Difference between revisions of "End-to-end learning"

From Computer Science Wiki
Jump to navigation Jump to search
Line 1: Line 1:
<center>
<center>
<blockquote style="padding: 5px; background-color: #FFF8DC; border: solid thin gray;">
<blockquote style="padding: 5px; background-color: #FFF8DC; border: solid thin gray;">
   [[File:Exclamation.png]] This is student work which has not yet been approved as correct by the instructor '''WIP'''
   [[File: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
</blockquote>
</blockquote>
</center>
</center>

Revision as of 02:34, 13 July 2017

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 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, in end-to-end learning machine uses previously gained human input, in order to execute its task accordingly.[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(symilarly to Deep_learning). Training[4] is the first phase, in which the machine records all of the all of the paramiters human operator uses in what sort of situations(essesed by Convolutional neural networks (CNNs)).[5] Inference[6] then is possyble, with the mashine acting upon previously gained experiance from the traning phase of the End-to-end learning.

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

Examples[edit]

End-to-end learning 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). As the autonomous car recives multyple paramiters through Convolutional neural networks (CNNs) at the same time, it is benefitial 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 asjust its speed aacordingly, while at the same time the cur actually needs to turn as well. In this sytuation end-to-end learning lets the car execute the correct Inference based upon multiple recived parameters.


Pictures, diagrams[edit]

As one can see the masterfully edyted picture in paint by the true paint protogy on the right. The cyrcled parameters are assesed jointly(at the same time), while the entire thing still remains to be Deep_learning. As the recived parameters are essesd jointly within this Deep_learning, this procces can be classyfied 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]