Applied Artificial Intelligence

Artificial Intelligence (AI) is being used extensively to solve real-world complex problems. From driving automobiles to providing virtual assistance, use of artificial intelligence in our day to day lives are projected to increase manifold in the coming years. In fact, as per a survey conducted by PwC, business leaders said they believe AI is going to be fundamental in the future. In fact, 72% termed it a “business advantage”.

At Columbia Engineering, we are fascinated by the possibilities of data-driven technologies. We have created the Applied Artificial Intelligence course, in partnership with EMERITUS, to help students across the world understand how this data-centric approach can be applied to your daily lives.

Duration and Course Fee

  • Starts 24 Jan 2019
  • 3 Months
  • 6 – 8 hours per week
  • Course Fees USD 1200

 

Faculty

John Paisley
John Paisley
Columbia University Associate Professor, Electrical Engineering
Affiliated Member, Data Sciences Institute

Columbia Engineering

Course Highlights

  • Faculty Video Lectures
  • Peer Learning
    Moderated Discussion Boards
  • assignment icon
    Quizzes/Assignments
  • Real World Applications
    Application Projects
  • Q&A Sessions with Course Leaders
  • webinar
    Live Online Teaching

SYllabus

  • Overview of AI
  • Applications of AI
  • AI foundation and history
  • Intelligent agents
  • Search agents
  • Uninformed search
  • Uninformed search examples
  • Heuristics and greedy search algorithm
  • A* search and optimality
  • Search algorithms recap
  • Local search
  • Adversarial search and games
  • Minimax algorithm
  • Alpha-beta pruning
  • Stochastic games
  • Machine learning concepts
  • K-nearest neighbors and training-testing
  • Overfitting-underfitting and regularization
  • Linear models for regression
  • Machine learning: perceptron
  • Logistic regression
  • Decision trees
  • Naïve Bayes
  • Ensemble methods
  • Neural networks
  • Clustering
  • Association rules
  • Constraint satisfaction problems
  • Cryptarithmetic puzzle
  • Backtracking
  • Constraint propagation
  • Problem structure
  • Reinforcement Learning Introduction
  • Reinforcement learning overview
  • Markov decision process (MDP)
  • Example of an MDP and Bellman equations
  • Value function – Matrix notation
  • Finding optimal policy in MDPs – iterative methods
  • Policy iteration method example
  • Value iteration method
  • Reinforcement learning – algorithms
  • Knowledge-based agents
  • The Wumpus world
  • Logical agent
  • Inference rules
  • Reduced Wumpus world
  • Model checking and inference
  • Theorem proving and proof by resolution
  • Conversion to CNF and resolution algorithm
  • Forward and backward chaining
  • Propositional logic: summary
  • First order logic
  • AI Applications: Natural language processing
  • Text classification
  • Language models
  • Progress in NLP
  • Deep learning: background and history
  • Deep learning: architecture and application
  • Introduction to robotics
  • Robot path planning – visibility graphs
  • Voronoi graphs and potential fields
  • Probabilistic roadmap planner (PRM)
  • Rapidly-exploring random tress (RRT) and path planning summary

PRE-REQUISITES: This is an advanced course which requires an undergraduate knowledge of linear algebra (vectors, matrices, derivatives), calculus, basic probability theory.

You should be comfortable with Python or any other programming language. All assignments/application projects will be done using the Python programming language.

BENEFITS TO THE LEARNER

Intellectual Capital

Intellectual Capital

  • Global Education
  • Rigorous and experiential curriculum
  • World-renowned faculty
  • Globally Connected Classroom: Peer to Peer Learning Circles
  • Action Learning: Learning by Doing

Brand-Capital

Brand Capital

  • Certificate from EMERITUS in collaboration with Columbia
    Engineering Executive Education

Social-Capital

Social Capital

  • Build new networks through peer interaction
  • Benefit from diverse class profiles

Career-Capital

Career Capital

  • Professional Acceleration through our enriched leadership toolkit
  • Learn while you earn
  • Get noticed. Get ahead.

Duration and Course Fee

  • Starts 28 February 2019
  • 3 Months
  • 6 – 8 hours per week
  • Course Fees USD 1200

 

Faculty

Ansaf Salleb-Aouissi Ansaf Salleb-Aouissi
Department of Computer Science, Columbia University Columbia Engineering Executive Education

Duration and Course Fee

  • Starts 28 February 2019
  • 3 Months
  • 6 – 8 hours per week
  • Course Fees USD 1200

 

Faculty

Ansaf Salleb-Aouissi Ansaf Salleb-Aouissi
Department of Computer Science, Columbia University Columbia Engineering Executive Education
Global Ivy Emeritus Institute of Management