Questions tagged [convolutional-neural-networks]

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

Filter by
Sorted by
Tagged with
83
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 ...
75
votes
10answers
6k 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 ...
2
votes
1answer
392 views

How can the convolution operation be implemented as a matrix multiplication?

How can the convolution operation used by CNNs be implemented as a matrix-vector multiplication? We often think of the convolution operation in CNNs as a kernel that slides across the input. However, ...
43
votes
8answers
36k 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 ...
63
votes
3answers
42k 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 ...
29
votes
6answers
51k 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 ...
11
votes
5answers
7k 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
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, ...
4
votes
2answers
1k views

How to calculate the number of parameters of a convolutional layer?

I was recently asked at an interview to calculate the number of parameters for a convolutional layer. I am deeply ashamed to admit I didn't know how to do that, even though I've been working and using ...
2
votes
1answer
146 views

Why do we need convolutional neural networks instead of feed-forward neural networks?

Why do we need convolutional neural networks instead of feed-forward neural networks? What is the significance of a CNN? Even a feed-forward neural network will able to solve the image classification ...
2
votes
2answers
155 views

Do convolutional neural networks perform convolution or cross-correlation?

Typically, people say that convolutional neural networks (CNN) perform the convolution operation, hence their name. However, some people have also said that a CNN actually performs the cross-...
2
votes
1answer
84 views

Is continuous learning possible with a deep convolutional neural network, without changing its topology?

In general, is continuous learning possible with a deep convolutional neural network, without changing its topology? In my case, I want to use a convolutional neural network as a classifier of ...
1
vote
1answer
238 views

What is a fully convolution network?

I was surveying some literature related to Fully Convolutional Networks and came across the following phrase, A fully convolutional network is achieved by replacing the parameter-rich fully ...
18
votes
3answers
31k 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 ...
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 ...
8
votes
2answers
6k 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 ...
2
votes
2answers
1k views

What's the role of bounding boxes in object detection?

I'm quite new to the field of computer vision and was wondering what are the purposes of having the boundary boxes in object detection. Obviously, it shows where the detected object is, and using a ...
9
votes
2answers
933 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 ...
4
votes
2answers
2k views

What is feature embedding in the context of convolutional neural networks?

What are feature embeddings in the context of convolutional neural networks? Is it related to bottleneck features or feature vectors?
2
votes
1answer
423 views

Can ConvNets be used for real-time object recognition from video feed?

Convolutional neural network are leading type of feed-forward artificial neural network for image recognition. Can they be used for real-time image recognition for videos (frame by frame), or it takes ...
1
vote
1answer
96 views

How many layers exists in my neural network?

I have a neural network model defined as below. How many layers exist there? Not sure which ones to count when we are asked about the number. ...
0
votes
1answer
43 views

Use deep learning to rank video scenes

I'm new to machine learning and especially, deep learning. Given a video (and it's subtitle), I need to generate a 10-second summary out of this video. How can I use ML and DL to produce the most ...
6
votes
1answer
102 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
431 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 ...
4
votes
2answers
180 views

What is the best approach for writing a program to identify objects in a picture then crop them a specific way?

My works quality control department is responsible for taking pictures of our products at various phases through our QC process and currently the process goes: Take picture of product Crop the ...
4
votes
3answers
1k views

Convolutional neural nets and reduction of the layers

I have a very simple question about Conv nets. I understand the whole principle, but only one thing is not well explained on the Internet. If I have a 16 channels image that goes on a convolutional ...
4
votes
3answers
939 views

Convolutional Neural Network: does each filter in each convolution layer create a new image?

Say I have a CNN with this structure: input = 1 image (say, 30x30 RGB pixels) first convolution layer = 10 5x5 convolution filters second convolution layer = 5 3x3 convolution filters one dense layer ...
3
votes
1answer
636 views

How to load an image into tensorflow.js code which reads handwritten numbers and clasify them

I'm new to machine learning, so i figured I should look into google's tensor flow guides and I know how to code in JS so that's why I'm using tensorflow.js, there's and example in the guide that ...
3
votes
1answer
358 views

How does backpropagation work on a custom loss function whose components have magnitudes of different orders?

I want to use a custom loss function which is a weighted combination of l1 and DSSIM losses. The DSSIM loss is limited between 0 and 0.5 where as the l1 loss can be orders of magnitude greater and is ...
3
votes
1answer
98 views

How are exploding numbers in a forward pass of a CNN combated?

Take AlexNet for example: In this case, only the activation function ReLU is used. Due to the fact ReLU cannot be saturated, it instead explodes, like in the following example: Say I have a weight ...
2
votes
1answer
42 views

Accuracy scores in a Deep Learning project

I'm using three pre-trained deep learning models to detect vehicles and count from an image data set. The vehicles belong to one of these classes ['car', 'truck', 'motorcycle', 'bus']. So, for a ...
2
votes
1answer
562 views

What are some good alternatives to U-Net for biomedical image segmentation?

Soon I will be working on biomedical image segmentation (microscopy images). There will be a small amount of data (a few dozens at best). Is there a neural network, that can compete with U-Net, in ...
2
votes
1answer
751 views

Which neural network architectures are there that perform 3D convolutions?

I am trying to do 3d image deconvolution using convolution neural network. But I cannot find many famous 3d CNNs. Can anyone point out some for me? Background: I am using PyTorch, but any language ...
1
vote
1answer
491 views

What is the computational complexity of the forward pass of a convolutional neural network?

How do I determine the computational complexity (big-O notation) of the forward pass of a convolutional neural network? Let's assume for simplicity that we use zero-padding such that the input size ...
1
vote
2answers
116 views

Why is the validation performance better than the training performance?

I am training a classifier to identify 24 hand signs of American Sign Language. I created a custom dataset by recording videos in different backgrounds for each of the signs and later converted the ...
1
vote
1answer
103 views

Are commercially available neural ICs digital?

Apparently, one can buy a special-purpose integrated circuit (an IC like this one, for instance) to host a convolutional neural network. QUESTION Is such a circuit digital? Except for digital random-...
1
vote
0answers
44 views

Doubt regarding research paper on Crowd Counting using Convolutional neural networks and Markov Random Field

I am currently reading the research paper Image Crowd Counting Using Convolutional Neural Network and Markov Random Field by Kang Han, Wanggen Wan, Haiyan Yao, and Li Hou. I did not understand the ...
0
votes
1answer
51 views

Keras DQN Model with Multiple Inputs and Multiple Outputs [closed]

I am trying to create a DQN agent where I have 2 inputs: the agent's position and a matrix of 0s and 1s. The output is composed of the agent's new chosen position, a matrix of 0s and 1s (different ...
0
votes
2answers
50 views

How to handle images that don’t pertain to image classifier at all?

I am trying to create a CNN model that classifies if a person is wearing a seatbelt or not to verify they drive safely. I know to get images of people wearing seatbelts and people not wearing ...
0
votes
1answer
84 views

If vanishing gradients are NOT the problem that ResNets solve, then what is the explanation behind ResNet success?

I often see blog posts or questions on here starting with the premise that ResNets solve the vanishing gradient problem. The original 2015 paper contains the following passage in section 4.1: We ...
0
votes
1answer
42 views

Pixel-Level Detection of Each Object of the Same Class In an Image

I have source data that can be represented as a 2D image of many similar curves. They may oftentimes cross over one another, so regions of interest will overlap. My goal is to implement a neural ...