The Stack Overflow podcast is back! Listen to an interview with our new CEO.

Questions tagged [convolutional-neural-networks]

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

Filter by
Sorted by
Tagged with
69
votes
8answers
12k 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 ...
63
votes
9answers
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 ...
41
votes
3answers
27k 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 ...
28
votes
8answers
24k 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 ...
21
votes
4answers
314 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

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 ...
14
votes
3answers
21k views

How to handle images of large sizes in CNN?

Suppose there are 10K images of sizes 2400 x 2400 are required to use in CNN.Acc to my view conventional computers the people use will be of use. Now the question is how to handle such large image ...
14
votes
2answers
1k 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! ...
11
votes
2answers
8k 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 ...
11
votes
3answers
871 views

What topologies are largely unexplored in machine learning?

Geometry and AI Matrices, cubes, layers, stacks, and hierarchies are what we could accurately call topologies. Consider topology in this context the higher level geometrical design of a learning ...
10
votes
2answers
2k views

Which layer consumes more time in CNN training ? Convolution layers vs FC layers

In Convolutional Neural Network, which layer consumes maximum time in training? Convolution layers or Fully Connected layers? We can take AlexNet architecture to understand this. I want to see time ...
10
votes
3answers
1k 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
2answers
1k 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 ...
9
votes
1answer
321 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
4answers
571 views

Beyond neural networks?

Are there possible algorithms that have the potential to replace neural nets in the near future? And do we need that? What is the worst thing of using neural networks in terms of efficiency?
8
votes
2answers
121 views

Can machine learning algorithms (CNNs?) be used/trained 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
2answers
2k 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 ...
8
votes
4answers
7k views

Convolutional neural networks with input images of different dimensions - 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 ...
8
votes
3answers
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 ...
8
votes
2answers
483 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 ...
7
votes
6answers
1k views

Why Python not C?

I like the enforced indentation of Python that many don't like because I hate parenthetic typing and redundant semicolons. I like the shell interface, but why do some think Python is de facto for ...
7
votes
4answers
4k 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?
7
votes
3answers
185 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
3answers
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 very problem or domain-specific. However, there should be at least some "rules" that hold most times for filter ...
7
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 ...
6
votes
4answers
1k 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
2k 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
35 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
3k 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 ...
6
votes
1answer
100 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 ...
5
votes
2answers
90 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
3answers
203 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
74 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
2answers
63 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
3answers
2k 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 ...
5
votes
3answers
526 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 ...
5
votes
3answers
3k 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
2answers
88 views

What defines a good dataset in Deep Learning approach?

Scenario: I am trying to create a dataset with images of choice for different animal classes. I am going to train those images for classification using CNN. Problem: Lets assume I somehow don't have ...
5
votes
1answer
112 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
309 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 ...
5
votes
1answer
87 views

How can neural networks that extract many features be fooled by adversarial images?

I have been reading a bit about networks where deep layers able to deal with a bunch of features (be it edges, colours, whatever). I am wondering: how can possibly a network based on this '...
5
votes
1answer
485 views

Understanding the loss function of You Only Look Once(YOLO) network

I'm trying to implement a custom version of YOLO neural network. Originally it was described in this paper. I have some problems understanding the loss function they used. Basic information: An ...
5
votes
1answer
476 views

What makes learned feature detectors specialize in CNN?

It has been shown that it is possible to use unsupervised learning techniques to produce good feature detectors in CNNs. I can't understand what drives specialization of those feature detectors. In ...
5
votes
2answers
91 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
1answer
129 views

Can a purely policy convolution neural network based game learn to play better than its opponents?

This question has come from my experiment of building a cnn based tic-tac-toe game that I'm using as a beginner machine learning project. The game works purely on policy networks, more specifically - ...
5
votes
1answer
386 views

Game AI - Fast python OCR or cropped image input

I'm developing a Game AI which tries to master racing simulations. I already trained a CNN (alexnet) on ingame footage of me playing the game and the pressed keys as the target. As the CNN is only ...
5
votes
2answers
93 views

How data augmentation like rotation affects the quality of detection?

I'm using an object detection neural network and I employ data augmentation to increase a little my small dataset. More specifically I do rotation, translation, mirroring and rescaling. I notice that ...
4
votes
2answers
143 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, ...
4
votes
2answers
180 views

Image Classification

I am currently working on a project to classify snake types separately using an image of the snake. I need to train a module to classify snake images, but the problem is there are only a small number ...
4
votes
1answer
148 views

Why would neural network dream scenes mirror the hallucinations people experience when they're tripping?

In DeepDream wikipedia page it's suggested that a dreamlike images created by a convolutional neural network may be related to how visual cortex works in humans when they're tripping. The imagery ...