Deep Learning has been a highly successful research field over the last 20 years across a range of domains (vision, language, audio, robotics; ``AI'' in general) and has also translated into significant commercial success. We can learn a comprehensive overview of neural network architectures and deep learning algorithms. 

The class will focus on the core principles of extracting meaningful representations from high-dimensional data, a fundamental aspect for several applications in autonomous decision making. Readers can check the details here: https://courses.cs.umbc.edu/graduate/675/#schedule 

Data structures manage how data is stored and accessed. Algorithms focus on processing this data. Examples of data structures are Array, Linked List, Tree and Heap, and examples of algorithms are Binary Search, Quick Sort and Merge Sort. 

For details, interested readers can check, https://www.geeksforgeeks.org/dsa/dsa-tutorial-learn-data-structures-and-algorithms/

We will introduce the core machine learning concepts required to experiment with survival methods. The chapter also introduces fundamental ideas in data splitting, resampling, cross-validation, benchmarking, and hyperparameter optimization, with an emphasis on estimating generalization error. 

By reading this article, we will know the conceptual framework and vocabulary required for supervised learning for survival analysis that will be used consistently throughout subsequent chapters. To know more, please check-out this article: https://www.mlsabook.com/P1C3_machinelearning.html#sec-ml-eval

This website covers a board range of concepts from performance evaluation to advanced risk minimization.  Multiple tuning strategies and nested re-sampling techniques are discussed in detail. 

The following topics are discussed here as well: 

1. Regularization

2. Boosting 

3. Gaussian Process

4. Imbalanced learning 

For more details, please check out: https://slds-lmu.github.io/i2ml/

Models that learn from data are widely and rapidly being deployed today for real-world use, but they suffer from unforeseen failures– this course will explore the reasons for these failures and state-of-the-art mitigation techniques. 

For details, interested readers can check this: https://courses.cs.umbc.edu/graduate/691rml/

Quantitative and physical aspects of remote sensing systems, how to solve remote sensing inverse problems, how to integrate knowledge-driven quantitative remote sensing models with data-driven AI models, environmental monitoring applications .

For details, interested readers can check this course. https://www.gsilab.ca/teaching.html