Presentation is loading. Please wait.

Presentation is loading. Please wait.

A New Artificial Intelligence 3 Kevin Warwick. Classical AI Humans like to compare ourselves with others Humans like to compare ourselves with others.

Similar presentations


Presentation on theme: "A New Artificial Intelligence 3 Kevin Warwick. Classical AI Humans like to compare ourselves with others Humans like to compare ourselves with others."— Presentation transcript:

1 A New Artificial Intelligence 3 Kevin Warwick

2 Classical AI Humans like to compare ourselves with others Humans like to compare ourselves with others We try to find ways in which we are better than someone or something else We try to find ways in which we are better than someone or something else As artificial intelligence was born, the desire arose to compare artificial intelligence with human intelligence As artificial intelligence was born, the desire arose to compare artificial intelligence with human intelligence Basic rule was that human intelligence is as good as it gets - even human intelligence is the only intelligence Basic rule was that human intelligence is as good as it gets - even human intelligence is the only intelligence The best artificial intelligence can achieve is to be as good as human intelligence - to copy it in some way. The best artificial intelligence can achieve is to be as good as human intelligence - to copy it in some way.

3 Minsky Definition Classical artificial intelligence techniques focus on getting a machine to copy human intelligence. Classical artificial intelligence techniques focus on getting a machine to copy human intelligence. Marvin Minsky definition, “Artificial intelligence is the science of making machines do things that would require intelligence if done by men”. Marvin Minsky definition, “Artificial intelligence is the science of making machines do things that would require intelligence if done by men”. Definition side steps the concept of what intelligence is - merely points to machines copying humans. Definition side steps the concept of what intelligence is - merely points to machines copying humans.

4

5 Herb Simon Philosophy in 1957 described by Herb Simon Philosophy in 1957 described by Herb Simon “There are now in the world machines that think, that learn and that create. Moreover, their ability to do these things is going to increase rapidly until … the range of problems they can handle will be coextensive with the range to which the human mind has been applied”. “There are now in the world machines that think, that learn and that create. Moreover, their ability to do these things is going to increase rapidly until … the range of problems they can handle will be coextensive with the range to which the human mind has been applied”.

6 Top Down Approach An approach to artificial intelligence arose along the lines of a psychiatrist An approach to artificial intelligence arose along the lines of a psychiatrist Attempt to understand the human brain’s processing from the outside Attempt to understand the human brain’s processing from the outside Then attempt to build a machine to copy that way of functioning Then attempt to build a machine to copy that way of functioning

7 Reasoning One key aspect of human intelligence is the ability of the human brain to reason One key aspect of human intelligence is the ability of the human brain to reason Given a number of facts, the human brain makes a reasoned assumption about a situation and decides on a conclusion Given a number of facts, the human brain makes a reasoned assumption about a situation and decides on a conclusion E.g. if it is 7am and my clock alarm is ringing then it is time to get up E.g. if it is 7am and my clock alarm is ringing then it is time to get up

8 Expert Systems An expert system reasons about facts in a specific domain and works like an expert’s brain An expert system reasons about facts in a specific domain and works like an expert’s brain Needs knowledge about the domain, rules (from experts) to follow when new information occurs and a way of communicating with a user Needs knowledge about the domain, rules (from experts) to follow when new information occurs and a way of communicating with a user Called rule based systems, knowledge based systems or expert systems. Called rule based systems, knowledge based systems or expert systems.

9 MYCIN Early successful working system - a medical system Early successful working system - a medical system MYCIN contained 450 rules - claimed to be better than junior doctors and as good some experts. MYCIN contained 450 rules - claimed to be better than junior doctors and as good some experts. Built by interviewing large numbers of experts who reported from experience. Built by interviewing large numbers of experts who reported from experience. The rules reflected the uncertainties with medical conditions. The rules reflected the uncertainties with medical conditions.

10 Rules Rules of the form: Rules of the form: IF (condition) THEN (conclusion). IF (condition) THEN (conclusion). Several conditions may need to exist for the rule to fire. A rule may be: Several conditions may need to exist for the rule to fire. A rule may be: IF (condition1 and condition2 or condition3) THEN (conclusion). IF (condition1 and condition2 or condition3) THEN (conclusion). Example: IF (sneezing and coughing or headache) THEN (flu). Example: IF (sneezing and coughing or headache) THEN (flu).

11 Conflict Resolution There might be several possible conclusions that can be drawn from the facts There might be several possible conclusions that can be drawn from the facts The system needs further rules for such instances – this is conflict resolution The system needs further rules for such instances – this is conflict resolution In many situations several conditions are met but only one conclusion is required In many situations several conditions are met but only one conclusion is required Decision is needed - which rules takes precedence Decision is needed - which rules takes precedence

12 Conflict Resolution - Techniques Highest priority rule Highest priority rule Highest priority conditions Highest priority conditions Most recent condition Most recent condition Most specific (most conditions) Most specific (most conditions) Context limiting – rules in groups – a rule must belong to an active group Context limiting – rules in groups – a rule must belong to an active group

13 Multiple Rules Expert systems involve rules which depend on each other. Example: engine management: Expert systems involve rules which depend on each other. Example: engine management: Layer 1 Rules: Layer 1 Rules: IF (start button pressed) THEN (start engine) IF (start button pressed) THEN (start engine) IF (gear selection) THEN (engage gears) IF (gear selection) THEN (engage gears) Layer 2 Rule: Layer 2 Rule: IF (engine started and gears engaged) THEN (vehicle drive) IF (engine started and gears engaged) THEN (vehicle drive)

14 Forward Chaining Set of facts apparent at a particular time Set of facts apparent at a particular time These fire a number of rules These fire a number of rules Realizing facts which fire other rules Realizing facts which fire other rules So on until a goal is reached So on until a goal is reached Working from input data to end goal is forward chaining Working from input data to end goal is forward chaining Discover what can be deduced from facts. Discover what can be deduced from facts.

15 Backward Chaining Expert systems can be used in reverse fashion Expert systems can be used in reverse fashion When a goal has been achieved - rules are searched to see what facts occurred for the system to deduce its conclusion When a goal has been achieved - rules are searched to see what facts occurred for the system to deduce its conclusion What facts we must input to the system to realize a specific goal? What facts we must input to the system to realize a specific goal? E.g. what happened to cause the vehicle to drive? E.g. what happened to cause the vehicle to drive? From backward chaining - the start button was pressed and the gear selection had been made. From backward chaining - the start button was pressed and the gear selection had been made. Backward chaining good for system verification, where the expert system must be safety critical and cannot arrive at a ‘wrong’ conclusion. Backward chaining good for system verification, where the expert system must be safety critical and cannot arrive at a ‘wrong’ conclusion.

16 Expert System Advantages Easy to program (IF-THEN structure). Easy to program (IF-THEN structure). Each rule is a separate entity with its own data to fire and its own individual conclusion drawn Each rule is a separate entity with its own data to fire and its own individual conclusion drawn Ideal for dealing with natural real world information Ideal for dealing with natural real world information System structure is separate from the data - same expert system structure could be employed in very different domains System structure is separate from the data - same expert system structure could be employed in very different domains Can deal with uncertainty, e.g. 75% certain about the conclusion Can deal with uncertainty, e.g. 75% certain about the conclusion Speed of response – compared to a human expert Speed of response – compared to a human expert

17 Problems Gathering rules can be awkward. It is difficult for a person to put into simple terms what it is they do in an everyday situation. If several experts are being asked, they may well give contradictory answers Gathering rules can be awkward. It is difficult for a person to put into simple terms what it is they do in an everyday situation. If several experts are being asked, they may well give contradictory answers Human experts can be expensive & have full diaries Human experts can be expensive & have full diaries Combinatorial explosion. To deal with absolutely every eventuality, rules must be continually added to cover for every possible situation, no matter how unlikely. Combinatorial explosion. To deal with absolutely every eventuality, rules must be continually added to cover for every possible situation, no matter how unlikely. Time - some expert systems contain thousands of rules, to deal with something that may be simple all these rules must be tested, along with conflict resolution Time - some expert systems contain thousands of rules, to deal with something that may be simple all these rules must be tested, along with conflict resolution Expert systems just deal with one aspect of intelligence Expert systems just deal with one aspect of intelligence

18 Machine Learning Important though not to see such systems as merely programmed decision making mechanisms that will always perform as we expect Important though not to see such systems as merely programmed decision making mechanisms that will always perform as we expect It is possible to operate them in this way It is possible to operate them in this way It is also possible to enable them to learn as they draw conclusions and experience their domain It is also possible to enable them to learn as they draw conclusions and experience their domain If a system draws a number of conclusions then the rules which result in the ‘winning’ conclusion can be ‘rewarded’ by making them more likely to be part of the overall conclusion next time around. If a system draws a number of conclusions then the rules which result in the ‘winning’ conclusion can be ‘rewarded’ by making them more likely to be part of the overall conclusion next time around. If a fired rule results in a conclusion which is not chosen then it is less likely to fire again. Success is rewarded and failure is punished - Bucket Brigade If a fired rule results in a conclusion which is not chosen then it is less likely to fire again. Success is rewarded and failure is punished - Bucket Brigade

19 Fuzzy Logic & Fuzzy Rules With the expert systems we have considered thus far it has been assumed that either a condition exists or it doesn’t. This is Logic. A fact is either true or false With the expert systems we have considered thus far it has been assumed that either a condition exists or it doesn’t. This is Logic. A fact is either true or false It is found useful in certain circumstances for conclusions to be partially true - for a confidence percentage to be applied to results It is found useful in certain circumstances for conclusions to be partially true - for a confidence percentage to be applied to results If someone is having a shower they want the water to be warm. The water is not simply hot or cold, it is warm If someone is having a shower they want the water to be warm. The water is not simply hot or cold, it is warm Fuzzy logic provides a basis for this. Fuzzy logic provides a basis for this.

20 Example Assume for shower water to be completely cold it will be at a temperature of 0 deg C - to be completely hot it will be at a temperature of 50 deg C Assume for shower water to be completely cold it will be at a temperature of 0 deg C - to be completely hot it will be at a temperature of 50 deg C If the water is 65% hot – it is warm, but has some way to go to be hot. If it is 12% hot then it is pretty cold If the water is 65% hot – it is warm, but has some way to go to be hot. If it is 12% hot then it is pretty cold Using fuzzy logic this does not necessarily mean that the actual measured temperature would be 65% of 50, i.e. 32.5 Using fuzzy logic this does not necessarily mean that the actual measured temperature would be 65% of 50, i.e. 32.5 Fuzzy logic is more directed to a human concept of the temperature – it is a form of artificial intelligence Fuzzy logic is more directed to a human concept of the temperature – it is a form of artificial intelligence We can draw up a relationship between the actual temperature and the percentage value we will assign it, between 0% and 100%. We can draw up a relationship between the actual temperature and the percentage value we will assign it, between 0% and 100%.

21 Fuzzification A real-world value must be made fuzzy – e.g. the water temperature is measured and then fuzzified. A temperature of 20 oC might become a fuzzy value of 45% A real-world value must be made fuzzy – e.g. the water temperature is measured and then fuzzified. A temperature of 20 oC might become a fuzzy value of 45% The relationship between the actual value and fuzzy value needs to be defined – this could be done through graphical means or a look up table The relationship between the actual value and fuzzy value needs to be defined – this could be done through graphical means or a look up table The actual fuzzification routine depends entirely on the application. The actual fuzzification routine depends entirely on the application.

22 Fuzzy Rules Once a value has been fuzzified it is passed to the rules for evaluation. Once a value has been fuzzified it is passed to the rules for evaluation. Fuzzy rules are the same as before, E.g. IF (water is hot) THEN (turn water heater on) Fuzzy rules are the same as before, E.g. IF (water is hot) THEN (turn water heater on) The condition part and conclusion part will be a percentage value as they are only partially true. The water heater will not be turned on or off, but will be turned on to a certain extent The condition part and conclusion part will be a percentage value as they are only partially true. The water heater will not be turned on or off, but will be turned on to a certain extent It may be that a rule has several conditions that need to be satisfied It may be that a rule has several conditions that need to be satisfied E.g. IF (water temperature is hot AND energy tariff is high) THEN (turn water heater on) E.g. IF (water temperature is hot AND energy tariff is high) THEN (turn water heater on) Each of the conditions has a percentage assigned to it. Where the AND term appears so the MINIMUM percentage value of the conditions is carried forward. Where the OR term appears so the MAXIMUM percentage value of the conditions is carried forward. Each of the conditions has a percentage assigned to it. Where the AND term appears so the MINIMUM percentage value of the conditions is carried forward. Where the OR term appears so the MAXIMUM percentage value of the conditions is carried forward. E.g. after fuzzification the water temperature has been assigned a percentage 62% AND the energy tariff has been assigned a percentage 48%. The value carried forward will be 48%. E.g. after fuzzification the water temperature has been assigned a percentage 62% AND the energy tariff has been assigned a percentage 48%. The value carried forward will be 48%. Normally a number of different rules will fire. Each of the rules will result in a different value taken forward - these values must be aggregated to provide a single value that actually means something Normally a number of different rules will fire. Each of the rules will result in a different value taken forward - these values must be aggregated to provide a single value that actually means something

23 Defuzzification Simplest is to average the values. Simplest is to average the values. We have three rules R1, R2 and R3 which have produced the resultant percentage values. R1 – 23%, R2 – 81% and R3 – 49% - the average value would be the three percentages added together divided by three, i.e. 51%. We have three rules R1, R2 and R3 which have produced the resultant percentage values. R1 – 23%, R2 – 81% and R3 – 49% - the average value would be the three percentages added together divided by three, i.e. 51%. Some rules may be more important than others - Centre of Gravity (COG) method. Some rules may be more important than others - Centre of Gravity (COG) method. If Rule R1 is more important than the others, give it a weighting of 5, R2 a weighting of 2 and R3 a weighting of 3. We multiply 23 by 5, 81 by 2 and 49 by 3, the result of which is 424, which, when we divide it by the sum=10, gives us a defuzzified value of 42.4%. It is lower than the unweighted calculation as emphasis was placed on R1 If Rule R1 is more important than the others, give it a weighting of 5, R2 a weighting of 2 and R3 a weighting of 3. We multiply 23 by 5, 81 by 2 and 49 by 3, the result of which is 424, which, when we divide it by the sum=10, gives us a defuzzified value of 42.4%. It is lower than the unweighted calculation as emphasis was placed on R1

24 Problem Solving We may need an AI system to solve problems for us. One example of this exists in a SatNav. We know where our start point is and we know where we wish to get to, but we don’t know how to get there. We may need an AI system to solve problems for us. One example of this exists in a SatNav. We know where our start point is and we know where we wish to get to, but we don’t know how to get there. Many solutions exist. We usually have further requirements, we wish to know the quickest route or the shortest one. This problem is something that AI can be very good at solving - quickly. Many solutions exist. We usually have further requirements, we wish to know the quickest route or the shortest one. This problem is something that AI can be very good at solving - quickly. Assume we wish to travel from Reading to Newcastle. Many possible routes – we could travel from Reading to Oxford or Reading to London. Both routes have costs associated with them - the time the route would take, the petrol used and so on. From Oxford we could travel to Banbury etc. Until Newcastle was reached. Assume we wish to travel from Reading to Newcastle. Many possible routes – we could travel from Reading to Oxford or Reading to London. Both routes have costs associated with them - the time the route would take, the petrol used and so on. From Oxford we could travel to Banbury etc. Until Newcastle was reached. Assume we limit the number of possible towns to be considered from Reading to Newcastle and we only visit a town once - there are a number of ways that an AI system could search for the best solution. Assume we limit the number of possible towns to be considered from Reading to Newcastle and we only visit a town once - there are a number of ways that an AI system could search for the best solution.

25 Searching To decide the best solution to our travel problem we must consider all possibilities To decide the best solution to our travel problem we must consider all possibilities In our example with Reading as a start point then we could search for the best route by firstly looking at all the possible towns to travel to from Reading – Oxford and London included. From each of those towns we could then look at all choices - cost In our example with Reading as a start point then we could search for the best route by firstly looking at all the possible towns to travel to from Reading – Oxford and London included. From each of those towns we could then look at all choices - cost We would eventually arrive at Newcastle via a number of different routes. As we know the total cost of each route then we can decide which is best in terms of distance, time or whatever We would eventually arrive at Newcastle via a number of different routes. As we know the total cost of each route then we can decide which is best in terms of distance, time or whatever

26 Methods Depth first search Depth first search Breadth first search Breadth first search Depth limited search Depth limited search Bidirectional search Bidirectional search Heuristic search Heuristic search

27 Example In May 1997 the IBM computer ‘Deep Blue’ beat the erstwhile human world chess champion, Gary Kasparov, over a 6 match series. In May 1997 the IBM computer ‘Deep Blue’ beat the erstwhile human world chess champion, Gary Kasparov, over a 6 match series. The computer was capable of searching and analyzing 200 million positions every second The computer was capable of searching and analyzing 200 million positions every second Kasparov said: “There were many, many discoveries in this match, and one of them was that sometimes the computer plays very, very human moves. It deeply understands positional factors”. Kasparov said: “There were many, many discoveries in this match, and one of them was that sometimes the computer plays very, very human moves. It deeply understands positional factors”.

28 Frames A frame represents everyday knowledge about an entity A frame represents everyday knowledge about an entity It is a computer file, with a number of pieces of information stored in slots in the file. Each of those slots is a sub-frame with further levels of information. It is a computer file, with a number of pieces of information stored in slots in the file. Each of those slots is a sub-frame with further levels of information. If we have a frame based artificial intelligence system used to describe a house – the initial frame is the house If we have a frame based artificial intelligence system used to describe a house – the initial frame is the house Within the house are slots, dining room, kitchen, lounge. Each slot is a frame itself. A kitchen frame contains slots, refrigerator, cooker, sink etc. These slots are frames with their own slots. Within the house are slots, dining room, kitchen, lounge. Each slot is a frame itself. A kitchen frame contains slots, refrigerator, cooker, sink etc. These slots are frames with their own slots.

29 Data Mining Extracting knowledge from data is called data mining. Extracting knowledge from data is called data mining. AI systems are well suited - they store enormous quantities of data and can draw out all sorts of relationships AI systems are well suited - they store enormous quantities of data and can draw out all sorts of relationships The amount of data in the world doubles each year – in a ten year span (e.g. 2002 to 2012) there will be a 1,000 times increase in data! The amount of data in the world doubles each year – in a ten year span (e.g. 2002 to 2012) there will be a 1,000 times increase in data! New data is usually not well understood and meanings are not readily drawn out. E.g. The human genome project has opened up the complexities of DNA - we can look at the functioning of brains and make sense of it based on the data New data is usually not well understood and meanings are not readily drawn out. E.g. The human genome project has opened up the complexities of DNA - we can look at the functioning of brains and make sense of it based on the data There are new business opportunities, new medical techniques and a more in depth understanding of the scientific world There are new business opportunities, new medical techniques and a more in depth understanding of the scientific world

30 Correlations To discover similarities, links and relationships between data and to predict outcomes To discover similarities, links and relationships between data and to predict outcomes Example - supermarket shopping. Such shopping is a regular exercise. Approximately 100 different types of produce available. Every time a person uses the supermarket, data is obtained on their purchases Example - supermarket shopping. Such shopping is a regular exercise. Approximately 100 different types of produce available. Every time a person uses the supermarket, data is obtained on their purchases Links can be drawn as to what a person buys and how often they buy it OR which people buy certain products and when they buy them Links can be drawn as to what a person buys and how often they buy it OR which people buy certain products and when they buy them We want a prediction - next Thursday a person will enter the supermarket, they will buy certain products – if they are available, the person will buy other products based on our predictions. Over 1,000 people it may well be sufficiently accurate for a significant profit We want a prediction - next Thursday a person will enter the supermarket, they will buy certain products – if they are available, the person will buy other products based on our predictions. Over 1,000 people it may well be sufficiently accurate for a significant profit Correlation - Look at a person’s purchases of milk and cheese. Over a one year period this can be analyzed to see how the two pieces of data are related to each other. Correlation - Look at a person’s purchases of milk and cheese. Over a one year period this can be analyzed to see how the two pieces of data are related to each other. A number of statistical tools are available for this, Principal Component Analysis, which detects the main links between pieces of data, e.g. for one person the purchasing of shoe polish may be closely linked to buying pickles. A number of statistical tools are available for this, Principal Component Analysis, which detects the main links between pieces of data, e.g. for one person the purchasing of shoe polish may be closely linked to buying pickles.

31 Decision Trees To reduce the complexity of problems to make a database easier to analyze - decision trees. To reduce the complexity of problems to make a database easier to analyze - decision trees. The data base is chopped up into manageable portions which makes it easy to follow a path through the tree. The data base is chopped up into manageable portions which makes it easy to follow a path through the tree. For the supermarket example, we could only consider female purchasers. A user specified branch - only data associated with female purchasers need be considered For the supermarket example, we could only consider female purchasers. A user specified branch - only data associated with female purchasers need be considered We can input requirements, the branches of which could be discovered as a part of the analysis. E.g. only those who spend more than £60, regularly purchase soup and buy fresh vegetables. We can input requirements, the branches of which could be discovered as a part of the analysis. E.g. only those who spend more than £60, regularly purchase soup and buy fresh vegetables. Rather than dealing with a large number of people, say 50,000, we may only need to consider 1,000, which will reduce the time taken and improve the accuracy of results Rather than dealing with a large number of people, say 50,000, we may only need to consider 1,000, which will reduce the time taken and improve the accuracy of results

32 Concluding Comments Classical AI techniques are based on trying to get machines to copy humans in tasks that when humans do those tasks, we deem them to be intelligent acts Classical AI techniques are based on trying to get machines to copy humans in tasks that when humans do those tasks, we deem them to be intelligent acts Discussion ranged from the way we store information (frames) to how we reason and decide (expert systems) Discussion ranged from the way we store information (frames) to how we reason and decide (expert systems) Motivation - advantages of artificial intelligence when compared with human intelligence – to replace humans! Motivation - advantages of artificial intelligence when compared with human intelligence – to replace humans! Speed of processing, accuracy of mathematical calculations, extent of memory, relating complex data and the ability to function 24/7 Speed of processing, accuracy of mathematical calculations, extent of memory, relating complex data and the ability to function 24/7 Intelligence is a controversial topic Intelligence is a controversial topic When we consider machines being intelligent this raises the stakes When we consider machines being intelligent this raises the stakes How does machine intelligence compare with human intelligence? Can a machine be alive? Next we look at philosophical issues that underpin the subject How does machine intelligence compare with human intelligence? Can a machine be alive? Next we look at philosophical issues that underpin the subject

33 Next Philosophy of New AI Philosophy of New AI

34 Contact Information Web site: www.kevinwarwick.com Web site: www.kevinwarwick.comwww.kevinwarwick.com Email: k.warwick@reading.ac.uk Email: k.warwick@reading.ac.ukk.warwick@reading.ac.uk Tel: (44)-1189-318210 Tel: (44)-1189-318210 Fax: (44)-1189-318220 Fax: (44)-1189-318220 Professor Kevin Warwick, Department of Cybernetics, University of Reading, Whiteknights, Reading, RG6 6AY,UK Professor Kevin Warwick, Department of Cybernetics, University of Reading, Whiteknights, Reading, RG6 6AY,UK


Download ppt "A New Artificial Intelligence 3 Kevin Warwick. Classical AI Humans like to compare ourselves with others Humans like to compare ourselves with others."

Similar presentations


Ads by Google