Home

As of July 2024

It might take me a bit to get everything written down, but I'll carve out some time for this section (there's just so much new tech these days!). In the meantime, I've set up a showcase section where you can check out all the source code and demos of the techniques I'll be covering. Stay tuned and happy learning!

Overview

Understanding the fundamental techniques of AI, such as search, planning, and reasoning, is crucial for developing intelligent systems capable of solving complex problems. These methods allow AI agents to navigate environments, make decisions, and find solutions efficiently. For instance, building an AI to solve Sudoku introduces the basics of logical constraints and backtracking, essential for structured problem-solving. This foundational knowledge helps create systems that can handle various real-world tasks, from scheduling to automated reasoning.

Additionally, techniques like uninformed and informed search, optimization methods, and game theory play a significant role in more advanced applications, such as developing AI chess players or competitive game agents. These methods enable AI to optimize decisions, anticipate opponents' moves, and perform well in strategic scenarios. Furthermore, probabilistic models and natural language processing equip AI with the ability to understand and generate human language, making these techniques indispensable for applications in communication, translation, and more. By mastering these core AI techniques, we pave the way for creating smarter, more efficient, and versatile AI systems that can revolutionize various industries.

Table of content

• Build an AI agent to solve Sudoku
  • Define core concepts from AI including “agents”,“environments”, and “states”
  • Learn the concept of “rational” behavior for AI agents
  • learn
    • represent problems in terms of logical constraints
    • constraint propagation to limit the potential solution space
    • Incorporate backtracking search to find a solution when the set of constraints is incomplete
• Forward Planning Agent (AI Chess player)
  • Classical search
    • Uninformed Search
    • Informed Search
  • Optimization Problems
    • Hill Climbing
    • Simulated Annealing
    • Genetic Algorithms
    • Late Acceptance Hill Climbing, Basin Hopping, & Differential Evolution
• Adversarial Game Playing Agent
  • Multi-Agent Domains
    • minimax search technique
    • state space search
  • Optimizing Minimax Search
  • Extending Minimax Search
• Part of Speech Tagging
  • Discrete distributions, joint probabilities, and conditional probabilities
  • Bayes Networks (Inference in Bayes Nets)
  • Hidden Markov Models
  • Dynamic Time Warping
  • Probabilistic graphical models