout, with performance refined through careful data preparation, principled weight initialization, and disciplined model selection.
-
- 0 Rating
- 0 Reviews
- 0 Students Enrolled
Requirements
- see DELTA course requirements
General Overview
Description
Foundations of Artificial Neural Networks introduce neurons, activation functions, layered compositions, and computational graphs as the basis for learning complex mappings. Neural Networks for Classification formalize multi-class prediction with the softmax function to produce class probabilities and cross-entropy as the training objective, linking decision boundaries to probabilistic outputs. Overfitting in Neural Networks is addressed via the bias–variance tradeoff, regularization (e.g., L2/L1), early stopping, and dropout to improve generalization. Further Tweaks and Tuning cover data preparation (scaling, splits), weight initialization (e.g., Xavier/He), and model selection through validation and systematic hyperparameter search.
Courses that include this CL
Recommended for you
Meet the instructors !
Stefan received a PhD from the University of Hamburg in 2007, where he also completed his habilitation on decision analysis and support using ensemble forecasting models in 2012. He then joined the Humboldt-University of Berlin in 2014, where he heads the Chair of Information Systems at the School of Business and Economics. He serves as an associate editor for the International Journal of Business Analytics, Digital Finance, and the International Journal of Forecasting, and as department editor of Business and Information System Engineering (BISE). Stefan has secured substantial amounts of research funding and published several papers in leading international journals and conferences. His research concerns the support of managerial decision-making using quantitative empirical methods. He specializes in applications of (deep) machine learning techniques in the broad scope of marketing and risk analytics. Stefan actively participates in knowledge transfer and consulting projects with industry partners; from start-up companies to global players and not-for-profit organizations.