Applied Artificial Intelligence

Our Applied Artificial Intelligence coursescombines our curated concepts for the basis in analysis with artificial intelligence with the methods &mindset of modeling for programming the intelligence behind each project. Our program is designed to be detailed enough for students to progress onto bigger topics while still able to navigate through similar background topics. In addition, the various projects that are specified for each day is built with previous topics in mind, thus not only reviewing the topic but enhancing the skills again in a programmed project.


Students will work through a collection of tutorials to be completed prior to the start of Artificial Intelligence Bootcamp. These are meant to cover the basics of Python, so that students can hit the ground running.



Artificial Intelligence Bootcamp

Session I : Introduction to Artificial Intelligence with Python

In our first class, we will introduce essential Python packages & beginning concepts of Artificial Intelligence
such as branches & agents, ending with deeper conceptssuch as the process behind modeling.

Session II : Supervised Learning: Regression & Classification

The second class composes of reviewing the differences between supervised & unsupervised learning as well as examples of each, such as logistic regression & Naïve Bayes, rounding off with SVM & a project using the SVM regressor to solidify the process behind modeling.

Session III : Extracting the Information from Ensemble Learning

Here we dive into ensembles, such as Decision Trees & their massive fellow: Random Forest. Both in which we will not only introduce methods of tune parameters, but tune features as well. We end with a real-life model: traffic.

Session IV : LocatingPatterns in Unsupervised Data

Since all patterns needed to be identified to be studied, we will introduce the fundamentals of unsupervised data & which models will be best to detect& recognize patterns in these types of data, such as Gaussian Mixture. To summarize the day, we have an example for the biggest industry: commerce.

Session V : Recommenders using K-Nearest & Filtering

In Day 5, we introduce another unsupervised algorithm: K-Nearest, with the explained benefits of nearest neighbors. We then examine the strengths of these neighbors with scores. Similarity between users will be established with one of several methods: collaborative filtering. We will then combine all these together in a movie recommendation system.

Session VI : Stages ofLogic Programming

On this day, we will provide the basics of logic programming as well as more Python packages. We will cover parsing family tree, solving puzzles, & more.

Session VII : Techniques in Heuristic Searches

Here we discover techniques in heuristic searches & use them on solution spaces. Applications include simulated annealing, region coloring, etc.

Session VIII : Algorithms for Genetics

Genetics is a big field, but we cover crossover, mutation, & fitness functions as well as build an intelligent robot controller in this day. The basis of this type of problems will be introduced as the symbol regression.

Session IX : Creation Day with Artificial Intelligence

In the middle of our program, we are designing & controlling the creation of games such as Tic Tac Toe, moving onto Connect Four, & ending off in the intelligent Hexapawn.

Session X : Natural Language Processing

The easiest untapped data is text & words. The entire methodology is introduced as Natural Language Processing where we internally define tokenization, stemming, & so on. Projects during this day will be topic modeling & sentiment analysis.

Session XI : Reasoning for Time Series in Probabilistic Methods

The foundation for stock market predictions are laid on this day, including Hidden Markov models & Conditional Random Fields. We then couple this with Natural Language Processing to do text sequence analysis.

Session XII : Building to Recognizing Speech Patterns

Just as important as textual data, speech data is data artificial intelligence excels in. On this day, we will not only demonstrate algorithms to analyze speech, but build a live recognition system.

Session XIII : Object Detection & Tracking

Algorithms related to object detections will be covered in our 13th day, where we will also cover topics such as optical flow, face tracking, & eye tracking.

Session XIV : Artificial Neural Networks

Building upon the previous days, students will be able to build an Optical Character Recognition system at the end of this day using algorithms specific to neutral networks.

Session XV : Reinforcement Learning

Students will wrap off the program by learning the techniques for reinforcement learning systems as well as move onto building learning agents that will be interactive.