Linked Questions

33
votes
6answers
13k views

Why do convolutional neural networks work?

I have often heard people saying that why convolutional neural networks are still poorly understood. Is it known why convolutional neural networks always end up learning increasingly sophisticated ...
9
votes
2answers
172 views

Is there any consensus on choosing an appropriate ML approach?

I am studying data science at the moment and we are taught a dizzying variety of basic regression/classification techniques (linear, logistic, trees, splines, ANN, SVM, MARS, and so on....), along ...
8
votes
1answer
16k views

Why should softmax be used in CNN

In the last layer of CNNs and MLPs it is common to use softmax layer or units with sigmoid activation functions for multi-class ...
5
votes
3answers
4k views

Neural Network Performs Bad On MNIST

I've been struggling with Neural Networks for a while now. I get the math behind backpropagation. Still as reference I'm using the formulas from here. The Network learns XOR: Prediction After ...
5
votes
1answer
372 views

Fully connected layer in deep learning

How to determine the best number of the fully connected layers in CNN? Can I use only one fully connected layer in CNN? How to determine the dimension of the fully ...
4
votes
2answers
3k views

Depth of a Neural network

I was self-teaching myself. I totally understand why depth of a neural network affects the learning and how it differs than its width. But I am looking for some theoretical justification about it. ...
4
votes
1answer
132 views

Is it a red flag that increasing the number of parameters makes the model less able to overfit small amounts of data?

I'm training a deep network (CNN-LSTM-CRF) for Named Entity Recognition. Is there a reason that increasing the number of parameters would make the network less able to overfit a small training set (~...
4
votes
0answers
80 views

Learning a logical function with a 2 layer BDN network - manual weight setting rule question?

So I am trying to construct a 2-layer network of binary decision neurons as proposed by McCullough and Pitts (1943) to learn a logical function (a composition of AND's and OR's) such as: $((\neg x_1\...
2
votes
3answers
387 views

How each layer of a neural net is responsible for one feature

Through my study of neural networks, I came across the idea that each layer of a neural network is responsible for recognizing one feature of the input data. For example, if we build a neural network ...
2
votes
2answers
166 views

Neural Network Hidden Layer Selection

I am trying to build an MLP classifier model on a dataset containing 30000 samples and 23 features. What are the standards I need to consider while selecting the ...
2
votes
1answer
192 views

How to implement keras LSTM time series [closed]

I am learning how to implement Keras LSTM on a simple time series data. The dataset I'm using has $12$ columns and $300k$ rows. Each group of $200$ rows represents ...
2
votes
1answer
168 views

Minimum Neurons in Neural Network

I use a brute-force mechanism to determine optimal hidden layers/neurons by incrementing the layers/neurons by 1 up to some maximums and then picking the optimal counts from the best performing model. ...
2
votes
3answers
545 views

Neural Network beginner level tutorial

I am trying to build a simple multi layer perceptron Neural Network in Java, but apparently my calculations are off. I am looking for a beginner-level tutorial which can help me to understand how to ...
2
votes
1answer
2k views

Choosing layer hyper-parameters of a CNN

Context: I'm building a CNN on MATLAB to classify wallpaper groups. I'm using the following network type. CONV -> ReLU -> POOL -> CONV -> ReLU -> POOL -> FC -> ...
2
votes
2answers
456 views

Should the different layers of deep learning models have same size or they should be changed based on a rule

I see a lot of people varying the width of each layer in a deep neural network. ie. Input->50->100->150->Output. I'm curious what, if any, are the advantages of this structure over static layer widths ...

15 30 50 per page