Presentation is loading. Please wait.

Presentation is loading. Please wait.

Artificial Intelligence What is the (physical) basis of intelligence? The Brain (it “thinks”) The Computer (it “calculates”) The Physical World (it “is”)

Similar presentations


Presentation on theme: "Artificial Intelligence What is the (physical) basis of intelligence? The Brain (it “thinks”) The Computer (it “calculates”) The Physical World (it “is”)"— Presentation transcript:

1 Artificial Intelligence What is the (physical) basis of intelligence? The Brain (it “thinks”) The Computer (it “calculates”) The Physical World (it “is”) Symbols point to signifieds

2

3 What is Intelligence?

4

5 Pattern Recognition

6

7

8

9

10

11 Hofstadter’s Idea “What if” driving down a country road you meet a swarm of bees Lucky my window wasn’t open Lucky I wasn’t on my bike If I was a deer I would have been killed Pity they weren’t £10 notes Lucky those bees weren’t made of cement

12

13 Two Approaches Connexionism Computationalism

14

15 Nature Inspired Computing Artificial Neural Nets - Symbiosis between computer and cognitive sciences

16

17 Cajal -1- CajalGolgi Cajal + Golgi indentification of independent neurons by staining, microscopy and looking. (Nobel Prize 1906)

18

19 Cajal -2-

20

21 Rat Neurons

22

23 Investigation of Single Neurons Microelectrode recording of Biological Neuron activation using tungsten electrode Hubel and Weisel. Nobel Prize 1958 Photomicrograph: Height = 1mm.

24

25 Biological Neurons dendrites axon synapse Signal flow Big Neurological principle #1 Neurons work using electricity, not blood or other special goo Signal shape

26

27 Single Neuron In 2 In 1 In 3 In 4 “activation” “input” A C B D “threshold” Big Neurological principle #2 “Integrate and Fire” Inputs summed. If above threshold output fires.

28

29 Learning in Neural Nets Before Learning After Learning Big Neurological principle #3 “Hebbian Learning” Synapse strength increases if both cells A and B are firing A A B B

30

31 Brains Minds and Computers BrainsComputers Work using Electricity Have inputs and outputs Can learn by experience Can be taught Work using Electricity Have inputs and outputs Can be programmed ? Can they learn ? ? Can they be taught ? So do we understand brains? Yep. Do we therefore understand Minds?Nope.

32

33 Artificial Neurons In 1 In 2 In 3 “output” “input” A C B D “threshold” inputs output

34

35 Learning Logical Gates ? Threshold = A B A B ? Ouput neuron fires only when sum is greater than the threshold AND - gate OR - gate ABO 000 010 100 111 ABO 000 011 101 111

36

37 Training an Artificial Neural Net eyesmotors right left

38

39 Back Propagation of Errors eyesmotors right left 10.5 eyesmotors right left 1 0.5

40

41 Neural Net Solver

42

43 Medical Application Flu Neural Net cough headache

44

45 Medical Diagnosis Cough Headache Meningitis Flu Pneuomonia Not ill 1 Cough Headache 1 Flu 1

46

47 “Classical” Medical Diagnosis If ( (symptom ! = cough) && (symptom != headache) ) illness = no illness; else if ( (symptom ! = cough) && (symptom == headache) ) illness = meningitis; else if ( (symptom == cough) && (symptom != headache) ) illness = pneumonia; else if ( (symptom == cough) && (symptom == headache) ) illness = flu; Rule-based Learning “ if … then …. else … “

48 CBP 2009-10Comp 3104 The Nature of Computing 48

49 ECG Interpretation

50

51 NNets vs Expert Systems ModelingExamplesExplanation EffortNeededProvided Rule-based Exp. Syst.highlowhigh Bayesian Netshighlowmoderate Classification Treeslowhigh“high” Neural Netslowhighlow Regression Modelshighmoderatemoderate

52


Download ppt "Artificial Intelligence What is the (physical) basis of intelligence? The Brain (it “thinks”) The Computer (it “calculates”) The Physical World (it “is”)"

Similar presentations


Ads by Google