CSCI 4150 Learning Machines and Perceptron

CSCI 4150 Learning Machines and Perceptron - Learning...

Info icon This preview shows pages 1–2. Sign up to view the full content.

Learning machines and the perceptron 5 5.1 Learning Machines 23 5.2 The McCulloch-Pitts neuron model 24 5.3 The perceptron 24 5.4 Summary 26 This chapter gives a brief historical introduction to learning machines and neural networks, before treating this area in a more modern fashion in the following chapters. 5.1 Learning Machines We have, so far, mainly looked at programming strategies to solve complex tasks. Specifically, we formulated complex tasks as search problems in a con- figuration space and then discussed general search strategies in potentially large spaces. Search is a huge component of AI. Of course, the real challenge is with the AI engineer to translate the problem into the programmable structure (ab- stractions) and to find the principle solution strategy. A further main area of AI is that of reasoning . In this area, we consider some information given to us and how we combine such information to make statements that are derived from such facts (e.g. if such and such, then ... ). This included propositional logic and higher order logic. Many of these strategies have gone a long way to solve complex tasks such as providing support for decision making or making computers that are good game players. However, many years of research and the analysis of common challenges has pointed to a common problem in AI. The major challenges for AI is that many problem domains in the real world are, at least in the eyes of a common observer, ever changing and unreliable . Modern research is AI is therefore looking into tackling this problem domain with two major strategies that dominate modern AI, that of machine learning (ML) and probabilistic reasoning (PR). Learning machines are important for several reasons. For example, such machines have the potential to find solutions strategies on their own when solutions are not known a priori, and, maybe more importantly, machines that are capable of learning have the ability to adapt to changing situations or to situations that have not been considered by the engineer when setting up the machine.
Image of page 1

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

Image of page 2
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