Trjtdtk

Denied boarding although I have proper visa and documentation. To whom should I make a complaint?

Fundamental Solution of the Pell Equation

How to write this math term? with cases it isn't working

AppleTVs create a chatty alternate WiFi network

Disembodied hand growing fangs

How to compare two different files line by line in unix?

How to Make a Beautiful Stacked 3D Plot

How come Sam didn't become Lord of Horn Hill?

Chinese Seal on silk painting - what does it mean?

How to convince students of the implication truth values?

Most bit efficient text communication method?

What are the out-of-universe reasons for the references to Toby Maguire-era Spider-Man in Into the Spider-Verse?

Is it ethical to give a final exam after the professor has quit before teaching the remaining chapters of the course?

Sum letters are not two different

What is GELU activation?

What is the appropriate index architecture when forced to implement IsDeleted (soft deletes)?

How does the math work when buying airline miles?

What is the effect of altitude on true airspeed?

Physics no longer uses mechanical models to describe phenomena

Does the Weapon Master feat grant you a fighting style?

How could we fake a moon landing now?

What's the meaning of "fortified infraction restraint"?

Is grep documentation about ignoring case wrong, since it doesn't ignore case in filenames?

Should I use a zero-interest credit card for a large one-time purchase?

Backprogagation

0

$begingroup$

I am new to Deep Learning. Suppose that we have a neural network with one input layer, one output layer, and one hidden layer. Let's refer to the weights from input to hidden as w and the weights from hidden to output as v. Suppose that we have initialized w and v, and ran them through the neural network via the Feedforward algorithm. Suppose that we have calculated v via backprogagation. When estimating the ideal weights for w, do we keep the weights v constant when updating w via gradient descent given we already calculated v, or do we allow v to update along with w?

I understand that both w and v should update simultaneously when updating v, that's not my question. My question is related to if we need to update v when updating w, given we already calculated v.

neural-network deep-learning backpropagation

share|improve this question

asked Apr 3 at 2:27

Joshua JonesJoshua Jones

1

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  During backpropogation, we first need to calculate the change in v. Then, with the help of v we will calculate the change in w.
  $endgroup$
  – Shubham Panchal
  Apr 3 at 2:53
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  So, in the code, which I am trying to do from scratch, we do not include v in the for loop that will be used for gradient descent to find w, yes? We simply use the same v for every iteration of gradient descent, right?
  $endgroup$
  – Joshua Jones
  Apr 3 at 4:58
  

  
  
  
  

add a comment | 

0

$begingroup$

I am new to Deep Learning. Suppose that we have a neural network with one input layer, one output layer, and one hidden layer. Let's refer to the weights from input to hidden as w and the weights from hidden to output as v. Suppose that we have initialized w and v, and ran them through the neural network via the Feedforward algorithm. Suppose that we have calculated v via backprogagation. When estimating the ideal weights for w, do we keep the weights v constant when updating w via gradient descent given we already calculated v, or do we allow v to update along with w?

I understand that both w and v should update simultaneously when updating v, that's not my question. My question is related to if we need to update v when updating w, given we already calculated v.

neural-network deep-learning backpropagation

share|improve this question

asked Apr 3 at 2:27

Joshua JonesJoshua Jones

1

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  During backpropogation, we first need to calculate the change in v. Then, with the help of v we will calculate the change in w.
  $endgroup$
  – Shubham Panchal
  Apr 3 at 2:53
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  So, in the code, which I am trying to do from scratch, we do not include v in the for loop that will be used for gradient descent to find w, yes? We simply use the same v for every iteration of gradient descent, right?
  $endgroup$
  – Joshua Jones
  Apr 3 at 4:58
  

  
  
  
  

add a comment | 

$begingroup$

I am new to Deep Learning. Suppose that we have a neural network with one input layer, one output layer, and one hidden layer. Let's refer to the weights from input to hidden as w and the weights from hidden to output as v. Suppose that we have initialized w and v, and ran them through the neural network via the Feedforward algorithm. Suppose that we have calculated v via backprogagation. When estimating the ideal weights for w, do we keep the weights v constant when updating w via gradient descent given we already calculated v, or do we allow v to update along with w?

I understand that both w and v should update simultaneously when updating v, that's not my question. My question is related to if we need to update v when updating w, given we already calculated v.

neural-network deep-learning backpropagation

share|improve this question

asked Apr 3 at 2:27

Joshua JonesJoshua Jones

1

$endgroup$

share|improve this question

asked Apr 3 at 2:27

Joshua JonesJoshua Jones

1

share|improve this question

asked Apr 3 at 2:27

Joshua JonesJoshua Jones

1

asked Apr 3 at 2:27

Joshua JonesJoshua Jones

1

asked Apr 3 at 2:27

Joshua JonesJoshua Jones

1