Search Results
| Search type | Search syntax |
|---|---|
| Tags | [tag] |
| Exact | "words here" |
| Author |
user:1234 user:me (yours) |
| Score |
score:3 (3+) score:0 (none) |
| Answers |
answers:3 (3+) answers:0 (none) isaccepted:yes hasaccepted:no inquestion:1234 |
| Views | views:250 |
| Code | code:"if (foo != bar)" |
| Sections |
title:apples body:"apples oranges" |
| URL | url:"*.example.com" |
| Saves | in:saves |
| Status |
closed:yes duplicate:no migrated:no wiki:no |
| Types |
is:question is:answer |
| Exclude |
-[tag] -apples |
| For more details on advanced search visit our help page | |
Results tagged with deep-learning
Search options answers only
not deleted
user 14675
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.
1
vote
Mapping output neurons to classes
In multiclass classification problems, the number of output units (i.e. neurons) is equal to the number of classes. Only in binary classification, you have 2 classes but just 1 output unit.
The mappi …
- 27.5k
6
votes
Why is deep learning used in recommender systems?
"Recommender Systems" is a very broad area and can be approached from different optics: latent variable models, graph models, etc.
"Deep learning" is an umbrella term for gradient-based optimization o …
- 27.5k
7
votes
Accepted
What is the purpose of setting an initial weight on deep learning model?
This is greatly addressed in the Stanford CS class CS231n:
Pitfall: all zero initialization. Lets start with what we should not do. Note that we do not know what the final value of every weight sh …
- 27.5k
4
votes
Accepted
Deep Learning to estimate what is beyond the edge
I think the closest problem that has been addressed with deep learning is image inpainting, that is, filling a blacked out region in the image:
For instance, this paper: Semantic Image Inpainting w …
- 27.5k
1
vote
Is it possible to design a deep CNN model on a small size image dataset
According to your description of the data, it is highly probable that training any neural network of reasonable size will overfit the training data.
One option is to apply any possible regularization …
- 27.5k
2
votes
Accepted
Neural network got a lucky guess. Can it be trusted?
The loss in the curve suggests that the training can be improved by tuning hyperparameters, especially the learning rate and/or the batch size. Therefore the optimal decision would be to keep refining …
- 27.5k
0
votes
Filters in convolutional autoencoders
You should take into account that the size of the images in the Keras example is as little as 28x28 and that they are grayscale images (i.e.a single channel), so if you want to actually compress the i …
- 27.5k
0
votes
Accepted
Should the data be shuffled on a translation dataset
Yes, in NMT data is always shuffled.
For training, if each batch contains the same "type of content" (e.g. domain, register), then your model will be biased toward the type of content of the last bat …
- 27.5k
1
vote
Accepted
Are Deep Neural Networks limited to grayscale images depending on whether you use Seq. or Fu...
The answer is no, they are not limited.
However, your statements seem to contain multiple misunderstandings, so let's first clarify them:
The sequential and functional APIs in Keras are different app …
- 27.5k
14
votes
Accepted
Is (manual) feature extraction outdated?
In the general case, this is by no means true. Let's break down the case for different data scenarios:
For discriminative image models (e.g. image classification/labeling) this is true for some scen …
- 27.5k
0
votes
Accepted
Understanding LSTM text input
The input to an LSTM must be a batch of sequences of vectors of real numbers, i.e. 3D tensor). Textual inputs are discrete tokens, so they are a batch of sequences of integers (indexes to the vocabula …
- 27.5k
0
votes
NN converges quickly but is it a problem when performance is good on test set?
One problem you may be facing is a data leak, that is, that part of your test data is also on your training data and, therefore, the model will perform worse when used on actually unseen data.
A typic …
- 27.5k
1
vote
Accepted
Are there any pre-trained non english model of deepspeech?
You can check Coqui, a fork of Mozilla DeepSpeech created by former Mozilla DeepSpeech developers. It is well maintained and there are models for a lot of languages.
- 27.5k
2
votes
Is it worth to upgrade CUDA and cuDNN while having older GPUs?
There is no right answer to this question, because there are many factors to consider, for instance:
Indirect dependency on specific/minimum CUDA version: with deep learning frameworks like pytorch a …
- 27.5k
0
votes
How big is the threshold that is usually used in determining the convergence of loss values ...
There is no threshold reference value. Different tasks, losses and datasets lead to radically different loss value ranges and different amounts of noise. This is a somewhat experimentally defined thin …
- 27.5k