Duration
4 days (10:00 AM - 5:00 PM Eastern)
Cost
$1,325.00

Online Training

Do you want to take an online, instructor-led class?

Onsite Training

Do you have five (5) or more people needing this class and want us to deliver it at your location?

Details

Subjects Covered

Prerequisites

Details

Course Details

Artificial Intelligence (AI) is the creation and study of “intelligent agents” – software devices that perceive their environment and take actions that maximize their chance of successfully achieving their goals.

Python is a high-level, interpreted, highly extensible, object-oriented language that consistently ranks as one of the most popular programming languages for working with AI. With its comprehensive standard library and a large community of extensions, it can be used to create a diverse array of types of programs.

This course will assist students in learning about which algorithms should be used in a given context, as well as teaching them how to create AI building blocks using standard data mining techniques, using examples gathered from real-world applications.

Subjects Covered

  • Introduction
    • What is Artificial Intelligence?
    • Applications of AI
    • Branches of AI
    • Building Agents
    • Development Environments
  • Classification and Regression
    • Supervised vs. Unsupervised Learning
    • What is Classification?
    • Preprocessing and Encoding
    • Types of Classifiers
    • What is Regression?
    • Building Regressors
  • Predictive Analytics
    • What is Ensemble Learning?
    • Using Decision Trees
    • Random Forests
    • Finding Optimal Training Parameters
    • Computing Relative Feature Importance
  • Pattern Detection and Unsupervised Learning
    • What is Unsupervised Learning?
    • Clustering Data With K-Means
    • Estimating Clusters With Mean Shift
    • Gaussian Mixture Models
    • Affinity Propagation Models
  • Recommender Systems
    • Building Recommender Systems
    • Creating a Training Pipeline
    • Extracting Nearest Neighbors
    • Computing Similarity Scores
    • Collaborative Filtering
  • Logic Programming
    • What is Logic Programming?
    • Solving Problems With Logic Programming
    • Matching Mathematical Expressions
    • Validating Primes
  • Heuristic Searches
    • Heuristic Search Techniques
    • Constraint Satisfaction Problems
    • Local Search Techniques
    • Solving Problems With Constraints
  • Genetic Algorithms
    • Evolutionary and Genetic Algorithms
    • Fundamental Concepts
    • Generating a Bit Pattern
    • Visualizing the Evolution
    • Solving the Symbol Regression Problem
  • Building Games
    • Using Search Algorithms in Games
    • Combinatorial Search
    • Minimax Algorithm
    • Alpha-Beta Pruning
    • Negamax Algorithm
    • Building Game Bots
  • Natural Language Processing
    • Tokenizing Text Data
    • Converting Words to Base Forms
    • Dividing Text Into Chunks
    • Extracting Word Frequencies
    • Topic Modeling Using Latent Dirichlet Allocation
  • Probabilistic Reasoning
    • Understanding Sequential Data
    • Slicing Time-Series Data
    • Extracting Statistics from Time-Series Data
    • Generating Data Using Hidden Markov Models
    • Identifying Alphabet Sequences
  • Speech Recognizers
    • Working With Speech Signals
    • Visualizing Audio Signals
    • Transforming Audio Signals to the Frequency Domain
    • Generating Audio Signals
    • Synthesizing Tones
    • Extracting Speech Features
    • Recognizing Spoken Words
  • Object Detection and Tracking
    • Frame Differencing
    • Tracking Objects Using Colorspaces
    • Tracking Objects Using Background Subtraction
    • Optical Flow Based Tracking
  • Artificial Neural Networks
    • Building a Perceptron Based Classifier
    • Single Layer Neural Networks
    • Multilayer Neural Networks
    • Vector Quantizers
  • Reinforcement Learning
    • Understanding the Premise
    • Reinforcement Learning vs. Supervised Learning
    • Building Blocks of Reinforcement Learning
    • Creating an Environment
    • Building a Learning Agent
  • Deep Learning and Convolutional Neural Networks
    • What are Convolutional Neural Networks?
    • Architecture
    • Types of Layers
    • Building a Perceptron Based Linear Regressor

Prerequisites

Before Taking this Class

Students should have solid experience in writing programs using Python.