Transcript Slides
AI History, Philosophical Foundations Part 2 Some highlights from early history of AI • Gödel’s theorem: 1930 • Turing machines: 1936 • McCulloch and Pitts neurons: 1943 (introduced field of "neural networks”) • Von Neumann self-reproducing automaton: 1940s • Dartmouth workshop: 1956 (2006 is 50th anniversary) • 1950s: – Lisp (McCarthy) – Logic Theorist (Newell and Simon) – General Problem Solver (Newell and Simon) – Learning checkers player (Samuel) – Geometry theorem prover (Gelernter) – Perceptrons (Rosenblatt) • Minsky and Papert Perceptrons book: 1969 "In from three to eight years, we'll have a machine with the general intelligence of an average human being.“ Marvin Minsky to Life magazine, 1970 Means-Ends Analysis (“General Problem Solver”) 1. Compare the current state with the goal state; find a difference between them. 2. Find in memory an operator that experience has taught reduces differences of this kind; 3. Apply the operator to change the state. 4. If state = goal state, return “success”, else go to 1. (See transparancies) Newell and Simon: Physical Symbol System hypothesis: “A physical symbol system has the necessary and sufficient means of general intelligent action.” Quote from Searle: “I thought the whole idea of strong AI is that we don’t need to know how the brain operates to know how the mind works. The basic hypothesis, or so I had supposed, was that there is a level of mental operations consisting of computational processes over formal elements that constitute the essence of the mental and can be realized in all sorts of different brain processes, in the same way that any computer program can be realized in different computer hardware: on the assumptions of strong AI, the mind is to the brain as the program is to the hardware, and thus we can understand the mind without doing neurophysiology.” Blocks World (used by Shrdlu) The dialog that was used as a SHRDLU demo: Person: PICK UP A BIG RED BLOCK. Computer: OK. (does it) Person: GRASP THE PYRAMID. Computer: I DON'T UNDERSTAND WHICH PYRAMID YOU MEAN. Person: FIND A BLOCK WHICH IS TALLER THAN THE ONE YOU ARE HOLDING AND PUT IT INTO THE BOX. Computer: BY "IT", I ASSUME YOU MEAN THE BLOCK WHICH IS TALLER THAN THE ONE I AM HOLDING. Computer: OK. (does it) Person: WHAT DOES THE BOX CONTAIN? Computer: THE BLUE PYRAMID AND THE BLUE BLOCK. Person: WHAT IS THE PYRAMID SUPPORTED BY? Computer: THE BOX. Person: HOW MANY BLOCKS ARE NOT IN THE BOX? Computer: FOUR OF THEM. Person: IS AT LEAST ONE OF THEM NARROWER THAN THE ONE WHICH I TOLD YOU TO PICK UP? Computer: YES, THE RED CUBE. Person: IS IT SUPPORTED? Computer: YES, BY THE TABLE. Person: CAN THE TABLE PICK UP BLOCKS? Computer: NO. Person: CAN A PYRAMID BE SUPPORTED BY A BLOCK? Computer: YES. Person: CAN A PYRAMID SUPPORT A PYRAMID? Computer: I DON'T KNOW. Person: STACK UP TWO PYRAMIDS. Computer: I CAN'T. Person: WILL YOU PLEASE STACK UP BOTH OF THE RED BLOCKS AND EITHER A GREEN CUBE OR A PYRAMID? Computer: OK. (does it) Person: WHICH CUBE IS SITTING ON THE TABLE? Computer: THE LARGE GREEN ONE WHICH SUPPORTS THE RED PYRAMID. Person: IS THERE A LARGE BLOCK BEHIND A PYRAMID? Computer: YES, THREE OF THEM: A LARGE RED ONE, A LARGE GREEN CUBE, AND THE BLUE ONE. Person: PUT A SMALL ONE ONTO THE GREEN CUBE WHICH SUPPORTS A PYRAMID. Computer: OK. (does it) Blocks world (Winston) • Input was a line drawing of a blocks world structure. • Program produced a semantic net representation of the structural description of the object biological neuron artificial neuron A two-layer neural network Output layer (activation represents classification) Hidden layer (“internal representation”) Input layer (activations represent feature vector for one training example) Weighted connections ALVINN (Pomerleau, 1993) • ALVINN learns to drive an autonomous vehicle at normal speeds on public highways (!) • Input: 30 x 32 grid of pixel intensities from camera Each output unit correspond to a particular steering direction. The most highly activated one gives the direction to steer.