COS4852 Answers.pdf - Artificial Neural Networks The future...

Info icon This preview shows pages 1–13. Sign up to view the full content.

View Full Document Right Arrow Icon
Artificial Neural Networks
Image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
The future of AI
Image of page 2
Restaurant Data Set
Image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Limited Expressiveness of Perceptrons
Image of page 4
The XOR affair Minsky and Papert (1969) showed certain simple functions cannot be represented (e.g. Boolean XOR). Killed the field! Mid 80 th : Non-linear Neural Networks (Rumelhart et al. 1986)
Image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
The XOR affair
Image of page 6
Neural Networks Rich history, starting in the early forties (McCulloch and Pitts 1943). Two views: Modeling the brain “Just” representation of complex functions (Continuous; contrast decision trees) Much progress on both fronts. Drawn interest from: Neuroscience, Cognitive science, AI, Physics, Statistics, and CS/EE.
Image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Neuron
Image of page 8
Neural Structure 1. Cell body; one axon (delivers output to other connect neurons); many dendrites (provide surface area for connections from other neurons). 2. Axon is a single long fiber. 100 or more times the diameter of cell body. Axon connects via synapses to dendrites of other cells. 3. Signals propagated via complicated electrochemical reaction. 4. Each neuron is a “threshold unit”. Neurons do nothing unless the collective influence from all inputs reaches a threshold level. 5. Produces full- strength output. “fires”. Stimulation at some synapses encourages neurons to fire; some discourage from firing. 6. Synapses can increase ( excitatory ) or decrease ( inhibitory ) potential (signal
Image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Why Neural Nets? Motivation: Solving problems under the constraints similar to those of the brain may lead to solutions to AI problems that would otherwise be overlooked. Individual neurons operate very slowly But the brain does complex tasks fast: massively parallel algorithms Neurons are failure-prone devices But brain is reliable anyway distributed representations Neurons promote approximate matching less brittle learnable
Image of page 10
Image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Connectionist Models of Learning Characterized by: A large number of very simple neuron-like processing elements.
Image of page 12
Image of page 13
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern