Linked Questions

2
votes
0answers
76 views

Maximum Layers in "any" Neural Network [duplicate]

I have about 6 months of experience in building and using Neural Networks with no prior/formal training. As I explore this field further, I see a lot of discussions about determining how many layers/...
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 ...
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 ...
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 ...
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. ...
1
vote
3answers
1k views

More layers in NN give worse result

So I was working on a classification task with the help of a NN. The data-set was normalised, weights random between 0-1, and all the activations were sigmoid ...
9
votes
2answers
168 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 ...
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 -> ...
5
votes
1answer
366 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 ...
2
votes
3answers
363 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 ...
0
votes
1answer
433 views

Properly using activation functions of neural network

I'm trying to understand the hidden layers of neural networks. Input layer section covers the steps that I use before passing information to hidden layer where concerns appear. Input Layer: From my ...
2
votes
3answers
539 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 ...
1
vote
2answers
850 views

How to obtain with a recurrent neural network the Xor function using keras? [closed]

I'm trying to implement a model of recurrent neural network to solve the XOR problem, but I am not still able to do that. Any hints?
1
vote
1answer
733 views

Predict method of the perceptron algorithm

Can someone explain to me how the predict method of the perceptron algorithm works? ...
2
votes
2answers
416 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 ...
2
votes
2answers
164 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 ...
1
vote
2answers
237 views

How does "linear algebraic" weight training function work?

This answer shows that linear and polynomial function weights can be trained using this matrix operation: $w = (X^TX)^{-1}X^Ty$ Therefore, algorithms such as gradient descent are not necessary for ...
2
votes
1answer
191 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 ...
4
votes
1answer
130 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 (~...
2
votes
1answer
161 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. ...
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\...
1
vote
1answer
80 views

Handle Unbalanced data [closed]

I have a data-set with 2 target classes. In training dataset, the ratio of the 2 classes are 1:93 With my neural network, the current accuracy is 63%. I tried undersampling, oversampling, equal ...
1
vote
0answers
59 views

Retraining Neural Network with Optimal Number of Layers/Neurons

So let's say you have determined the optimal number of layers/neurons for your neural network. When it comes time to re-train your network with new data values (the inputs are the same, just newer ...
1
vote
1answer
23 views

What is the structure of a MLP that allows for arbitrary decision boundaries? [closed]

I'm just doing some reacher for my machine learning class, I found out it must be three layers MLP. But why? Is there a proof/paper or I'm wrong?