Can we build hardware as complex as the brain ?
How complicated is our brain ?
- a neuron, or nerve cell, is the basic information processing unit
- estimated to be on the order of 10 to the power 12 neurons in a human brain
- many more synapses (10 to the power 14) connecting these neurons
- cycle time: 10 -3 second ( 1 millisecond )
How complex can we make computers ?
- 10 to the power 8 or more transistors per CPU
- supercomputer: hundreds of CPUs, 10 to the power 12 bits of RAM
- cycle times: order of 10 to the power -9 seconds
Conclusions
- YES: in the near future we can have computers with as many basic processing elements as our brain, but with
far fewer interconnections (wires or synapses) than the brain
much faster updates than the brain
- but building hardware is very different from making a computer behave like a brain !
Can Computers beat Humans at Chess ?
Chess playing is a classic AI problem
- well-defined problem
- very complex: difficult for humans to play well
Conclusion:
YES: today's computers can beat even the best human
Can Computers Talk ?
- This is know as "speech synthesis"
e.g. "fictitious" -> fik-tish-es
- use pronunciation rules to map phonemes to actual sound
e.g. "tish" -> sequence of basic audio sounds
Difficulties
- sounds made by this "lookup" approach sound unnatural
- sounds are not independent
e.g. "act" and "action"
modern systems (e.g. at AT & T) can handle this pretty well
- a harder problems is emphasis, emotion, etc
humans understand what they are saying
machines don't: so they sound unnatural
Conclusion:
- No, for complete sentences
- YES, for individual words
Can Computers Recognize Speech ?
Speech Recognition:
- mapping sounds from a microphone into a list of words
- classic problem in AI, very difficult
"Lets talk about how to wreck a nice beach"
(I really said "...................................")
Recognizing single words from a small vocabulary
- System can do this with high accuracy (order of 99%)
- e.g., directory inquiries
Limited vocabulary (area codes, city names)
Computer tries to recognize you first, if unsuccessful hands you over to a human operator
Saves millions dollars a year for the phone companies
Recognizing normal speech is much more difficult
- Speech is continuous: where are the boundaries between words ?
e.g. An English professor wrote words: A woman without her man is nothing: on the board and asked his students to punctuate it correctly.
All of the males in the class wrote: "A woman, without her man, is nothing."
All of the females in the class wrote: "A woman without her, man is nothing."
- large vocabularies
- can be many thousands of possible words
- we can use context to help figure out what someone said
e.g., hypothesize and test
try telling a waiter in a restaurant:
"I would like some dream and sugar in my coffee"
- background noise, other speakers, accents, colds, etc
- no normal speech, modern system are only about 60-70% accurate
Conclusion:
- No, normal speech is too complex to accurately recognize
- YES, for restricted problems (small vocabulary, single speaker)
Can Computers Understand speech ?
Understanding is different to recognition:
-assume the computer can recognize all the words
-many different interpretations are there?
1. time passes quickly like an arrow?
2. command: time the files the way an arrow times the files
3. command: only time those files which are like an arrow
4. :time-files" are fond of arrows
only 1. makes any sense,
but how could a computer figure this out?
clearly humans use a lot of implicit commonsense knowledge in communication
Conclusion:
- No, much of what we say is beyond the capabilities of a computer to understand at present
Can Computers Learn and Adapt ?
Learning and Adaptation
- Consider a computer learning to drive on the freeway
- we could teach it lots of rules about what to do
- or we could let it rive and steer it back on route when it heads for the edge
System like this are under development (e.g. Daimler Benz)
e.g. RALPH at CMU
- Machine learning allows computers to learn to do things without explicit programming
- Many successful applications:
requires some "set-up" does not me an your PC can learn to forecast the stock market or become a brain surgeon
Conclusion:
- YES, computers can learn and adapt, when presented with information in the appropriate way.
Can Computers "see" ?
Recognition v. Understanding (like speech)
- Recognition and Understanding of Objects in a scene
look around this room
you can effortlessly recognize objects
human brain can map 2d visual image to 3d "map"
Why is visual recognition a hard problem ?
Conclusion:
- mostly NO: computers can only "see" certain types of objects under limited circumstances
- YES for certain constrained problems (e.g., face recognition)
Can Computers plan and make optimal decision ?
Intelligence
- involves solving problems and making decision and plans
- e.g., you want to take a holiday in Brazil
you need to decide on flights
you need to get to the airport, etc.
involve a sequence of decision, plans, and actions
What makes planning hard ?
- the world is not predictable:
your flight is canceled or there's a backup on the 405
- there are a potentially huge number of details
do you consider all flights? all dates
- no: commonsense constrains your solutions
- AI systems are only successful in constrained planning problems
Conclusion:
- NO, real-world planning and decision-making is still beyond the capabilities of modern computers
exception: very well-defined, constrained problems
Summary of State of AI System in practice
Speech synthesis, recognition and understanding
- very useful for limited vocabulary applications
- unconstrained speech understanding is still too hard
Computer vision
- works for constrained problems (hand-written zip-codes)
- understanding real-world, natural scenes is still too hard
Planning and Reasoning
- only works for constrained problems: e.g., chess
- real-world is too complex for general systems
Intelligence Systems in your Everyday Life
Post Office
- automatic address recognition and sorting of mail
Banks
- automatic check readers, signature verification systems
- automatic application classification
Customer Service
- automatic voice recognition
The Web
- identifying your age, gender, location, from your Web surfing
- Automated fraud detection
Digital Cameras
- Automated face detection and focusing
Computer Games
- intelligent characters/agents
AI Application: Machine Translation
Language problems in international business
- e.g., at a meeting of Japanese, Korean, Vietnamese and Swedish investors, no common language
- or: you are shipping your software manuals to 127 countries
- solution; hire translators translate
- would be much cheaper if a machine could do this
How hard is automated translation
- very difficult! e.g., English to Russian
"The spirit is willing but the flesh is weak" (English)
"The vodka is good but the meat is rotten" (Russian)
- not only must the words be translated, but their meaning also!
- is this problem "AI-complete"?
Nonetheless.....
- commercial systems can do a lot of the work very well (e.g., restricted vocabularies in software documentation)
- algorithm which combine dictionaries, grammar models, etc
- Recent progress using "black-box" machine learning techniques.
How complicated is our brain ?
- a neuron, or nerve cell, is the basic information processing unit
- estimated to be on the order of 10 to the power 12 neurons in a human brain
- many more synapses (10 to the power 14) connecting these neurons
- cycle time: 10 -3 second ( 1 millisecond )
How complex can we make computers ?
- 10 to the power 8 or more transistors per CPU
- supercomputer: hundreds of CPUs, 10 to the power 12 bits of RAM
- cycle times: order of 10 to the power -9 seconds
Conclusions
- YES: in the near future we can have computers with as many basic processing elements as our brain, but with
far fewer interconnections (wires or synapses) than the brain
much faster updates than the brain
- but building hardware is very different from making a computer behave like a brain !
Can Computers beat Humans at Chess ?
Chess playing is a classic AI problem
- well-defined problem
- very complex: difficult for humans to play well
YES: today's computers can beat even the best human
Can Computers Talk ?
- This is know as "speech synthesis"
e.g. "fictitious" -> fik-tish-es
- use pronunciation rules to map phonemes to actual sound
e.g. "tish" -> sequence of basic audio sounds
Difficulties
- sounds made by this "lookup" approach sound unnatural
- sounds are not independent
e.g. "act" and "action"
modern systems (e.g. at AT & T) can handle this pretty well
- a harder problems is emphasis, emotion, etc
humans understand what they are saying
machines don't: so they sound unnatural
Conclusion:
- No, for complete sentences
- YES, for individual words
Can Computers Recognize Speech ?
Speech Recognition:
- mapping sounds from a microphone into a list of words
- classic problem in AI, very difficult
"Lets talk about how to wreck a nice beach"
(I really said "...................................")
Recognizing single words from a small vocabulary
- System can do this with high accuracy (order of 99%)
- e.g., directory inquiries
Limited vocabulary (area codes, city names)
Computer tries to recognize you first, if unsuccessful hands you over to a human operator
Saves millions dollars a year for the phone companies
Recognizing normal speech is much more difficult
- Speech is continuous: where are the boundaries between words ?
e.g. An English professor wrote words: A woman without her man is nothing: on the board and asked his students to punctuate it correctly.
All of the males in the class wrote: "A woman, without her man, is nothing."
All of the females in the class wrote: "A woman without her, man is nothing."
- large vocabularies
- can be many thousands of possible words
- we can use context to help figure out what someone said
e.g., hypothesize and test
try telling a waiter in a restaurant:
"I would like some dream and sugar in my coffee"
- background noise, other speakers, accents, colds, etc
- no normal speech, modern system are only about 60-70% accurate
Conclusion:
- No, normal speech is too complex to accurately recognize
- YES, for restricted problems (small vocabulary, single speaker)
Can Computers Understand speech ?
Understanding is different to recognition:
-assume the computer can recognize all the words
-many different interpretations are there?
1. time passes quickly like an arrow?
2. command: time the files the way an arrow times the files
3. command: only time those files which are like an arrow
4. :time-files" are fond of arrows
only 1. makes any sense,
but how could a computer figure this out?
clearly humans use a lot of implicit commonsense knowledge in communication
Conclusion:
- No, much of what we say is beyond the capabilities of a computer to understand at present
Can Computers Learn and Adapt ?
Learning and Adaptation
- Consider a computer learning to drive on the freeway
- we could teach it lots of rules about what to do
- or we could let it rive and steer it back on route when it heads for the edge
System like this are under development (e.g. Daimler Benz)
e.g. RALPH at CMU
- Machine learning allows computers to learn to do things without explicit programming
- Many successful applications:
requires some "set-up" does not me an your PC can learn to forecast the stock market or become a brain surgeon
Conclusion:
- YES, computers can learn and adapt, when presented with information in the appropriate way.
Can Computers "see" ?
Recognition v. Understanding (like speech)
- Recognition and Understanding of Objects in a scene
look around this room
you can effortlessly recognize objects
human brain can map 2d visual image to 3d "map"
Why is visual recognition a hard problem ?
Conclusion:
- mostly NO: computers can only "see" certain types of objects under limited circumstances
- YES for certain constrained problems (e.g., face recognition)
Can Computers plan and make optimal decision ?
Intelligence
- involves solving problems and making decision and plans
- e.g., you want to take a holiday in Brazil
you need to decide on flights
you need to get to the airport, etc.
involve a sequence of decision, plans, and actions
What makes planning hard ?
- the world is not predictable:
your flight is canceled or there's a backup on the 405
- there are a potentially huge number of details
do you consider all flights? all dates
- no: commonsense constrains your solutions
- AI systems are only successful in constrained planning problems
Conclusion:
- NO, real-world planning and decision-making is still beyond the capabilities of modern computers
exception: very well-defined, constrained problems
Summary of State of AI System in practice
Speech synthesis, recognition and understanding
- very useful for limited vocabulary applications
- unconstrained speech understanding is still too hard
Computer vision
- works for constrained problems (hand-written zip-codes)
- understanding real-world, natural scenes is still too hard
Planning and Reasoning
- only works for constrained problems: e.g., chess
- real-world is too complex for general systems
Intelligence Systems in your Everyday Life
Post Office
- automatic address recognition and sorting of mail
Banks
- automatic check readers, signature verification systems
- automatic application classification
Customer Service
- automatic voice recognition
The Web
- identifying your age, gender, location, from your Web surfing
- Automated fraud detection
Digital Cameras
- Automated face detection and focusing
Computer Games
- intelligent characters/agents
AI Application: Machine Translation
Language problems in international business
- e.g., at a meeting of Japanese, Korean, Vietnamese and Swedish investors, no common language
- or: you are shipping your software manuals to 127 countries
- solution; hire translators translate
- would be much cheaper if a machine could do this
How hard is automated translation
- very difficult! e.g., English to Russian
"The spirit is willing but the flesh is weak" (English)
"The vodka is good but the meat is rotten" (Russian)
- not only must the words be translated, but their meaning also!
- is this problem "AI-complete"?
Nonetheless.....
- commercial systems can do a lot of the work very well (e.g., restricted vocabularies in software documentation)
- algorithm which combine dictionaries, grammar models, etc
- Recent progress using "black-box" machine learning techniques.
.jpg)
No comments:
Post a Comment