User Tools

Site Tools


cs501r_f2018:lab3

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Next revision Both sides next revision
cs501r_f2018:lab3 [2018/09/13 22:46]
carr
cs501r_f2018:lab3 [2018/09/14 17:49]
wingated
Line 13: Line 13:
 ====Deliverable:​==== ====Deliverable:​====
  
-For this lab, you will submit an ipython notebook via learningsuite.+For this lab, you will submit an ipython notebook via learningsuite.  This is where you build your first deep neural network! 
 + 
 +For this lab, we'll be combining several different concepts that we've covered during class, including new layer types, initialization strategies, and an understanding of convolutions.
  
 ---- ----
-//Part 0:/Watch and follow video tutorial+====Grading standards:​==== 
 + 
 + 
 +  * 30% Part 0: Successfully followed lab video and typed in code 
 +  * 20% Part 1: Re-implement Conv2D and CrossEntropy loss function 
 +  * 20% Part 2: Implement different initialization strategies 
 +  * 10% Part 3: Print parameters, plot train/test accuracy 
 +  * 10% Part 4: Convolution parameters quiz 
 +  * 10% Tidy and legible figures, including labeled axes where appropriate 
 + 
 +---- 
 +====Detailed specs:​==== 
 + 
 + 
 +**Part 0:** Watch and follow video tutorial
  
 **Part 1:** Re-implement a Conv2D module ​ with parameters and a CrossEntropy loss function. **Part 1:** Re-implement a Conv2D module ​ with parameters and a CrossEntropy loss function.
 +
 You will need to use  You will need to use 
      ​https://​pytorch.org/​docs/​stable/​nn.html#​torch.nn.Parameter      ​https://​pytorch.org/​docs/​stable/​nn.html#​torch.nn.Parameter
cs501r_f2018/lab3.txt · Last modified: 2021/06/30 23:42 (external edit)