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.
4,843
questions
1
vote
1
answer
140
views
which application domains are not well suited to deep learning?
Deep learning seems to be the new cool thing in AI/machine learning and it works well in many domains, but I want to know- what are the specific application areas where deep learning is not the best ...
- 4,139
0
votes
1
answer
278
views
Deep learning - rule generation
I wanted to know if there is any methodology in Deep/Machine learning, where given a set of input/output values, it can derive rules for the same.
Lets say I generate training input and output by $y=...
- 28.6k
9
votes
1
answer
4k
views
How to approach the numer.ai competition with anonymous scaled numerical predictors?
Numer.ai has been around for a while now and there seem to be only few posts or other discussions about it on the web.
The system has changed from time to time and the set-up today is the following:
...
- 36
2
votes
1
answer
64
views
Two ways of optimize the same function?
I'm actually reading this tutorial about deepLearning and in particular about Logistic Regression.
I don't get why it first says to optimize logistic regression taking the max Probability and after ...
- 8,256
6
votes
1
answer
1k
views
Approaches for implementing Domain specific Question answering System
Given several wikipedia articles on different movies.
What are the different approaches to implement a QA system to answer different quires related to movies.
...
5
votes
2
answers
174
views
Deep neural net modelling strategy
are there any resources out there (book, blog, your own answer post etc.) that gives advise on modelling strategy of deep neural net?
I know how to fit a neural net, I know how to change settings ...
- 19
3
votes
1
answer
630
views
Deep Learning for Time series
Deep Learning is an excellent model for classification problem such as image recognition or object detection. Can we use deep learning for regression problems - Time Series prediction ? So if it can, ...
- 28.6k
8
votes
1
answer
2k
views
Using Neural Networks to extract multiple parameters from images
I want to extract parameters from an image using a neural network.
Example:
Given an image of a brick wall the NN should extract the width and height of the bricks, the color and the roughness.
I ...
- 28.6k
2
votes
0
answers
551
views
Why is this trained model misclassifying new cases?
Below is text / code from a recent SO post of mine that I hope you could comment on:
Using Keras/Theano, I successfully trained a model using the Keras sample code for CIFAR10. It ran for about 2 ...
CommunityBot
- 1
5
votes
1
answer
4k
views
Google TPU: when/how will it be available to me?
Google recently announced the TPU custom chip.
They stated it is available in Google Cloud Platform, but only for their internal usage.
When will I be able to use it? Will it be possible to buy this ...
- 313
2
votes
0
answers
303
views
Multi-GPU, multi-machine computation with Torch
I know that Torch supports multi-GPU computation on the same machine (Example).
Is it possible to perform multi-GPU, multi-machine computations with Torch?
- 5,640
3
votes
1
answer
527
views
Difference between Validation data and Testing data?
I am bit confused about validating data. What is this data mainly for?? Like I am seeing some tutorial and they have some training[I know it] images , they they have some validation images[donot know] ...
- 1,637
3
votes
3
answers
2k
views
Predicting next action to take to reach a final state
Does anyone know of an algorithm that could be used to determine the next action to take to reach a desired state when trained on time-series data?
For example, a robot starts at a certain state, ...
- 196
2
votes
0
answers
153
views
In plain English, how to descibe i/o of the TensorFlow for language modelling?
I have followed the tutorial here about language modelling using Tensorflow to create LSTM and used PTB dataset. The code is here
I failed to understnad the exact specific input and the output of the ...
- 161
5
votes
1
answer
502
views
Training neural nets: is it important that the data is randomly sorted?
Let's say I have a neural network that classifies data into A, B or C.
I've heard that it's bad to train the network with data from one class at a time, e.g. ...
- 196
9
votes
2
answers
11k
views
Training Deep Nets on an Ordinary Laptop
Would it be possible for a an amateur who is interested in getting some "hands-on" experience in desining and training deep neural networks, to use an ordinary laptop for that purpose (no GPU), or is ...
- 196
3
votes
1
answer
387
views
Noisy behavior in deep learning feed-forward net
I am a bit unsure about optimizing a neural net with 3 or more layers. The input data is quite noisy and I seem to project the noise into the learning (strong bias in the data, 90% belong to one class ...
- 196
1
vote
1
answer
453
views
Character recognition neural net topology/design
I'm building a neural net for classifying characters in pictures. The input can be any character a-z, lowercase and uppercase. I only care about classifying the characters, and not the case, so the ...
- 28.6k
3
votes
0
answers
139
views
Heterodox use of Deep Learning to find hidden patterns
I would appreciate your comments/help about a strategy I am applying in one of my analysis. In short, my case is:
1) My data have biological origin, collected in a period of 120s, from a
subject ...
- 141
2
votes
0
answers
2k
views
Image Captioning example in keras Approach?
I have used the keras example code of Image Captioning in that I have used the VGG pretrained model for extracting image features(4096) and for text part I have done indexing to the unique words and ...
- 8,256
1
vote
1
answer
101
views
Questions regarding deep learning?
I have questions regarding this Normalized weights and Initial inputs video on Udacity course Deep Learning
In this video the lecturer talks about variables that go into Big-loss function should have ...
CommunityBot
- 1
7
votes
2
answers
6k
views
Why is my artificial neural networks almost always predicting positive elements?
I've been working for a long time with an artificial neural network algorithm (specifically, a siamese neural network) that I implemented in Torch & Lua.
I've been studying and playing with many ...
- 121
11
votes
1
answer
4k
views
HOW TO: Deep Neural Network weight initialization
Given difficult learning task (e.g high dimensionality, inherent data complexity) Deep Neural Networks become hard to train.
To ease many of the problems one might:
Normalize && handpick ...
CommunityBot
- 1
1
vote
0
answers
425
views
Why does the square loss not decrease in deconvolution network?
I use square loss to measure the difference between the output of the deconvolution network and the input image, use learning rate 0.01 and use SGD to optimize, code is written in tensorflow.
...
- 111
5
votes
2
answers
229
views
What are the most concrete and easiest to understand applications of deep learning in the industry?
I am a researcher in deep learning, and have given courses on the theory. Recently I was approached to give the same course adding sections using some very concrete examples of deep learning for ...
- 7,979
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 ...
- 101
2
votes
0
answers
234
views
Contrastive divergence in RBM
I have the following code, where x in the input data, w is the weight matrix, bv and bh are the biases for the visible and hidden units.
...
- 18.8k
1
vote
0
answers
712
views
How to implement a BiLSTM to classify speech data
I would like to know how should I provide the inputs to a BiLSTM if I am going to classify speech files (.wav) files. What is the proper way to label the data? Do I have to label each individual frame ...
- 111
10
votes
1
answer
3k
views
Why is Reconstruction in Autoencoders Using the Same Activation Function as Forward Activation, and not the Inverse?
Suppose you have an input layer with n neurons and the first hidden layer has $m$ neurons, with typically $m < n$. Then you compute the actication $a_j$ of the $j$-th neuron in the hidden layer by
...
- 28.6k
3
votes
2
answers
358
views
Deep Learning for Recommender System
I read about Recursive Neural Networks that they can convert Documents to distributed word representation.
In the context of new article recommendation, I am thinking to use this model to convert ...
- 3,775
5
votes
1
answer
7k
views
How to prepare colored images for neural networks?
I have seen many examples online regarding the MNIST dataset, but it's all in black and white. In that case, a 2D array can be constructed where the values at each array element represent the ...
- 3,077
5
votes
2
answers
558
views
How is it possible to process an image with a few neurons?
An 1024*1024 pixel image has around one million pixels. If I would like to connect each pixel to an R,G,B input neuron, then more than 3 million neurons are needed.
It would be really hard, to train ...
- 156
1
vote
0
answers
117
views
Include label for each time step to allow gradient flow in LSTM
Say I want to do a many-to-one classification task such as sentiment analysis with a sequence of ~100 elements using a LSTM. Might it help to train the network using a many-to-many setup instead to ...
- 790
1
vote
0
answers
206
views
Neural network with multiple kinds of output
Introduction:
I am trying to build a neural network similar to the following one http://www.nature.com/articles/srep11476 to predict two different features at the same time:
Secondary structure: ...
- 11
2
votes
0
answers
202
views
How to create Self learning data product
I am trying to build price recommendation solution for clients in a scalable manner. I have two choices as below.
Professional service: Statistician involvement to build regression model or any ...
- 865
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 ...
- 129
3
votes
1
answer
108
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 ...
CommunityBot
- 1
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 ...
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% ...
- 31
5
votes
1
answer
332
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?
- 731
0
votes
1
answer
544
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 ...
CommunityBot
- 1
1
vote
0
answers
87
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.
...
- 111
2
votes
0
answers
196
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 ...
- 121