1 / 20

Approaches to A. I.

Approaches to A. I. Human Rational. Thinking Acting. (Artificial) Neural Networks. Biological inspiration Synthetic networks non-Von Neumann Machine learning Perceptrons – MATH Perceptron learning Varieties of Artificial Neural Networks. Brain - Neurons.

tasya
Télécharger la présentation

Approaches to A. I.

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Approaches to A. I. Human Rational Thinking Acting

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

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

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

  5. Modeling the Neural Network

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

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

  8. The Percepton • A simple computational model of a single neuron. • Frank Rosenblatt, 1957 • The entries in are usually real-valued (not limited to 0 and 1)

  9. The Perceptron

  10. Perceptrons can be combined to make a network

  11. How to “program” a Perceptron? • Programming a Perceptron means determining the values in . • That’s worse than C or Fortran! • Back to induction: Ideally, we can find from a set of classified inputs.

  12. Perceptron Learning Rule Training data: Valid weights: Perceptron function:

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

  14. Feed-forward network

  15. Recurrent Neural Networks

  16. Hopfield Network

  17. On Learning the Past Tense of English Verbs • Rumelhart and McClelland, 1980s

  18. On Learning the Past Tense of English Verbs

  19. On Learning the Past Tense of English Verbs

  20. 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

More Related