Questions tagged [deep-learning]

a new area of Machine Learning research concerned with the technologies used for learning hierarchical representations of data, mainly done with deep neural networks (i.e. networks with two or more hidden layers), but also with some sort of Probabilistic Graphical Models.

Filter by
Sorted by
Tagged with
248 votes
10 answers
361k views

How to set class weights for imbalanced classes in Keras?

I know that there is a possibility in Keras with the class_weights parameter dictionary at fitting, but I couldn't find any example. Would somebody so kind to ...
user avatar
  • 7,947
180 votes
5 answers
127k 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 ...
user avatar
  • 3,815
178 votes
6 answers
291k 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:
user avatar
  • 2,277
170 votes
6 answers
163k views

When to use GRU over LSTM?

The key difference between a GRU and an LSTM is that a GRU has two gates (reset and update gates) whereas an LSTM has three gates (namely input, output and forget gates). Why do we make use of GRU ...
user avatar
155 votes
19 answers
185k 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 ...
user avatar
  • 17.6k
112 votes
10 answers
116k views

Choosing a learning rate

I'm currently working on implementing Stochastic Gradient Descent, SGD, for neural nets using back-propagation, and while I understand its purpose I have some ...
user avatar
  • 1,804
85 votes
7 answers
60k views

Time series prediction using ARIMA vs LSTM

The problem that I am dealing with is predicting time series values. I am looking at one time series at a time and based on for example 15% of the input data, I would like to predict its future values....
user avatar
  • 1,065
81 votes
1 answer
79k 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 ...
user avatar
72 votes
4 answers
34k 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)...
user avatar
  • 883
69 votes
6 answers
138k 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 <...
user avatar
  • 2,921
69 votes
5 answers
121k views

What is the difference between Gradient Descent and Stochastic Gradient Descent?

What is the difference between Gradient Descent and Stochastic Gradient Descent? I am not very familiar with these, can you describe the difference with a short example?
user avatar
  • 979
66 votes
5 answers
44k 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 ...
user avatar
  • 1,145
64 votes
4 answers
69k views

Why mini batch size is better than one single "batch" with all training data?

I often read that in case of Deep Learning models the usual practice is to apply mini batches (generally a small one, 32/64) over several training epochs. I cannot really fathom the reason behind this....
user avatar
  • 7,947
59 votes
4 answers
75k views

Does batch_size in Keras have any effects in results' quality?

I am about to train a big LSTM network with 2-3 million articles and am struggling with Memory Errors (I use AWS EC2 g2x2large). I found out that one solution is to reduce the ...
user avatar
  • 1,110
59 votes
5 answers
24k views

In softmax classifier, why use exp function to do normalization?

Why use softmax as opposed to standard normalization? In the comment area of the top answer of this question, @Kilian Batzner raised 2 questions which also confuse me a lot. It seems no one gives an ...
user avatar
  • 693
58 votes
10 answers
81k 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 ...
user avatar
  • 13.4k
57 votes
5 answers
69k views

Number of parameters in an LSTM model

How many parameters does a single stacked LSTM have? The number of parameters imposes a lower bound on the number of training examples required and also influences the training time. Hence knowing the ...
user avatar
  • 1,237
57 votes
3 answers
25k views

How to fight underfitting in a deep neural net

When I started with artificial neural networks (NN) I thought I'd have to fight overfitting as the main problem. But in practice I can't even get my NN to pass the 20% error rate barrier. I can't even ...
user avatar
  • 693
53 votes
5 answers
152k views

How to get accuracy, F1, precision and recall, for a keras model?

I want to compute the precision, recall and F1-score for my binary KerasClassifier model, but don't find any solution. Here's my actual code: ...
user avatar
  • 897
48 votes
7 answers
38k views

Deep Learning vs gradient boosting: When to use what?

I have a big data problem with a large dataset (take for example 50 million rows and 200 columns). The dataset consists of about 100 numerical columns and 100 categorical columns and a response column ...
user avatar
  • 1,575
44 votes
3 answers
95k views

What is Ground Truth

In the context of Machine Learning, I have seen the term Ground Truth used a lot. I have searched a lot and found the following definition in Wikipedia: In machine learning, the term "ground ...
user avatar
  • 13.4k
43 votes
2 answers
69k views

Merging two different models in Keras

I am trying to merge two Keras models into a single model and I am unable to accomplish this. For example in the attached Figure, I would like to fetch the middle layer $A2$ of dimension 8, and use ...
user avatar
  • 973
42 votes
13 answers
25k views

Data science related funny quotes [closed]

It has been customary for the users of different communities to quote funny things about their fields. It may be fun to share your funny things about Machine Learning, Deep Learning, Data Science and ...
42 votes
5 answers
57k 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 ...
user avatar
  • 523
42 votes
5 answers
36k views

Intuitive explanation of Noise Contrastive Estimation (NCE) loss?

I read about NCE (a form of candidate sampling) from these two sources: Tensorflow writeup Original Paper Can someone help me with the following: A simple explanation of how NCE works (I found the ...
user avatar
  • 3,815
41 votes
4 answers
27k 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 ...
user avatar
41 votes
4 answers
56k views

Multi GPU in Keras

How we can program in the Keras library (or TensorFlow) to partition training on multiple GPUs? Let's say that you are in an Amazon ec2 instance that has 8 GPUs and you would like to use all of them ...
user avatar
39 votes
6 answers
49k views

Are there free cloud services to train machine learning models?

I want to train a deep model with a large amount of training data, but my desktop does not have that power to train such a deep model with these abundant data. I'd like to know whether there are any ...
user avatar
  • 13.4k
39 votes
3 answers
47k views

Choosing between CPU and GPU for training a neural network

I've seen discussions about the 'overhead' of a GPU, and that for 'small' networks, it may actually be faster to train on a CPU (or network of CPUs) than a GPU. What is meant by 'small'? For ...
user avatar
38 votes
6 answers
9k 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 ...
user avatar
  • 543
37 votes
2 answers
53k views

Should we apply normalization to test data as well?

I am doing a project on an author identification problem. I applied the tf-idf normalization to train data and then trained an SVM on that data. Now when using the classifier, should I normalize test ...
user avatar
37 votes
1 answer
56k 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 ...
user avatar
  • 1,002
37 votes
4 answers
20k views

Early stopping on validation loss or on accuracy?

I am currently training a neural network and I cannot decide which to use to implement my Early Stopping criteria: validation loss or a metrics like accuracy/f1score/auc/whatever calculated on the ...
user avatar
  • 1,024
35 votes
3 answers
28k views

What does Logits in machine learning mean?

"One common mistake that I would make is adding a non-linearity to my logits output." What does the term "logit" means here or what does it represent ?
user avatar
  • 857
35 votes
1 answer
13k views

Paper: What's the difference between Layer Normalization, Recurrent Batch Normalization (2016), and Batch Normalized RNN (2015)?

So, recently there's a Layer Normalization paper. There's also an implementation of it on Keras. But I remember there are papers titled Recurrent Batch Normalization (Cooijmans, 2016) and Batch ...
user avatar
35 votes
2 answers
82k views

Keras difference beetween val_loss and loss during training

What is the difference between val_loss and loss during training in Keras? E.g. ...
user avatar
33 votes
6 answers
14k 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 ...
user avatar
32 votes
1 answer
12k views

Time Series prediction using LSTMs: Importance of making time series stationary

In this link on Stationarity and differencing, it has been mentioned that models like ARIMA require a stationarized time series for forecasting as it's statistical properties like mean, variance, ...
user avatar
31 votes
2 answers
35k views

Are there any rules for choosing the size of a mini-batch?

When training neural networks, one hyperparameter is the size of a minibatch. Common choices are 32, 64, and 128 elements per mini batch. Are there any rules/guidelines on how big a mini-batch should ...
user avatar
  • 17.6k
30 votes
4 answers
30k 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: ...
user avatar
  • 1,765
29 votes
7 answers
16k views

Can machine learning learn a function like finding maximum from a list?

I have an input which is a list and the output is the maximum of the elements of the input-list. Can machine learning learn such a function which always selects the maximum of the input-elements ...
user avatar
  • 299
29 votes
4 answers
54k views

How to use LeakyRelu as activation function in sequence DNN in keras?When it perfoms better than Relu?

How do you use LeakyRelu as an activation function in sequence DNN in keras? If I want to write something similar to: ...
user avatar
  • 1,586
28 votes
6 answers
10k views

Deep learning basics

I am looking for a paper detailing the very basics of deep learning. Ideally like the Andrew Ng course for deep learning. Do you know where I can find this ?
user avatar
  • 423
28 votes
2 answers
27k views

What is the difference between fit() and fit_generator() in Keras?

What is the difference between fit() and fit_generator() in Keras? When should I use fit() ...
user avatar
  • 1,765
27 votes
3 answers
52k views

What is weight and bias in deep learning?

I'm starting to learn Machine learning from Tensorflow website. I have developed a very very rudimentary understanding of the flow a deep learning program follows (this method makes me learn fast ...
user avatar
27 votes
3 answers
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.
user avatar
27 votes
2 answers
12k views

Keras vs. tf.keras

I'm a bit confused in choosing between Keras (keras-team/keras) and tf.keras (tensorflow/tensorflow/python/keras/) for my new research project. There is a debate that Keras isn't owned by anyone, so ...
user avatar
  • 1,175
26 votes
2 answers
16k 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)...
user avatar
  • 373
26 votes
1 answer
10k views

PyTorch vs. Tensorflow Fold

Both PyTorch and Tensorflow Fold are deep learning frameworks meant to deal with situations where the input data has non-uniform length or dimensions (that is, situations where dynamic graphs are ...
user avatar
  • 16k
25 votes
3 answers
26k views

Why convolutions always use odd-numbers as filter size

If we have a look to 90-99% of the papers published using a CNN (ConvNet). The vast majority of them use filter size of odd numbers:{1, 3, 5, 7} for the most used. This situation can lead to some ...
user avatar

1
2 3 4 5
92