Questions tagged [deep-learning]

For questions related to deep learning, which refers to a subset of machine learning methods based on artificial neural networks (ANNs) with multiple hidden layers. The adjective deep thus refers to the number of layers of the ANNs. The expression deep learning was apparently introduced (although not in the context of machine learning or ANNs) in 1986 by Rina Dechter in the paper "Learning while searching in constraint-satisfaction-problems".

647 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
2
votes
1answer
48 views

A model for each sub-problem vs one model for the whole problem

Let's say one wants to use a neural net to learn some function $g(x)$. Let's say that we know that $g$ is a combination of two functions (or two sub-problems), $g(x)=f_2(f_1(x))$, and that we have two ...
2
votes
0answers
33 views

Single label classification into hierarchical categories using a neural network

I am working on a classification problem into progressive classes. In other words, there is some hierarchy of categories in such a way, that A < B < C, e.g. low, medium, high, very high. What ...
2
votes
0answers
38 views

Creating Dataset for Image Classification

I want to develop a CNN model to identify 24 hand signs in American Sign Language. I created a custom dataset that contains 3000 images for each hand sign i.e. 72000 images in the entire dataset. For ...
2
votes
0answers
33 views

Possible approaches to dealing with unbalanced dataset and highly biased deep learning algorithm

I have an extremely unbalanced video dataset for a two class video classification problem.All my videos in my current video dataset is $40$ second long with $900p$ resolution.However the dataset is ...
2
votes
0answers
45 views

Is Mean Squared Error Loss function a good loss function for continuous variables $0 < x < 1$

Suppose I am utilising a neural network to predict the next state, $s'$ based on the current $(s, a)$ pairs. all my neural network inputs are between 0 and 1 and the loss function for this network ...
2
votes
0answers
130 views

What is symbol-to-number differentiation?

I recently came across symbol-to-symbol and symbol-to-number differentiation, out of which symbol to symbol seemed fairly straightforward - the computational graph is extended to include gradient ...
2
votes
0answers
53 views

What are examples of commonly used feature and readout maps?

It is well-known that deep feedforward networks can approximate any continuous function from $\mathbb{R}^k$ to $\mathbb{R}^l$, (uniformly on compacts). However, in practice feature maps are ...
2
votes
0answers
29 views

Is there any wrong in my focal loss derivation?

Assume $\mathbf{X} \in R^{N, C}$ is the input of the softmax $\mathbf{P} \in R^{N, C}$, where $N$ is number of examples and $C$ is number of classes: $$\mathbf{p}_i = \left[ \frac{e^{x_{ik}}}{\sum_{j=...
2
votes
1answer
128 views

Can a fully convolutional network always return an image of the same size as the original?

I'm trying to perform a segmentation task on images of multiple sizes using fully convolutional neural networks. Currently, I'm using EfficientNet as a feature extractor, and adding a deconvolution/...
2
votes
0answers
46 views

Why is my DQN model not getting better?

I've created a deep Q network. My model does not get better, and can't see what I'm doing wrong. I'm new to RL. Replay Memory ...
2
votes
0answers
40 views

How can I get to a final output of shape $224 \times 224$, without FC layers, from a tensor of specific shape, in OpenPose?

I am approaching the implementation of the OpenPose algorithm for realtime human body pose estimation. According to the official paper OpenPose: Realtime Multi-Person 2D Pose Estimation using Part ...
2
votes
0answers
30 views

Can the addition of low-quality images to the training dataset increase the network performance?

I already trained a deep neural network called YOLO (You Only Look Once) with high-quality images (1920 by 1080 pixels) for a detection task. The result for mAP and IOU were 93% and 89% respectively. ...
2
votes
0answers
44 views

Recent algorithms for correcting mislabeled data using multilayer perceptrons

I am doing literature research on algorithms for correcting mislabeled data using multilayer perceptrons. Found an "old" paper An algorithm for correcting mislabeled data (2001) by Xinchuan Zeng et al....
2
votes
0answers
39 views

Is there an efficient way of determining the layers with the best performance as feature extractors in GoogleNet?

I am using a caffe model of pre-trained GoogleNet trained on ImageNet from here for image retrieval task (place recognition, more specifically). I would like to know the layer with best performance ...
2
votes
0answers
45 views

Is there a way to add “focus” on parts of the image when using CNNs?

I'm building a CNN/3DCNN model that classifies hand gestures. The problem is that the actual gesture occupies only like 1% of the whole image. That means that an enormous amount of convolutional ...
2
votes
1answer
215 views

What's the intuition behind contrastive learning?

Recently, I have seen a surge of papers w.r.t contrastive learning (a subset of semi-supervised learning). Can anyone give a detailed explanation of this approach with its advantages/disadvantages ...
2
votes
0answers
47 views

How does positional encoding work in the transformer model?

In the transformer model, to incorporate positional information of texts, the researchers have added a positional encoding to the model. How does positional encoding work? How does the positional ...
2
votes
1answer
56 views

Why is the sample size of stochastic gradient descent a power of 2?

I watched in the video lecture of cs224: Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 2 – Word Vectors and Word Senses. They take the sample size of the window to be $2^5 = 32$ or $...
2
votes
0answers
65 views

Why gradients are so small in deep learning?

The learning rate in my model is 0.00001 and the gradients of the model is within the distribution of [-0.0001, 0.0001]. Is it ...
2
votes
0answers
50 views

Suitable deep learning algorithms for spatial / geometric data

I have a task of classifying spatial data from a geographic information system. More precisely, I need a way to filter out unnecessary line segments from the CAD system before loading into the GIS (...
2
votes
0answers
128 views

How does adding noise to the action in DDPG help in learning?

I can't understand how playing with the action generated by the actor network in DDPG by adding the noise term helps in exploration.
2
votes
0answers
77 views

How is the receptive field of a CNN affected by transposed convolution?

When computing receptive field recursively through a CNN, does a transposed convolution affect the receptive field the same way that a convolution does if the kernel and stride is the same?
2
votes
2answers
94 views

Does a fully convolutional network share the same translation invariance properties we get from networks that use max-pooling?

Does a fully convolutional network share the same translation invariance properties we get from networks that use max-pooling? If not, why do they perform as well as networks which use max-pooling?
2
votes
0answers
67 views

External GPU for Mac

I'd like to buy an eGPU for my MaxBook Pro to use for simple deep learning tasks. My setup is: ...
2
votes
0answers
25 views

What are the current tools and techniques for image segmentation in order of pragmatism?

To explain what I mean I'll depict the two extremes and something in the middle. 1) Most pragmatic: If you need to just segment a few images for a design project, forget AI. Go into Adobe Photoshop ...
2
votes
0answers
265 views

How do I train a multiple-speaker model (speech synthesis) based on Tacotron 2 and espnet?

I'm new to Speech Synthesis & Deep Learning. Recently, I got a task as described below: I have problem in training a multi-speaker model which should be created by Tacotron2. And I was told I can ...
2
votes
0answers
27 views

Did people analyze dynamics of very simple LSTMs?

I wonder if researchers tried to understand how LSTMs work by analyzing the dynamics of simple LSTM (e.g. with 2 units)? For example how the hidden state evolves depending on the properties of weight ...
2
votes
0answers
118 views

What is the difference between using a backbone architecture and transfer learning?

I'm super new to deep learning and computer vision, so this question may sound dumb. In this link (https://github.com/GeorgeSeif/Semantic-Segmentation-Suite), there are pre-trained models (e.g., ...
2
votes
0answers
17 views

Getting started with creating a general AI based on textual and then image based data?

I have a pool of knowledge that I want to mine for information and allow an AI to deduce likely conclusions from this information. My goal is to give the AI a set of textual data that is rated on a ...
2
votes
0answers
33 views

How can I train a Deep Learning model using degraded photos and their clean version to correct photos

I have 5000 degraded pictures ( pixelated, blurry, too much luminosity ... ) and their clean versions, and I would like to train a model so that it can predict how to correct future pictures. I've ...
2
votes
0answers
41 views

How can I compare EEG data with accelerometer data in 1 algorithm?

I have frequency EEG data from fall and non-fall events and I am trying to incorporate it with accelerometer data that was collected at the same time. One approach is, of course, to use two separate ...
2
votes
0answers
470 views

Why isn't there a model playing FPS like CoD or Battlefield already existing?

Assuming we had an unlimited time to train a model and a very powerful machine to use our model in real-time (hello quantum computer), I'd like to know why no one could achieve to build an AI able to ...
2
votes
0answers
38 views

How can I extract the reason of the legal compensation from a court report?

I'm working on a project (court-related). At a certain point, I have to extract the reason of the legal compensation. For instance, let's take these sentences (from a court report) Order mister X ...
2
votes
0answers
36 views

YOLO 9000 about Better Stronger

In this paper, YOLO has three features compared to YOLO v1. This question is about Better and Faster. In the Better section, there are many techniques such as Batch Norm, Anchor Box and so on. In the ...
2
votes
1answer
402 views

How does a batch normalization layer work?

I understood that we normalize to input features in order to bring them on the same scale so that weights won't be learned in arbitrary fashion and training would be faster. Then I studied about ...
2
votes
0answers
36 views

Are there any approaches other than deep learning to deal with unexpected questions in a question answering system?

I'm working on a question answering bot as my graduation project. The main concept is having a text file with many sentences, and building a question answering bot which answers a user's question ...
2
votes
0answers
38 views

How can I prevent a Recursive Neural Network from performing extremely poorly after a few cycles?

I've trained a neural network that can predict the $(n+1)^{th}$ element in a sequence, given the $n^{th}$ element. It does a pretty good job doing this, with very little error. The problem emerges ...
2
votes
0answers
83 views

Which neural network should I use to transform the pixels of a video overtime?

I want to train a network with video data and have it transform pixel values overtime on an input video. This is for an art project and does not need to be super elaborate, but the videos I want to ...
2
votes
0answers
41 views

FasterRCNN's RPN network training

I would like to know if my understanding of RPN training is correct, and if never training the RPN on some specific anchor box is bad (i.e if the anchor never sees good nor bad examples). To make my ...
2
votes
0answers
25 views

Which algorithm and architecture to use for 1:1 matrix transformation of an 8X8 dimension?

I would like to map the simplest 8X8 matrices, one to one, but am not sure which AI algorithm would give the best performance. I am thinking about the DeepLearning4j, however, I don't know which ...
2
votes
0answers
103 views

Position of layer normalization in transformer model

In Attention Is All You Need paper: That is, the output of each sub-layer is $LayerNorm(x+Sublayer(x))$, where $Sublayer(x)$ is the function implemented by the sub-layer itself. We apply dropout to ...
2
votes
0answers
67 views

How would one develop an action space for a game that is proprietary?

I'm currently trying to develop an RL that will teach itself to play the popular fighting game "Tekken 7". I initially had the idea of teaching it to play generally- against actual opponents with ...
2
votes
0answers
146 views

What is a location-based addressing in a neural Turing machine?

In the neural Turing machine (NTM), the content-based addressing and location-based addressing is used for memory addressing. Content-based addressing is similar to the attention-based model, ...
2
votes
0answers
14 views

yolo output and how to define labels for backpropogation on it

I want to build the yolo architecture in keras but can't understand the basic idea behind the training of the yolo, like how to define the labels for whether there is no object there what we have to ...
2
votes
0answers
14 views

Loss function for increasing the quality of the image when labels are not perfectly alligned

I am trying to increse the quality of the images that I gather from the microscope. That is a acoustic microscope and there are lots of technical details but in a nutshell the low quality images and ...
2
votes
0answers
344 views

How does deepfake technology work with multiple people in a single frame?

I was watching this video from corridor crew, according to them, they have used deepfake technology to create this video. I myself have never made a deepfake videos, but I have enough knowledge in the ...
2
votes
0answers
39 views

How should I make output layer of my neural network so that I can get outputs ranging from [-20,-1]

I am trying to make a neural network which takes in 0 and 1 as it's input and should give me output ranging from [-20,-1].I am using three layers with sigmoid as the activation function .How should I ...
2
votes
1answer
67 views

How to represent integer values in sequence to sequence prediction task in encoder-decoder LSTM?

I have a large 2D grid having 30k rows and 35k columns, so a total of 30x35k grid cells. Each grid cell is represented by a unique integer number (identity of grid cell). I have several trajectories ...
2
votes
0answers
44 views

Which deep neural networks are appropriate for the detection of bombs?

This is a follow-up question from my previous post here about explosion detection. I gathered a dataset of explosions. As I'm new to Deep Learning in Keras, I'm trying to see what architecture best ...
2
votes
0answers
363 views

Is it possible to create a decompiler using AI?

I would like to decompile a compiled file to source code. Is it possible to use any AI technique to perform decompilation? Is there any research on this topic? If yes, can you briefly explain one of ...

1 2
3
4 5
13