Approaches to A I Human Rational Thinking like

  • Slides: 20
Download presentation
Approaches to A. I. Human Rational Thinking like humans • Cognitive science Thinking •

Approaches to A. I. Human Rational Thinking like humans • Cognitive science Thinking • Neuron level • Neuroanatomical level • Mind level Acting like humans • Understand language • Play games • Control the body • The Turing Test Thinking rationally • Aristotle, syllogisms • Logic • “Laws of thought” Acting rationally • Business approach • Results oriented

(Artificial) Neural Networks • • Biological inspiration Synthetic networks non-Von Neumann Machine learning Perceptrons

(Artificial) Neural Networks • • Biological inspiration Synthetic networks non-Von Neumann Machine learning Perceptrons – MATH Perceptron learning Varieties of Artificial Neural Networks

Brain - Neurons 10 billion neurons (in humans) Each one has an electro-chemical state

Brain - Neurons 10 billion neurons (in humans) Each one has an electro-chemical state

Brain – Network of Neurons Each neuron has on average 7, 000 synaptic connections

Brain – Network of Neurons Each neuron has on average 7, 000 synaptic connections with other neurons. A neuron “fires” to communicate with neighbors.

Modeling the Neural Network

Modeling the Neural Network

von Neumann Architecture Separation of processor and memory. One instruction executed at a time.

von Neumann Architecture Separation of processor and memory. One instruction executed at a time.

Animal Neural Architecture von Neumann Birds and bees (and us) • Separate processor and

Animal Neural Architecture von Neumann Birds and bees (and us) • Separate processor and memory • Sequential instructions • Each neuron has state and processing • Massively parallel, massively interconnected.

The Percepton •

The Percepton •

The Perceptron

The Perceptron

Perceptrons can be combined to make a network

Perceptrons can be combined to make a network

How to “program” a Perceptron? •

How to “program” a Perceptron? •

Perceptron Learning Rule Training data: Input x 1 x 2 12 9 -2 8

Perceptron Learning Rule Training data: Input x 1 x 2 12 9 -2 8 3 0 9 -0. 5 Valid weights: Perceptron function: Output 1 if avg(x 1, x 2)>x 3, 0 otherwise x 3 6 15 3 4 1 0 0 1

Varieties of Artificial Neural Networks • Neurons that are not Perceptrons. • Multiple neurons,

Varieties of Artificial Neural Networks • Neurons that are not Perceptrons. • Multiple neurons, often organized in layers.

Feed-forward network

Feed-forward network

Recurrent Neural Networks

Recurrent Neural Networks

Hopfield Network

Hopfield Network

On Learning the Past Tense of English Verbs • Rumelhart and Mc. Clelland, 1980

On Learning the Past Tense of English Verbs • Rumelhart and Mc. Clelland, 1980 s

On Learning the Past Tense of English Verbs

On Learning the Past Tense of English Verbs

On Learning the Past Tense of English Verbs

On Learning the Past Tense of English Verbs

Neural Networks • Alluring because of their biological inspiration – degrade gracefully – handle

Neural Networks • Alluring because of their biological inspiration – degrade gracefully – handle noisy inputs well – good for classification – model human learning (to some extent) – don’t need to be programmed • Limited – hard to understand, impossible to debug – not appropriate for symbolic information processing