Questions tagged [convolutional-neural-networks]

For questions about convolutional neural networks, also known as CNN or ConvNet.

Filter by
Sorted by
Tagged with
81
votes
8answers
14k views

Do scientists know what is happening inside artificial neural networks?

Do scientists or research experts know from the kitchen what is happening inside complex "deep" neural network with at least millions of connections firing at an instant? Do they understand the ...
73
votes
10answers
5k views

How is it possible that deep neural networks are so easily fooled?

The following page/study demonstrates that the deep neural networks are easily fooled by giving high confidence predictions for unrecognisable images, e.g. How this is possible? Can you please ...
59
votes
3answers
39k views

How can neural networks deal with varying input sizes?

As far as I can tell, neural networks have a fixed number of neurons in the input layer. If neural networks are used in a context like NLP, sentences or blocks of text of varying sizes are fed to a ...
40
votes
8answers
33k views

In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels?

My understanding is that the convolutional layer of a convolutional neural network has four dimensions: input_channels, filter_height, filter_width, number_of_filters. Furthermore, it is my ...
33
votes
6answers
9k views

Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?

I trained a simple CNN on the MNIST database of handwritten digits to 99% accuracy. I'm feeding in a bunch of handwritten digits, and non-digits from a document. I want the CNN to report errors, so I ...
27
votes
6answers
47k views

What is the difference between a convolutional neural network and a regular neural network?

I've seen these terms thrown around this site a lot, specifically in the tags convolutional-neural-networks and neural-networks. I know that a neural network is a system based loosely on the human ...
21
votes
4answers
346 views

Is the pattern recognition capability of CNNs limited to image processing?

Can a Convolutional Neural Network be used for pattern recognition in a problem domain where there are no pre-existing images, say by representing abstract data graphically? Would that always be less ...
16
votes
3answers
28k views

How do I handle large images when training a CNN?

Suppose that I have 10K images of sizes $2400 \times 2400$ to train a CNN. How do I handle such large image sizes without downsampling? Here are a few more specific questions. Are there any ...
14
votes
0answers
2k views

What's the main concept behind capsule networks? [duplicate]

As you might know, capsule networks have been recently introduced by Hinton. There also have been several heads up within his talks. As expected, the paper elaborates on the idea way theoretically! ...
13
votes
5answers
14k views

How can I deal with images of variable dimensions when doing image segmentation?

I'm facing the problem of having images of different dimensions as inputs in a segmentation task. Note that the images do not even have the same aspect ratio. One common approach that I found in ...
11
votes
2answers
4k views

Which layer in a CNN consumes more training time: convolution layers or fully connected layers?

In a convolutional neural network, which layer consumes more training time: convolution layers or fully connected layers? We can take AlexNet architecture to understand this. I want to see the time ...
11
votes
2answers
11k views

What are bottleneck features?

In the blog post Building powerful image classification models using very little data, bottleneck features are mentioned. What are the bottleneck features? Do they change with the architecture that is ...
10
votes
5answers
6k views

What is the fundamental difference between CNN and RNN?

What is the fundamental difference between convolutional neural networks and recurrent neural networks? Where are they applied?
10
votes
2answers
2k views

Use AI or Neural Network for logo detection

I am trying to detect a TV channel logo inside a video file, so simply given an input .mp4 video, detect if it has that logo present in a specific frame, say first ...
10
votes
2answers
3k views

What is the difference between a receptive field and a feature map?

In a CNN, the receptive field is the portion of the image used to compute the filter's output. But one filter's output (which is also called a "feature map") is the next filter's input. What's the ...
10
votes
4answers
832 views

What are the models that have the potential to replace neural networks in the near future?

Are there possible models that have the potential to replace neural networks in the near future? And do we even need that? What is the worst thing about using neural networks in terms of efficiency?
10
votes
2answers
7k views

What is the concept of channels in CNNs?

I am trying to understand what channels mean in convolutional neural networks. When working with grayscale and colored images, I understand that the number of channels is set to 1 and 3 (in the first ...
10
votes
3answers
2k views

Using neural network to recognise patterns in matrices

I am trying to develop a neural network which can identify design features in CAD models (i.e. slots, bosses, holes, pockets, steps). The input data I intend to use for the network is a n x n matrix (...
9
votes
1answer
347 views

How much of a problem is white noise for the real-world usage of a DNN?

I read that deep neural networks can be relatively easily fooled (link) to give high confidence in recognition of synthetic/artificial images that are completely (or at least mostly) out of the ...
9
votes
2answers
1k views

Do deep learning algorithms represent ensemble-based methods?

Shortly about deep learning (for reference): Deep learning is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph ...
9
votes
2answers
754 views

What benefits can be got by applying Graph Convolutional Neural Network instead of ordinary CNN?

What benefits can we got by applying Graph Convolutional Neural Network instead of ordinary CNN? I mean if we can solve a problem by CNN, what is the reason should we convert to Graph Convolutional ...
8
votes
2answers
159 views

Can machine learning algorithms be used to differentiate between small differences in details between images?

I was wondering if machine learning algorithms (CNNs?) can be used/trained to differentiate between small differences in details between images (such as slight differences in shades of red or other ...
8
votes
3answers
6k views

Learning Rotated bounding box for object detection

I have checked out many methods and paper like yolo, ssd, etc with very promising result in detecting a rectangular box around object, But could not find any paper, which shows an learning a rotated ...
8
votes
3answers
5k views

Using machine learning to identify CAD model features

I am trying to develop a machine learning algorithm to identify topological features within 3D CAD models (i.e. slots, pockets, holes, bosses etc) For the input data I have decided to use the ...
8
votes
2answers
5k views

How do we choose the kernel size depending on the problem?

Obviously, finding suitable hyper-parameters for a neural network is a complex task and problem or domain-specific. However, there should be at least some "rules" that hold most times for the size of ...
8
votes
1answer
3k views

Confusion regarding anchor boxes in YOLO

I'm going through Andrew NG's course which talks about YOLO but he doesn't go into the implementation details of anchor boxes. Look through the code, each anchor box is represented by two values, but ...
7
votes
2answers
2k views

When should I use 3D convolution?

I am new to convolutional neural networks, and I am learning 3D convolution. What I could understand is that 2D convolution gives us relationships between low-level features in the X-Y dimension, ...
7
votes
3answers
357 views

CNN's vs Densely Connected NN's

In image classification we are generally told the main reason of using CNN's is that densely connected NN's cannot handle so many parameters (10 ^ 6 for a 1000 * 1000 image). My question is, is there ...
7
votes
2answers
1k views

What is the difference between graph convolution in the spatial vs spectral domain?

I've been reading different papers regarding graph convolution and it seems that they come into two flavors: spatial and spectral. From what I can see the main difference between the two approaches is ...
6
votes
2answers
3k views

How to use CNN for making predictions on non-image data?

I have a dataset which I have loaded as a data frame in Python. It consists of 21392 rows (the data instances, each row is one sample) and 1972 columns (the features). The last column i.e. column 1972 ...
6
votes
4answers
2k views

Why my test error is lower then train error

I am trying to train a CNN regression model using the ADAM optimizer, dropout and weight decay. My test accuracy is better than training accuracy. But as I know, usually train accuracy is better than ...
6
votes
4answers
3k views

What is the purpose of hidden nodes in neural network?

If I have a set of sensory nodes taking in information and a set of "action nodes" which determine the behavior of my robot, why do I need hidden nodes between them when I can let all sensory nodes ...
6
votes
1answer
58 views

Is there any use of using 3D convolutions for traditional images (like cifar10, imagenet)?

I am curious if there is any advantage of using 3D convolutions on Images like Cifar10/100 or Imagenet. I know that they are not usually used on this data set, though they could because the channel ...
6
votes
3answers
892 views

CNN backpropagation with stride>1

I read that to compute the derivative of the error with respect to the input of a convolution layer is the same to make of a convolution between deltas of the next layer and the weight matrix rotated ...
6
votes
1answer
71 views

Are there well-established ways of mixing different inputs (e.g. image and numbers)?

I am interested in the possibility of having extra input along with the main data. For instance, a medical application that would rely mostly on an image: how could one also account for sex, age, etc.?...
6
votes
1answer
477 views

What are the benefits of using max-pooling in convolutional neural networks?

I am reading Francois Chollet's Deep learning with Python, and I came across a section about max-pooling that's really giving me trouble. I am unable to copy-paste the content, so I've included ...
6
votes
2answers
108 views

CNNs: What happens from one neuron volume to the next?

I've gone through several descriptions of CNNs online and they all leave out a crucial part as if it were trivial. A "volume" of neurons consists of several parallel layers ("feature maps"), each the ...
5
votes
2answers
121 views

How do I improve accuracy and know when to stop training?

I am training a modified VGG-16 to classify crowd density (empty, low, moderate, high). 2 dropout layers were added at the end on the network each one after one of the last 2 FC layers. network ...
5
votes
2answers
2k views

Can Convolutional Neural Networks be applied in domains other than image recognition?

I'm new in this argument, my question is: Can convolution be applied in other contexts different from image recognition? Is there a good source to learn from?
5
votes
1answer
412 views

Can a vanilla neural network theoretically achieve the same performance as CNN?

I perfectly understand that CNN takes into account the local dependency of each pixel to the nearby pixels. In addition, CNNs are spatially invariant which means that they are able to detect the same ...
5
votes
3answers
209 views

How to make convnets aware what the image actually is, not what is depicted on it?

I've uploaded a picture to Wolfram's ImageIdentify of graffiti on the wall, but it recognized it as 'monocle'. Secondary guesses were 'primate', 'hominid', and 'person', so not even close to 'graffiti'...
5
votes
1answer
68 views

Concrete example of latent variables and observables plugged into the Bayes' rule

In the context of the variational auto-encoder, can someone give me a concrete example of the application of the Bayes' rule $$p_{\theta}(z|x)=\frac{p_{\theta}(x|z)p(z)}{p(x)}$$ for a given latent ...
5
votes
1answer
238 views

Does it make sense to apply softmax on top of relu?

While working through some example from Github I've found this network (it's for FashionMNIST but it doesn't really matter). Pytorch forward method (my query in upper case comments with regards to ...
5
votes
4answers
6k views

Traffic signs dataset

I'm looking for annotated dataset of traffic signs. I was able to find Belgium, German and many more traffic signs datasets. The only problem is these datasets contain only cropped images, like this: ...
5
votes
4answers
142 views

What kind of neural network architecture do I use to classify images into one hundred thousand classes?

I have an image dataset where objects may belong to one of the hundred thousand classes. What kind of neural network architecture should I use in order to achieve this?
5
votes
2answers
73 views

Can translational invariance of CNNs be unwanted if object is likely in certain positions?

Various texts on using CNNs for object detection in images talk about how their translation invariance is a good thing. Which makes sense for tasks where the object could be anywhere in the image. Let'...
5
votes
2answers
142 views

Aren't all discrete convolutions (not just 2D) linear transforms?

The image above, a screenshot from this article, describes discrete 2D convolutions as linear transforms. The idea used, as far as I understand, is to represent the 2 dimensional $n$x$n$ input grid as ...
5
votes
3answers
4k views

How can 3 same size CNN layers in different ordering output different receptive field from the input layer?

Below is a quote from CS231n Prefer a stack of small filter CONV to one large receptive field CONV layer. Suppose that you stack three 3x3 CONV layers on top of each other (with non-linearities ...
5
votes
1answer
120 views

Use ConvNet to predict bitmap

I want to build a classifier which takes an aerial image and outputs a bitmap. The bitmap is supposed to be 1 at every pixel where the aerial image has water. For this process I want to use a ConvNet ...
5
votes
2answers
338 views

Feasibility of generating large images with a convnet

I've spent the past couple of months learning about neural networks, and am thinking of projects that would be fun to work on to cement my understanding of this tech. One thing that came to mind last ...

1
2 3 4 5
16