Introduction to intelligent systems
n Duration: 1 hr
n Outline:
1. What is an intelligent system?
2. Applications
3. Challenges
What is an intelligent system?
§ Technologically advanced machine can perceive and respond to
the world around it (i.e., system can sense and react to its
environment)
§ Ex: automated vacuum cleaner, facial recognition program,
Amazon’s personalized shopping suggestion, app Siri, smart watch,
etc.
Areas within intelligent systems
§ How machines perceive their environment?
Ø Through sensors
Ø Through vision (computer can understand and interpret visual
information from images/videos)
§ How machines interact with their environment?
Ø E.x: autonomous taxi
https://www.youtube.com/watch?v=vC8paIPH2xY
Autonomous taxi
§ How machines perceive their environment?
Ø Through sensors
Ø Through vision (computer can understand and interpret visual
information from images/videos)
§ How machines interact with their environment?
Ø E.x: autonomous taxi
https://www.youtube.com/watch?v=vC8paIPH2xY
Applications
n Factory automation
n Field and service robotics
n Assistive robotics
n Military applications
n Medical care
n Education
n Entertainment
Applications
n Visual inspection
n Character recognition
n Human identification using various biometric modalities (e.g.
face, fingerprint, iris, hand)
n Visual surveillance
n Intelligent transportation
Acknowledge for intelligent systems
n Programming n Physics
n Data structures n Numerical methods
n Algorithms n Math (calculate, linear algebra,
n Pattern recognition staticstic and prob.)
n Machine learning n Psychology
n Artificial intelligence
Challenges
§ Uncertainty: sensors provide limited, noisy and inaccurate
information à actions may be incorrect.
§ Dynamic world: the physical world changes continuously à
decisions should be made at fast time scales
§ Time-consuming computation: searching for the optimal path to
a goal requires extensive search through a very large state space.
§ Mapping: information lost in the transformation from the 3D world
to the 2D world. Computer vision must deal with challenges
including changes in perspective, lighting and scale; background
clutter or motion; etc.