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
3 votes
2 answers
7k views

How does strided deconvolution works?

I am trying to understand how the shape of the image changes after deconvolution ? I am trying to understand the example code of convolutional autoencoder from neon. ...
user avatar
  • 131
5 votes
1 answer
3k views

Deconvolutional Network in Semantic Segmentation

I recently came across a paper about doing semantic segmentation using deconvolutional network: Learning Deconvolution Network for Semantic Segmentation. The basic structure of the network is like ...
user avatar
  • 63
17 votes
3 answers
13k views

Bagging vs Dropout in Deep Neural Networks

Bagging is the generation of multiple predictors that works as ensamble as a single predictor. Dropout is a technique that teach to a neural networks to average all possible subnetworks. Looking at ...
user avatar
  • 415
1 vote
1 answer
319 views

Understanding convolutional pooling sizes (deep learning)

I'm dumb but still trying to understand the code provided from this e-book on deep learning, but it doesn't explain where the n_in=40*4*4 comes from. ...
user avatar
  • 267
10 votes
1 answer
784 views

Transforming AutoEncoders

I've just read Geoff Hinton's paper on transforming autoencoders Hinton, Krizhevsky and Wang: Transforming Auto-encoders. In Artificial Neural Networks and Machine Learning, 2011. and would quite ...
user avatar
9 votes
1 answer
5k views

Understanding dropout and gradient descent

I am looking at how to implement dropout on deep neural networks and found something counter intuitive. In the forward phase dropout mask activations with a random tensor of 1s and 0s to force net to ...
user avatar
  • 415
9 votes
5 answers
1k views

Any idea about application of deep dream?

Recently Google publicized interesting deep dream. Besides art generation such as http://deepdreamgenerator.com/, do you see any potential applications of deep dream in computer vision or machine ...
user avatar
7 votes
2 answers
6k views

How word2vec can handle unseen / new words to bypass this for new classifications?

In simple terms, if my classification is based on word2vec as features, what I am supposed to do, if a new word comes, which does not have a word2vec? I am trying to used word2vec or word vectors for ...
user avatar
  • 71
5 votes
3 answers
7k views

Do I need to buy a NVIDIA graphic card to run deep learning algorithm?

I am new in deep learning. I am running a MacBook Pro yosemite (upgraded from Snowleopard). I don't have a CUDA-enabled card GPU, and running the code on the CPU is extremely slow. I heard that I can ...
user avatar
  • 153
1 vote
0 answers
162 views

"Recursive ConvNets for Dummies" Library [closed]

I've look at the questions on here regarding the different python libraries around for deep learning and neural nets. They include: Keras Caffe Lasagne PyLearn2 Deepy Theano Torch My understanding ...
user avatar
2 votes
0 answers
548 views

Fisher's Iris data set with Caffe

I am trying to use Caffe on the usual Fisher's Iris data set (150 flowers, each having 4 features, and split into 3 classes): if a flower belong to class 1 (setosa), the network output should be [1, ...
user avatar
5 votes
1 answer
2k views

How to do multitask learning using Caffe?

I wonder how to do multitask learning using Caffe. Should I simply use the output layer SigmoidCrossEntropyLoss or EuclideanLoss, and define more than one outputs? E.g. is the following architecture ...
user avatar
5 votes
2 answers
946 views

Can theano work on mapreduce or on spark?

I am not sure whether the Theano library can be used to write parallelized code in map reduce or in spark. Any expert opinion is welcome. A discussion was on at: Theano-dev
user avatar
  • 571
2 votes
0 answers
1k views

Caffe net.predict() outputs random results (GoogleNet)

I used pretrained GoogleNet from https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet and finetuned it with my own data (~ 100k images, 101 classes). After one day training I achieved 62% ...
user avatar
  • 31
-1 votes
2 answers
496 views

How can an undergraduate learn more about deep learning? [duplicate]

I am an undergraduate who needs to submit a thesis for graduation. I am fairly interested in deep learning, and am working on a project that uses deep learning methods extensively (rCNNs to be precise)...
user avatar
  • 1
10 votes
1 answer
4k views

How do I calculate the delta term of a Convolutional Layer, given the delta terms and weights of the previous Convolutional Layer?

I am trying to train an artificial neural network with two convolutional layers (c1, c2) and two hidden layers (c1, c2). I am using the standard backpropagation approach. In the backward pass I ...
user avatar
  • 181
9 votes
1 answer
442 views

Theano in deep learning research

How widely is Theano used in deep learning research? Is Theano a good start to learn the implementation of machine learning algorithms? Will learning the implementation of something like a feed ...
user avatar
6 votes
2 answers
4k views

Convolutional neural network for sparse one-hot representation

I have some basic features which I encoded in a one-hot vector. Length of the feature vector equals to 400. It is sparse. I saw that conv nets is applied to a dense feature vectors. Is there any ...
user avatar
  • 163
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
1 vote
0 answers
86 views

Prove Reccurrent Neural Network can exhibit oscillatory behavior

I understand how recurrent neural networks work, however I'm trying to build a deep intuitive understanding of their behavior which is difficult for me because they exhibit such complex behaviors. ...
user avatar
0 votes
1 answer
501 views

Identity covariance matrix, decorrelated data?

Why would you want to decorrelated data? As I am reading about PCA and whitening on image data for DNN, I wonder what is the purpose of achieving the identity covariance matrix in your data is? Is ...
user avatar
2 votes
0 answers
194 views

Which one is easier to debug between theano and caffe? [closed]

I am investigating whether to use theano or caffe for convnets. I would like to know which one provides a better debug environment. In caffe, it seems you don't write any code just a config in ...
user avatar
  • 121
3 votes
1 answer
106 views

What are the possible ways to handle class unbalance in a large scale image recognition problem with Deep Neural Nets?

I have 22 classes of objects but they have very skewed distributions where max class has 100.000 images and the min class has 1600 images. In that setting I would like to hear some possible solutions ...
user avatar
  • 181
5 votes
1 answer
326 views

Route to picking up Deep learning [closed]

I would like to pick up on the topic of deep learning. Should I begin from the topic of AI before working my way into Deep learning?
user avatar
  • 51
10 votes
3 answers
7k views

What cost function and penalty are suitable for imbalanced datasets?

For an imbalanced data set, is it better to choose an L1 or L2 regularization? Is there a cost function more suitable for imbalanced datasets to improve the model score (...
user avatar
  • 101
14 votes
2 answers
4k views

Visualizing deep neural network training

I'm trying to find an equivalent of Hinton Diagrams for multilayer networks to plot the weights during training. The trained network is somewhat similar to a Deep SRN, i.e. it has a high number of ...
user avatar
  • 283
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
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
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
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
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

1
88 89 90 91
92