ACM AI Workshops
Crash Course on Machine Learning
UAS@UCLA is collaborating with ACM AI in order to lay down the foundation as well as develop the vision platform.
See the GitHub page.
Machine Learning Crash Course
Stuff to Know Before Workshops
- Python and NumPy
Linear regression is continuous while classification is discrete. Both have cost functions.
Logistic Regression is a machine learning model used primarily for problem spaces where a selection from a group of categories/classes is needed.
Python and NumPy
NumPy is a library for the Python programming language, adding support for large, multi-dimensional arrays and matrices, along with a large collection of high-level mathematical functions to operate on these arrays.
See this textbook website. The PDF copy is free. Skim through Chapters 1, 3, 4, and 10. These chapters are short reads. We expect you to have a high level understanding of these concepts.
You have an input layer, hidden layers, and an output layer.
The passing between layers is a computation (e.g. softmax, sigmoid functions), outputting a new vector. You keep passing the input deeper and deeper into more layers.
Multilayer Neural Networks and Applications
Backpropagation is used instead of gradient descent for neural networks. Backpropagation takes the partial derivatives of the cost with respect to the weights.