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.

Filter by
Sorted by
Tagged with
36
votes
6answers
8k views

How to set the number of neurons and layers in neural networks

I am a beginner to neural networks and have had trouble grasping two concepts: How does one decide the number of middle layers a given neural network have? 1 vs. 10 or whatever. How does one decide ...
38
votes
5answers
47k views

Does gradient descent always converge to an optimum?

I am wondering whether there is any scenario in which gradient descent does not converge to a minimum. I am aware that gradient descent is not always guaranteed to converge to a global optimum. I am ...
30
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 ...
260
votes
11answers
241k views

What are deconvolutional layers?

I recently read Fully Convolutional Networks for Semantic Segmentation by Jonathan Long, Evan Shelhamer, Trevor Darrell. I don't understand what "deconvolutional layers" do / how they work. The ...
165
votes
5answers
111k views

What is the "dying ReLU" problem in neural networks?

Referring to the Stanford course notes on Convolutional Neural Networks for Visual Recognition, a paragraph says: "Unfortunately, ReLU units can be fragile during training and can "die". For ...
63
votes
5answers
39k views

Adding Features To Time Series Model LSTM

have been reading up a bit on LSTM's and their use for time series and its been interesting but difficult at the same time. One thing I have had difficulties with understanding is the approach to ...
49
votes
9answers
66k views

Why should the data be shuffled for machine learning tasks

In machine learning tasks it is common to shuffle data and normalize it. The purpose of normalization is clear (for having same range of feature values). But, after struggling a lot, I did not find ...
32
votes
2answers
42k views

Should we apply normalization to test data as well?

I am doing a project on author identification problem. I had applied the tf-idf normalization to train data and then trained a svm on that data. Now when using the classifier should I normalize test ...
64
votes
4answers
25k views

What is the difference between "equivariant to translation" and "invariant to translation"

I'm having trouble understanding the difference between equivariant to translation and invariant to translation. In the book Deep Learning. MIT Press, 2016 (I. Goodfellow, A. Courville, and Y. Bengio)...
27
votes
4answers
10k views

Role derivative of sigmoid function in neural networks

I try to understand role of derivative of sigmoid function in neural networks. First I plot sigmoid function, and derivative of all points from definition using python. What is the role of this ...
19
votes
1answer
32k views

Why ReLU is better than the other activation functions

Here the answer refers to vanishing and exploding gradients that has been in sigmoid-like activation functions but, I guess, Relu...
31
votes
2answers
29k views

Why use both validation set and test set?

Consider a neural network: For a given set of data, we divide it into training, validation and test set. Suppose we do it in the classic 60:20:20 ratio, then we prevent overfitting by validating the ...
6
votes
2answers
5k views

Does MLP always find local minimum

In linear regression we use the following cost function which is a convex function: We Use the following cost function in ...
12
votes
1answer
4k views

Using a pre trained CNN classifier and apply it on a different image dataset

How would you optimize a pre-trained neural network to apply it to a separate problem? Would you just add more layers to the pre-trained model and test it on your ...
6
votes
2answers
7k views

What are useful evaluation metrics used in machine learning

I am using CNN in order to predict codes after analyzing text. As an example, I will write "I am crazy" .. the model will predict some code " X321". All this based on CNN. I want to evaluate my ...
9
votes
2answers
1k views

Transform an Autoencoder to a Variational Autoencoder?

I would like to compare the training by an Autoencoder and a variational autoencoder. I have already run the traing using AE. I would like to know if it's possible to transform this AE into a VAE and ...
3
votes
1answer
169 views

Understanding computations of Perceptron and Multi-Layer Perceptrons on Geometric level

I am currently watching amazing Deep Learning lecture series from Carnegie Melllon University, but I am having little bit of trouble understanding how Perceptrons and MLP are making their decisions on ...
148
votes
17answers
123k views

Best python library for neural networks

I'm using Neural Networks to solve different Machine learning problems. I'm using Python and pybrain but this library is almost discontinued. Are there other good alternatives in Python?
137
votes
18answers
151k views

How do you visualize neural network architectures?

When writing a paper / making a presentation about a topic which is about neural networks, one usually visualizes the networks architecture. What are good / simple ways to visualize common ...
63
votes
6answers
126k views

Cross-entropy loss explanation

Suppose I build a neural network for classification. The last layer is a dense layer with Softmax activation. I have five different classes to classify. Suppose for a single training example, the <...
80
votes
4answers
37k views

How are 1x1 convolutions the same as a fully connected layer?

I've recently read Yan LeCuns comment on 1x1 convolutions: In Convolutional Nets, there is no such thing as "fully-connected layers". There are only convolution layers with 1x1 convolution kernels ...
78
votes
1answer
72k views

When to use (He or Glorot) normal initialization over uniform init? And what are its effects with Batch Normalization?

I knew that Residual Network (ResNet) made He normal initialization popular. In ResNet, He normal initialization is used , while the first layer uses He uniform initialization. I've looked through ...
37
votes
3answers
23k views

Why is ReLU used as an activation function?

Activation functions are used to introduce non-linearities in the linear output of the type w * x + b in a neural network. Which I am able to understand ...
20
votes
3answers
17k views

What is the relationship between the accuracy and the loss in deep learning?

I have created three different models using deep learning for multi-class classification and each model gave me a different accuracy and loss value. The results of the testing model as the following: ...
15
votes
3answers
4k views

Can a neural network compute $y = x^2$?

In spirit of the famous Tensorflow Fizz Buzz joke and XOr problem I started to think, if it's possible to design a neural network that implements $y = x^2$ function? Given some representation of a ...
31
votes
4answers
24k views

Neural Network parse string data?

So, I'm just starting to learn how a neural network can operate to recognize patterns and categorize inputs, and I've seen how an artificial neural network can parse image data and categorize the ...
8
votes
1answer
37k views

How to download dynamic files created during work on Google Colab?

I have two different files and on the first, I tried to save data to file as: np.save(open(Q1_TRAINING_DATA_FILE, 'wb'), q1_data) On second file, i'm trying to ...
7
votes
2answers
5k views

Difference between cell state and hidden state

LSTM cells consist of two types of states, the cell state and hidden state. How do cell and hidden states differ, in terms of their functionality? What information do they carry?
9
votes
2answers
8k views

Why large weights are prohibited in neural networks?

Why weights with large values cause neural networks to be overfitted, and consequently we use approaches like regularization to neutralize weights with large values?
9
votes
5answers
12k views

In which epoch should i stop the training to avoid overfitting

I'm working on an age estimation project trying to classify a given face in a predefined age range. For that purpose I'm training a deep NN using the keras library. The accuracy for the training and ...
8
votes
2answers
10k views

How to plot cost versus number of iterations in scikit learn?

One of the recommendations in the Coursera Machine Learning course when working with gradient descent based algorithms is: Debugging gradient descent. Make a plot with number of iterations on the x-...
7
votes
2answers
22k views

Keras Sequential model returns loss 'nan'

I'm implementing a neural network with Keras, but the Sequential model returns nan as loss value. I have sigmoid activation ...
2
votes
1answer
420 views

Compute backpropagation

I have the question which is mentioned in the above picture. It is trying to find the derivative of f with respect to weight matrix ...
9
votes
1answer
3k views

When does decision tree perform better than the neural network?

I was experimenting with different modelling methods including KNN, Decision Trees, Neural Networks and SVN and trying to fit my data to see which works the best. To my surprise, the decision tree ...
6
votes
1answer
5k views

Is it possible to customize the activation function in scikit-learn's MLPClassifier?

Scikit-learn lists these as the implemented activation functions for it's multi-layer perceptron classifier: ...
1
vote
2answers
993 views

Finding optimal weights for models

I'm trying to implement an algorithm to find the minimal value of a function. Before moving to sigmoid activation functions, i'm trying to understand linear regression. Usually, a gradient descent ...
2
votes
2answers
1k views

Explain Binary Classification with output 0.5 (True)

What is the interpretation of output 0.5 of a typical classifier? I made a prediction and the probability of that data point being from the True class is 0.5.
159
votes
6answers
244k views

How to draw Deep learning network architecture diagrams?

I have built my model. Now I want to draw the network architecture diagram for my research paper. Example is shown below:
94
votes
4answers
57k views

Backprop Through Max-Pooling Layers?

This is a small conceptual question that's been nagging me for a while: How can we back-propagate through a max-pooling layer in a neural network? I came across max-pooling layers while going through ...
42
votes
2answers
40k views

How to prepare/augment images for neural network?

I would like to use a neural network for image classification. I'll start with pre-trained CaffeNet and train it for my application. How should I prepare the input images? In this case, all the ...
17
votes
9answers
3k views

How Do I Learn Neural Networks?

I'm a freshman undergraduate student (mentioning this so you may forgive my unfamiliarity) who is currently doing research using neural networks. I've coded a three-node neural network (that works) ...
31
votes
1answer
32k views

RNN's with multiple features

I have a bit of self taught knowledge working with Machine Learning algorithms (the basic Random Forest and Linear Regression type stuff). I decided to branch out and begin learning RNN's with Keras. ...
26
votes
3answers
2k views

Why are NLP and Machine Learning communities interested in deep learning?

I hope you can help me, as I have some questions on this topic. I'm new in the field of deep learning, and while I did some tutorials, I can't relate or distinguish concepts from one another.
23
votes
5answers
62k views

Validation loss is not decreasing

I am trying to train a LSTM model. Is this model suffering from overfitting? Here is train and validation loss graph:
37
votes
1answer
54k views

How does Keras calculate accuracy?

How does Keras calculate accuracy from the classwise probabilities? Say, for example we have 100 samples in the test set which can belong to one of two classes. We also have a list of the classwise ...
14
votes
3answers
10k views

Is there a thumb-rule for designing neural-networks?

I know that a neural-network architecture is mostly based on the problem itself and the types of input/output, but still - there's always a "square one" when starting to build one. So my question is - ...
22
votes
2answers
13k views

Is there away to change the metric used by the Early Stopping callback in Keras?

When using the early stopping callback in Keras, training stops when some metric (usually validation loss) is not increasing. Is there a way to use another metric (like precision, recall, or f-measure)...
17
votes
2answers
6k views

Why do activation functions have to be monotonic?

I am currently preparing for an exam on neural networks. In several protocols from former exams I read that the activation functions of neurons (in multilayer perceptrons) have to be monotonic. I ...
14
votes
1answer
5k views

Back-propagation through max pooling layers

I have a small sub-question to this question. I understand that when back-propagating through a max pooling layer the gradient is routed back in a way that the neuron in the previous layer which was ...
13
votes
2answers
30k views

How to normalize data for Neural Network and Decision Forest

I have a data set with 20000 samples, each has 12 different features. Each sample is either in category 0 or 1. I want to train a neural network and a decision forest to categorize the samples so that ...

1
2 3 4 5