Linked Questions

1
vote
0answers
50 views

Interpretation of a deep neural network [duplicate]

I am an economist so my academic career has been spent on interpreting beta hat rather than optimising y hat. But I've become quite fascinated by neural networks so I wanted to get some things ...
2
votes
0answers
17 views

Is it possible to define what the last hidden layer represents in a neural net? [duplicate]

I am trying to determine how to set up a neural net to use in a recommendation engine I am building to recommend a cheese to the user. I have a clear understanding of what the output layer represents (...
10
votes
3answers
4k views

What is the "credit assignment" problem in Machine Learning and Deep Learning?

I was watching a very interesting video with Yoshua Bengio where he is brainstorming with his students. In this video they seem to make a distinction between "credit assignment" vs gradient descent vs ...
12
votes
3answers
371 views

How does one ensure Machine Learning doesn't come to correct classifications via the wrong ways?

I got good results on a radiation exposure prediction problem using SVM and DT where the ultimate goal is to predict the radiation dose an individual was exposed to using data about individual related ...
2
votes
3answers
1k views

What is a "shallow" layer and a "deep" layer of a neural network?

What does shallow, deep, shallower, deeper, mean in the context of neural network layers? For context:
3
votes
1answer
2k views

Interpreting neural network weights

I created a neural network model for a classification task based on 14 variables, 1 hidden layer of size 8. Outputs give 3 possible classes. The weights I got from input (left) and output (right) ...
0
votes
1answer
350 views

Can we say that last but one layer (that is fully connected layer) in CNN architectures is 'compressed' version of input image?

In CNN architectures, can we say that the layer before the last softmax layer is compressed version of input image?
2
votes
2answers
87 views

Do earlier hidden layers learn more concepts/features than later ones, in neural networks?

I am wondering whether there is a general statement of the sort "earlier layers in neural networks learn more concepts/features than later layers" or the other way around. The output layer not being ...
1
vote
1answer
132 views

How multi layer neural network classify data without extracting features?

In CNN we have convolution layer and pooling layer for feature extraction. How the features are extracted in Fully connected neural network? Secondly CNN has more expressive power and and number of ...
1
vote
1answer
130 views

About the FC layer in a CNN

So we know that the major disadvantage of pushing images through an ANN is due to the loss of information, particularly spatial information. But in regards to CNNs, in the last layer of the ...
0
votes
1answer
87 views

Machine Learning alternative for hashing [closed]

Is there a Machine Learning technique that can used to detect the slightest change in data? I know this can be done using a hash but I was just wondering if there is any machine learning technique out ...