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 neural-network
Search options not deleted
user 843
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.
0
votes
Accepted
Does the network learn based on previous training or does it restart? Matlab, neuralnetworks
It trains again based on what it learned the first time you did OP = train(OP,inputsVals,targetVals). More generally, train uses your network's weights, i.e. it does not initialize the weights. The we …
- 5,820
0
votes
How are deep-learning NNs different now (2016) from the ones I studied just 4 years ago (2012)?
A similar question was asked on CV: difference between neural network and deep learning:
Deep learning = deep artificial neural networks + other kind of deep
models.
Deep artificial neural …
- 5,820
1
vote
Are stacked NN the second generation of NN?
No.
Kumar, Satish. Neural networks: a classroom approach. Tata McGraw-Hill Education, 2004.:
The first generation of neural network models employed McCulloch-Pitts TLN type neuron. They were esse …
- 5,820
19
votes
Accepted
Difference of Activation Functions in Neural Networks in general
A similar question was asked on CV: Comprehensive list of activation functions in neural networks with pros/cons.
I copy below one of the answers:
One such a list, though not much exhaustive:
h …
- 5,820
6
votes
Accepted
Pylearn2 vs TensorFlow
You might want to take into consideration that Pylearn2 has no more developer, and now points to other Theano-based libraries:
There are other machine learning frameworks built on top of Theano th …
- 5,820
5
votes
Best python library for neural networks
neon:
Python based
Open source (Apache 2.0 License)
Developed by Nervana Systems (if you don't know them: Deep learning startup Nervana raises $20.5M; Nervana Systems raises 3.3M USD to build hardw …
19
votes
Best python library for neural networks
TensorFlow (by Google, released on 2015-11-09) looks promising.
open source (Apache 2.0 License) (GitHub)
Python (backend in C++)
CPU/GPU
Auto-Differentiation
Portable (even works on mobile devices) …
7
votes
Best python library for neural networks
MXNet:
written in C++ but has an API in Python (and a few other programming languages such as R, Julia, and Go)
Scales up to multi GPUs and distributed setting with auto parallelism.
Automatic diffe …
6
votes
4
answers
2k
views
What GPU specifications matter when training and using neural networks?
I need to purchase some GPUs, which I plan to use for training and using some neural networks (most likely with Theano and Torch). Which GPU specifications should I pay attention to?
E.g.:
one shou …
- 5,820
3
votes
Best python library for neural networks
Microsoft Cognition Toolkit (previously known as CNTK) has a Python API. Amongst other things, it is supposed to be good for multi-GPU:
Examples and tutorials can be found on https://github.com/Mi …
9
votes
Accepted
After the training phase, is it better to run neural networks on a GPU or CPU?
This depends on many factors, such as the neural network architecture (CNNs tend to be better optimized than RNN on GPU) as well as how many test samples you give as input to the neural network (GPUs …
- 5,820
4
votes
Why do CNNs with ReLU learn that well?
ignoring that is not differentiable at 00, as I think it is done in practice
yes see ReLUs are not differentiable at zero
If a neuron outputs 0 for every sample of the training data, it is b …
- 5,820
4
votes
Best python library for neural networks
DyNet: The Dynamic Neural Network Toolkit. From {1}:
We describe DyNet, a toolkit for implementing neural network models based on dynamic declaration of network structure. In the static declaratio …
7
votes
HOW TO: Deep Neural Network weight initialization
As far as I know the two formulas you gave are pretty much the standard initialization. I had done a literature review a while ago, I copied it below if interested.
[1] addresses the question:
Fir …
- 5,820
1
vote
0
answers
80
views
What are the downsides of using TPUs instead of GPUs when performing neural network training...
What are the downsides of using TPUs instead of GPUs when performing neural network training or inference?
From what I read on https://www.predictiveanalyticsworld.com/machinelearningtimes/should-you …
- 5,820