Udacity
Глобальный
Курс
Online
В любой момент
3 месяца
Стоимость курса
399 USD
Подробности и регистрация

Expand Your Knowledge of Artificial Intelligence

Навыки, которые вы получите:
Artificial intelligence Python

Learn essential Artificial Intelligence concepts from AI experts like Peter Norvig and Sebastian Thrun, including search, optimization, planning, pattern recognition, and more.

Necessary preparation

  • Basic knowledge of linear algebra and calculus.
  • The ability to apply basic probability and statistics.
  • Programming experience in Python.
  • Experience implementing computer science algorithms and object-oriented programming.
  • The ability to run programs and interpret output from a command line terminal or shell.
  • You will also need access to a Windows, macOS, or Linux computer with Python 3.4 or later installed, and admin permissions to install new programs.

For those who want to

  • Learn to write programs using the foundational AI algorithms powering everything from NASA’s Mars Rover to DeepMind’s AlphaGo Zero. 
  • Learn classical AI algorithms applied to common problem types.
  • Master Bayes Networks and Hidden Markov Models, and more.

The Program 

  1. Introduction to Artificial Intelligence.
  2. Classical Search.
  3. Automated Planning.
  4. Optimization Problems.
  5. Adversarial Search.
  6. Fundamentals of Probabilistic Graphical Models.

What will you learn

  • The foundations of AI.
  • Classical graph search algorithms--including uninformed search techniques like breadth-first and depth-first search and informed search with heuristics including A*.
  •  To represent general problem domains with symbolic logic and use search to find optimal plans for achieving your agent’s goals. Planning & scheduling systems power modern automation & logistics operations, and aerospace applications like the Hubble telescope & NASA Mars rovers.
  • Iterative improvement optimization problems and classical algorithms emphasizing gradient-free methods for solving them.
  • How to search in multi-agent environments (including decision making in competitive environments) using the minimax theorem from game theory. 
  •  To use Bayes Nets to represent complex probability distributions, and algorithms for sampling from those distributions.
  •  The algorithms used to train, predict, and evaluate Hidden Markov Models for pattern recognition.
Нам нужен ваш фидбек!
Честный и беспристрастный