Questions tagged [neural-network]
Artificial neural networks (ANN), are composed of 'neurons' - programming constructs that mimic the properties of biological neurons. A set of weighted connections between the neurons allows information to propagate through the network to solve artificial intelligence problems without the network designer having had a model of a real system.
4,383
questions
0
votes
0
answers
9
views
Overfitting - Imbalance Classification using Deep-feed forward network
I have an unbalanced dataset, so I used SMOTEENN on the training set to resample, after training DFF,i could see the model is overfitting, could someone help me solve this?
Thank You.
...
1
vote
1
answer
34
views
Unordered Set Classification Problem
In my setup I have one feature which is a sparse list representing categories. For example, let's say that we have M categories in the interval ...
- 111
2
votes
1
answer
169
views
AutoDiff on different operations?
How it is possible to use automative differentiation (computational graph) on operations like - convolution?
I know that 2d convolution can be represented by matrix multiplication. But what about 3d ...
- 43
0
votes
0
answers
9
views
Patterns in weights of trained model?
Apologies for a naive question. Let's say I am training a simple feed-forward neural network using stochastic gradient descent with a fixed architecture, learning rate, number of training epochs, and ...
- 101
3
votes
1
answer
808
views
How does a Neural Net handle an unseen class for a Categorical Feature?
Let's say I train a Neural Net, and I have a Categorical Feature X.
During training, there are only 3 classes seen in feature X; A, B, C.
Now, let's say I want to make predictions from this trained ...
- 139
2
votes
0
answers
62
views
Transfer learning for tabular data
I wonder if transfer learning can be used in tabular data similarly to how it's used in neural networks for image recognition. My idea would be to train a "general" model and then "...
- 135
0
votes
0
answers
41
views
Tensorflow SegNet architecture
I was unable to find a complete description of the SegNet architecture for image segmentation (specifically, the decoder layers). Therefore, I would like to clarify the correctness of my ...
- 51
0
votes
0
answers
22
views
Losing Information while resizing the image in Segmentation task using U-net
I'm using U-net architecture to build a segmentation task of image. During training I have image of size 256256 image. It works very well on the segmentation of same size 256256 or near to size 256*...
0
votes
0
answers
23
views
Question about the limitations of regularization
I am training a neural network which is overfitting. Even when I increase the number of parameters, the test lost plateaus while the training loss keeps decreasing. Can regularization (like an L1 or ...
0
votes
0
answers
13
views
How to build a model where each data point has different levels of information?
Let’s say I want to predict the weight of a person given information about them; height & sex.
Now, let’s say that that I have additional information about roughly 50% of the individuals included ...
- 139
1
vote
0
answers
33
views
When can we claim that the training converged?
I've been working for a while in a binary classification problem with different types of neural networks. In this particular case, I'm using an 3-layer MLP with hyperbolic tangent activation in input ...
- 51
0
votes
0
answers
8
views
Resources for writing CNN for semantic segmentation
I am intermediate/advanced in Python and new to machine learning. Most of what I know about deep learning I learned through Deep Learning with Python by François Chollet. I am trying to do image ...
0
votes
0
answers
12
views
How can I combine/pool of the results of regression with neural network?
My study has ten imputed dependent variables (plausible values). After separately analyzing each dependent variable using a regression neural network (NN), I must combine/pool the results. I tried ...
- 1
0
votes
0
answers
15
views
graph signal in GNN
I am reading several materials about graph signal processing for a thesis on Graph Neural Network and i see that a graph signal is defined as a vector so each node signal is a scalar. In practice, a ...
- 101
0
votes
0
answers
18
views
Loss increase while accuracy also increase [duplicate]
I'm training a fairly large classification model,and I'm having the below results.
...
- 13