introduction to artifical intelligence jitendra malik u.c. berkeley jitendra malik u.c. berkeley
Post on 22-Dec-2015
229 views
TRANSCRIPT
Introduction to Artifical Intelligence
Introduction to Artifical Intelligence
Jitendra Malik
U.C. Berkeley
Jitendra Malik
U.C. Berkeley
BRAINBRAIN
Imaging the BrainImaging the Brain
Some facts…Some facts…
• 100 Billion neurons
• On average, connected to 1 K others
• Neurons are slow. Firing rates < 100 Hz.
• Can be classified into– Sensory – Motor– Central
• 100 Billion neurons
• On average, connected to 1 K others
• Neurons are slow. Firing rates < 100 Hz.
• Can be classified into– Sensory – Motor– Central
Sensory SystemsSensory Systems
• Vision (nearly 30-50% )
• Audition (nearly 10%)
• Somatic
• Chemical– Taste– Olfaction
• Vision (nearly 30-50% )
• Audition (nearly 10%)
• Somatic
• Chemical– Taste– Olfaction
Motor SystemsMotor Systems
• Locomotion
• Manipulation
• Speech
• Locomotion
• Manipulation
• Speech
Central SystemsCentral Systems
• Reasoning and problem solving
• Language
• ……..
• Reasoning and problem solving
• Language
• ……..
NEURONNEURON
Trends in biological and machine brain evolution
Trends in biological and machine brain evolution
Hans Moravec: ROBOTHans Moravec: ROBOT
Moravec’s argumentMoravec’s argument
• 1 neuron = 1000 instructions/sec• 1 synapse = 1 byte of information• Human brain then processes 10^14 IPS and
has 10^14 bytes of storage• In 2000, we have 10^9 IPS and 10^9 bytes
on a desktop machine• In 25 years, assuming Moore’s law we
obtain human level computing power
• 1 neuron = 1000 instructions/sec• 1 synapse = 1 byte of information• Human brain then processes 10^14 IPS and
has 10^14 bytes of storage• In 2000, we have 10^9 IPS and 10^9 bytes
on a desktop machine• In 25 years, assuming Moore’s law we
obtain human level computing power
How Intelligence could have begun…
How Intelligence could have begun…
• V. Braitenberg: Vehicles, Experiments in Synthetic Psychology
• V. Braitenberg: Vehicles, Experiments in Synthetic Psychology
Agents and EnvironmentsAgents and Environments
Reflex agent with stateReflex agent with state
Goal-oriented agentGoal-oriented agent
Utility-based agentUtility-based agent