Presentation is loading. Please wait.

Presentation is loading. Please wait.

Artificial Intelligence In the Real World Computing Science University of Aberdeen.

Similar presentations


Presentation on theme: "Artificial Intelligence In the Real World Computing Science University of Aberdeen."— Presentation transcript:

1 Artificial Intelligence In the Real World Computing Science University of Aberdeen

2 Artificial Intelligence In the Real World Artificial Intelligence In the Movies

3 Artificial Intelligence In the Real World Artificial Intelligence In the Movies

4 Artificial Intelligence In the Real World Artificial Intelligence In the Movies ?

5 Artificial Intelligence Began in 1956… Great expectations… Machines will be capable, within twenty years, of doing any work that a man can do. Herbert Simon, 1965.

6 What Happened? Machines will be capable, within twenty years, of doing any work that a man can do. Herbert Simon, 1965.

7 What Happened? Machines cant do everything a man can do… People thought machines could replace humans… instead they are usually supporting humans Machines will be capable, within twenty years, of doing any work that a man can do. Herbert Simon, 1965.

8 What Happened? Machines cant do everything a man can do… People thought machines could replace humans… instead they are usually supporting humans Healthcare, Science, Government, Business, Military… Machines will be capable, within twenty years, of doing any work that a man can do. Herbert Simon, 1965.

9 What Happened? Machines cant do everything a man can do… People thought machines could replace humans… instead they are usually supporting humans Healthcare, Science, Government, Business, Military… Most difficult problems are solved my human+machine astronomy, nuclear physics, genetics, maths, drug discovery… Machines will be capable, within twenty years, of doing any work that a man can do. Herbert Simon, 1965.

10 Neural Networks Neural Networks are a popular Artificial Intelligence technique Used in many applications which help humans The idea comes from trying to copy the human brain…

11 Fascinating Brain Facts… 100,000,000,000 = 10 11 neurons 100 000 are irretrievably lost each day Each neuron connects to 10,000 -150,000 others Every person on planet make 200 000 phone calls same number of connections as in a single human brain in a day Grey part folded to fit - would cover surface of office desk The gray cells occupy only 5% of our brains 95% is taken up by the communication network between them About 2x10 6 km of wiring (to the moon and back twice) Pulses travel at more than 400 km/h (250 mph) 2% of body weight… but consumes 20% of oxygen All the time! Even when sleeping What about copying neurons in Computers?

12 Artificial Neural Network (ANN) loosely based on biological neuron Each unit is simple, but many connected in a complex network If enough inputs are received Neuron gets excited Passes on a signal, or fires ANN different to biological: ANN outputs a single value Biological neuron sends out a complex series of spikes Biological neurons not fully understood Image from Purves et al., Life: The Science of Biology, 4th Edition, by Sinauer Associates and WH Freeman Biological Inspiration

13 Now play with the flash animation to see how synapses work http://www.mind.ilstu.edu/curriculum/neurons_intro/flash_sum mary.php?modGUI=232&compGUI=1828&itemGUI=3160 (Maybe this is a bit too long – about 3 or 4 mins)

14 The Perceptron add weight 1 output input 1 input 2 input 3 input 4 weight 4 (threshold) weight 2 weight 3

15 The Perceptron add weight 1 output input 1 input 2 input 3 input 4 weight 4 (threshold) weight 2 weight 3 Save Graph and Data

16 The Perceptron Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 1Richard11010 2Alan11101 3Alison00100 4Jeff01010 5Gail10111 6Simon01110 Save Graph and Data

17 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.2 Threshold = 0.5 0.2 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 1Richard11010

18 The Perceptron add 0.15 _ output First last year _ Male _ hardworking _ Lives in halls 0.15 Threshold = 0.5 0.15 0.2 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 1Richard11010

19 The Perceptron add 0.15 _ output First last year _ Male _ hardworking _ Lives in halls 0.15 Threshold = 0.5 0.15 0.2 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 2Alan11101

20 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.15 Threshold = 0.5 0.2 0.25 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 2Alan11101

21 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.15 Threshold = 0.5 0.2 0.25 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 3Alison00100

22 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.15 Threshold = 0.5 0.2 0.25 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 4Jeff01010

23 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.15 Threshold = 0.5 0.2 0.25 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 5Gail10111

24 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.15 Threshold = 0.5 0.2 0.25 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 6Simon01110

25 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.15 0.20 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 6Simon01110

26 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.15 0.20 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 1Richard11010

27 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.15 0.20 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 2Alan11101

28 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.15 0.20 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 3Alison00100

29 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.15 0.20 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 4Jeff01010

30 The Perceptron add 0.2 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.15 0.20 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 5Gail10111

31 The Perceptron add 0.25 _ output First last year _ Male _ hardworking _ Lives in halls 0.15 Threshold = 0.5 0.15 0.25 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 5Gail10111

32 The Perceptron add 0.25 _ output First last year _ Male _ hardworking _ Lives in halls 0.15 Threshold = 0.5 0.15 0.25 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 6Simon01110

33 The Perceptron add 0.25 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.10 0.20 Note: example from Alison Cawsey studentfirst last year maleworks hard Lives in halls First this year 6Simon01110

34 The Perceptron add 0.25 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.10 0.20 Finished

35 The Perceptron add 0.25 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.10 0.20 Finished Ready to try unseen examples

36 The Perceptron add 0.25 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.10 0.20 studentfirst last year maleworks hard Lives in halls First this year James0101?

37 The Perceptron add 0.25 _ output First last year _ Male _ hardworking _ Lives in halls 0.10 Threshold = 0.5 0.10 0.20 Simple perceptron works ok for this example But sometimes will never find weights that fit everything In our example: Important: Getting a first last year, Being hardworking Not so important: Male, Living in halls Suppose there was an exclusive or Important: (male) OR (live in halls), but not both Cant capture this relationship

38 Stock Exchange Example Company NameCompany less than 2 years old Paid dividend >10% last year Share price increases in following year 1Robot Components Ltd. 110 2Silicon Devices101 3Bleeding Edge Software 000 4Human Interfaces Inc. 110 5Data Management Inc. 011 6Intelligent Systems110

39 Multilayer Networks We saw: perceptron cant capture relationships among inputs Multilayer networks can capture complicated relationships

40 Stock Exchange Example Hidden Layer

41 Neural Net example: ALVINN Autonomous vehicle controlled by Artificial Neural Network Drives up to 70mph on public highways Note: most images are from the online slides for Tom Mitchells book Machine Learning

42 Neural Net example: ALVINN Autonomous vehicle controlled by Artificial Neural Network Drives up to 70mph on public highways

43 Neural Net example: ALVINN Input is 30x32 pixels = 960 values 1 input pixel 4 hidden units 30 output units Sharp right Straight ahead Sharp left

44 Neural Net example: ALVINN Input is 30x32 pixels = 960 values 1 input pixel 4 hidden units 30 output units Sharp right Straight ahead Sharp left Learning means adjusting weight values

45 Neural Net example: ALVINN Input is 30x32 pixels = 960 values 1 input pixel 4 hidden units 30 output units Sharp right Straight ahead Sharp left

46 Neural Net example: ALVINN

47 This shows one hidden node Input is 30x32 array of pixel values = 960 values Note: no special visual processing Size/colour corresponds to weight on link

48 Neural Net example: ALVINN Output is array of 30 values This corresponds to steering instructions E.g. hard left, hard right This shows one hidden node Input is 30x32 array of pixel values = 960 values Note: no special visual processing Size/colour corresponds to weight on link

49 Lets try a more complicated example with the program… In this example well get the program to help us to build the neural network

50 Neural Network Applications Particularly good for pattern recognition

51 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical

52 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical Character recognition (typed or handwritten)

53 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical Character recognition (typed or handwritten) Image recognition (e.g. human faces)

54 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical Character recognition (typed or handwritten) Image recognition (e.g. human faces) Robot control - hand-arm-block.mpg

55 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical Character recognition (typed or handwritten) Image recognition (e.g. human faces) Robot control ECG pattern – had a heart attack?

56 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical Character recognition (typed or handwritten) Image recognition (e.g. human faces) Robot control ECG pattern – had a heart attack? Application for credit card or mortgage

57 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical Character recognition (typed or handwritten) Image recognition (e.g. human faces) Robot control ECG pattern – had a heart attack? Application for credit card or mortgage Data Mining on Customers

58 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical Character recognition (typed or handwritten) Image recognition (e.g. human faces) Robot control ECG pattern – had a heart attack? Application for credit card or mortgage Data Mining on Customers Other types of Data Mining - Science

59 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical Character recognition (typed or handwritten) Image recognition (e.g. human faces) Robot control ECG pattern – had a heart attack? Application for credit card or mortgage Data Mining on Customers Other types of Data Mining Spam filtering

60 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical Character recognition (typed or handwritten) Image recognition (e.g. human faces) Robot control ECG pattern – had a heart attack? Application for credit card or mortgage Data Mining on Customers Other types of Data Mining Spam filtering Shape in Go

61 Neural Network Applications Particularly good for pattern recognition Sound recognition – voice, or medical Character recognition (typed or handwritten) Image recognition (e.g. human faces) Robot control ECG pattern – had a heart attack? Application for credit card or mortgage Data Mining on Customers Other types of Data Mining Spam filtering Shape in Go… and many more!

62 What are Neural Networks Good For? When training data is noisy, or inaccurate E.g. camera or microphone inputs Very fast performance once network is trained Can accept input numbers from sensors directly Human doesnt need to interpret them first

63 What are Neural Networks Good For? When training data is noisy, or inaccurate E.g. camera or microphone inputs Very fast performance once network is trained Can accept input numbers from sensors directly Human doesnt need to interpret them first Need a lot of data – training examples Training time could be very long This is the big problem for large networks Network is like a black box A human cant look inside and understand what has been learnt Precise logical rules would be easier to understand Disadvantages?


Download ppt "Artificial Intelligence In the Real World Computing Science University of Aberdeen."

Similar presentations


Ads by Google