Mathematics of Artificial intelligence and Machine Learning

I will not use acronyms

Machine Learning examples for Calculus I

Machine Learning examples for Calculus II

Machine Learning examples for Calculus III

Machine Learning examples for Computers and Numerical Algorithms

Machine Learning examples for Linear Algebra

Machine Learning and Normed Vector Spaces

Machine Learning examples for Differential Equations

Machine Learning examples for Probability and Statistics

Machine Learning examples for Optimization

Machine Learning examples for Numerical Linear Algebra

Machine Learning examples for Mathematical Modeling

Machine Learning examples: Monte Carlo Methods

Machine Learning examples: Topology

• Manifolds and Topology: linked example Colah's blog

Machine learning and Geometry

• Geometric Deep Learning webpage

Machine Learning: Do It Yourself

Artificial Intelligence: Mathematical Logic

Artificial Intelligence: Incompleteness Theorem

Artificial Intelligence: Computability

Artificial Intelligence: Tractability

Artificial Intelligence: (Nondeterministic Polynomial time) NP-completeness

Artificial Intelligence: Control Theory and Stochastic Optimal Control

Artificial Intelligence: Game Theory

Artificial Intelligence: Decision Theory

Artificial Intelligence: Operations Research

Artificial Intelligence: Graphics Processing Unit (GPU), Tensor Processing Unit (TPU), Wafer-Scale Engine (WSE) and Quantum Computing

My favorite excerpts from AI and Machine Learning books that help put AI in perspective

• Not magic or science fiction, but rather science, engineering and mathematics.
• These remarkable successes have led to a resurgence of interest in AI among students, companies, investors, governments, the media, and the general public. It seems that every week there is news of a news AI application approaching or exceeding human performance, often accompanied by a speculation of either accelerated success or a new AI winter.
• Society is now at a crucial juncture in determining how to deploy AI-based technologies in ways that promote rather than hinder democratic values such as freedom, equality and transparency.
• What can AI do today? Perhaps not as much as some of the more optimistic media articles might lead one to believe, but still a great deal.
• AI was founded in part as a rebellion against existing fields like control theory and statistics, but in this period it embraced the positive results of those fields.
• Beginning 2012, things changed.... A machine learning model that took a full day to train in 2014 takes only two minutes in 2018.
• Although it is not yet practical, quantum computing holds out the promise of far greater accelerations for some important subclasses of AI algorithms.
• Probability Theory describes what an agent should believe on the basis of evidence, Utility Theory describes what the agent wants, and Decision Theory puts the two together to describe what an agent should do.
• An agent is learning if it improves its performance after making observations about the world.
• Bayesian networks provide a well developed representation for uncertain knowledge. They play a role roughly analogous to that of propositional logic for definite logic.
• AI professors worldwide are about 80% male, 20% female. Similar numbers hold for Ph.D. students and industry hires.

• A deep neural network is a (very) simplified model of our cerebral cortex, composed of a stack of layers of artificial neurons.
• Deep Learning was not only possible, but capable of mind-blowing achievements that no other Machine Learning technique could hope to match (with the help of tremendous computing power and great amounts of data).
• [Machine Learning] is at the heart of much of the magic in today's high-tech products, ranking your web search results, powering your smartphone's speech recognition, recommending videos, and beating the world's champion at the game of Go. Before you know it, it will be driving your car.

If you are new to Python

1. Download Python 3: I used Anaconda Individual Edition. If you don't like installing using the command line then click on the graphical installer to install.
2. After downloading Anaconda open the Anaconda Navigator.
3. You can use Spyder Integrated Development Environment (IDE). You will see Spyder within the Anaconda Navigator.
4. Good, now you can start writing Python code (at the Spyder IDE).
5. Basic vocabulary: a module is a bunch of functions, a package is a bunch of modules, and a library is a bunch of packages.
6. For Artificial Intelligence and Machine Learning you will need the following Python libraries (do not look for these to install, you will import them when you need them and some of them already came with your Anaconda installation): numpy, SciPy, matplotlib, scikit-learn, TensorFlow and Keras. Pandas is popular for data extraction and preparation before training.
7. It's good to get in the habit of explaining and organizing your work. Jupyter helps you do that. It allows you to create and share documents that contain live code, texts explaining your projects and code, mathematical equations, data visualizations and much more. This link helps you with the markdown in Jupyter notebook so your work looks pretty and organized:
   • Jupyter text

• Learning with Python 3
• Think Python

Can we do Machine Learning with Matlab?

• Machine Learning with Matlab

We need the hardware

• cerebras blog

How big is Big Data?

Algorithms or Data?

Good Reads in Artificial Intelligence and Machine Learning

• Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville

Good Conferences to Attend in Artificial Intelligence and Machine Learning

• Top conferences for machine learning and artificial intelligence
• SIAM conference on Data Mining
• SIAM conference on Mathematics of Data Science

Good Journals to follow on Artificial Intelligence and Machine Learning

• SIAM Journal on Mathematics of Data Science