Data Structures, Algorithms and Machine Learning Optimization

Colleagues, the Data Structures, Algorithms, and Machine Learning Optimization program provides you with a functional, hands-on understanding of the essential computer science for machine learning applications. Learn "big O" notation to characterize the time efficiency and space efficiency of a given algorithm,  use Python data structures, including list-, dictionary-, tree-, and graph-based structures, understand the essential algorithms for working with data, including those for searching, sorting, hashing, and traversing, implement statistical and machine learning approaches to optimization differ, and why you would select one or the other for a given problem you're solving, grasp versatile (stochastic) gradient descent optimization algorithm works, and familiarize yourself with the "fancy" optimizers that are available for advanced machine learning approaches. Skill-based training modules cover: 1) Orientation to Data Structures and Algorithms - Machine Learning Foundations Series, A Brief History of Data and Algorithms, and their Applications to Machine Learning; 2) "Big O" Notation - Constant, Linear and Polynomial  Time, Common Runtimes, Best versus Worst Case scenarios; 3) List-Based Data Structures - Lists, Arrays, Linked Lists, Doubly-Linked Lists, Stacks, Queues, Deques; 4) Searching and Sorting - Binary Search, Bubble-Merge-Quick Sorts; 5) Sets and Hashing - Maps and Dictionaries, Sets, Hash Functions, Collisions, Load Factor, Hash Maps, String Keys, Hashing in ML; 6) Trees - Decision Trees, Random Forests, XGBoost: Gradient-Boosted Trees; 7) Graphs - Directed versus Undirected Graphs, DAGs: Directed Acyclic Graphs, Pandas DataFrames; 8) Machine Learning Optimization - Statistics versus Machine Learning - Objective Functions, Mean Absolute Error, Mean Squared Error, Minimizing Cost with Gradient Descent, Gradient Descent from Scratch with PyTorch, Critical Points, Stochastic Gradient Descent, Learning Rate Scheduling, Maximizing Reward with Gradient Ascent; and 9) Fancy Deep Learning Optimizers - Jacobian Matrices, Second-Order Optimization and Hessians, Momentum, and Adaptive Optimizers.

Enroll today (teams & execs welcome): https://tinyurl.com/yc2dfb8f 

Recommended reading: Data-Driven Organizations book series:

1 - Data-Driven Decision-Making (Kindle) (Audible)

2 - Implementing Data Science Methodology: From Data Wrangling to Data Viz (Kindle) (Audible)

And download your complimentary AI-ML-DL - Career Transformation Guide.

Much career success, Lawrence E. Wilson - Artificial Intelligence Academy (subscribe & share)