End-to-end learning

From Computer Science Wiki
Revision as of 01:48, 14 July 2017 by 18wilk w (talk | contribs)
Jump to navigation Jump to search

Exclamation.png This is student work which has not yet been approved as correct by the instructor WIP need to check grammar and structure, other than that i have done everything

Case study notes[1]

Introduction[edit]

End-to-end learning process is a type of Deep_learning process in which all of the parameters are trained jointly, rather than step by step. [2] Furthermore, just like in the case of Deep_learning precess, in end-to-end learning process the machine uses previously gained human input, in order to execute its task.[3] This proces is specyfcly prevelant in the auntonomous cars industry(our 2018's case study), as this proces's benefites fitt perfectly with the car's Convolutional neural networks (CNNs).

How does it work or a deeper look[edit]

End-to-end learning can be separated into two major parts(similarly to Deep_learning). Training[4] is the first phase, in which the machine records all of the all of the parameters human operator uses in what sort of situations(accessed by Convolutional neural networks (CNNs)). Inference[5] then is possible, with the machine acting upon previously gained experience from the training phase of the End-to-end learning.

The only difference between end-to-end learning and Deep_learning processes is that the end-to-end learning must collect the parameters jointly(at the same time), while Deep_learning can collect the parameters jointly or step by step. Therefore, every end-to-end learning is Deep_learning process , but not every Deep_learning process is step by step learning.

Examples[edit]

End-to-end learning is specifically prevalent in the autonomous cars industry(our 2018's case study), as this process benefits fit perfectly with the car's Convolutional neural networks (CNNs). As the autonomous car receives multiple parameters through Convolutional neural networks (CNNs) at the same time, it is beneficial to use end-to-end learning which is able to Train or Infer upon them.

For example, the autonomous car "turns right to the compund", as there is a smaller speed limit the car needs to adjust its speed accordingly, while at the same time the car actually needs to turn as well. In this situation end-to-end learning lets the car execute the correct Inference based upon multiple receive parameters.


Pictures, diagrams[edit]

As one can see the masterfully edited picture in paint by the true paint prodigy on the right. The circled parameters are assessed jointly(at the same time), while the entire thing still remains to be Deep_learning. As the received parameters are assessed jointly within this Deep_learning, this process can be classified as end-to-end learning as well.


Training-624x291.png

External links[edit]

  • It would be helpful
  • to include many links
  • to other internet resources
  • to help fellow students
  • Please make sure the content is good
  • and don't link to a google search results, please

References[edit]