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".

Filter by
Sorted by
Tagged with
1
vote
0answers
30 views

Reason why chess neural network might not be training

I've been trying to use a Stockfish-like chess evaluation neural network for the past few weeks but to no avail. I wanted to get some other opinions about why my current methods haven't worked. Input: ...
1
vote
0answers
7 views

Output representation for a neural network to learn grid-based game with multiple units

I have a round based game played on a grid map with multiple units that I would like to control in some fashion using neural network (NN). All of the units are moved at once. Each unit can move in any ...
0
votes
0answers
25 views

How to predict the possible next moves of cars from given first moves?

I want to find the next moves of cars from the previous moves, but I could not figure out what should I use as an algorithm. Can you help me to find a way to solve this problem? I have a lot of car ...
1
vote
0answers
14 views

Perform clustering on high dimensional data

Recently I trained a BYOL model on a set of images to learn an embedding space where similar vectors are close by. The performance was fantastic when I performed approximate K-nearest neighbours ...
0
votes
0answers
17 views

What is the motivation behind NAS Bench 201 research?

I recently read the "paper NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search", which can be found here. I can say that I understood most of the paper but I am not ...
1
vote
1answer
39 views

Does reaching the global optima guarantee good performance in a task?

It is to my understanding that, in deep learning, we are essentially trying to minimize the loss function that we have defined and reach its global optima through some form of optimization technique. ...
0
votes
1answer
39 views

Which data representation of text as input for NLP Deep Learning models?

I have been given a data set with 30.000 text documents (each text file is rather small with respect to its length and consists in most cases of around 20 sentences), which are labelled with 0 or 1. ...
0
votes
1answer
40 views

Equations for computing true positives and false positives when using object detection algorithms?

I am running some evaluation metrics using the YOLOv5 object detection algorithm, and wish to calculate my true positives and false positives. For instance, the evaluation metric outputs are as ...
0
votes
1answer
26 views

How can I adapt a trained neural network model to learn from newer data containing additional features?

We shall assume that we have a trained neural network model for some task $A$. The dataset used to train the model contained some $n$ features per sample. Using this dataset, we were able to train a ...
0
votes
0answers
30 views

Limit of momentum update equation

I am self-studying on optimization algorithm on https://d2l.ai/chapter_optimization/momentum.html and couldn't get my head around some derivation: Instead of the standard gradient descent update ...
0
votes
0answers
34 views

Deep learning and machine learning [duplicate]

If I was Given a set of large training examples (xi,yi), how can training a neural network (NN) via stochastic gradient descent differs from using regular gradient descent in terms of the mathematical ...
0
votes
1answer
29 views

Does "number of actions" refer to the number of actions taken or size of the action space?

In the original DDQN article (https://arxiv.org/pdf/1509.06461.pdf,) the phrase "number of actions" is used twice; First, in the following context: Secondly in Theorem 1. I have a hard ...
0
votes
1answer
27 views

What is the difference between Mean Teacher and Knowledge Distillation?

I recently read two papers: BYOL Bootstrap your own latent: A new approach to self-supervised Learning DINO Emerging Properties in Self-Supervised Vision Transformers. I am confused about the terms ...
0
votes
0answers
29 views

How to use EfficientDet for semantic segmentation?

In the EfficientDet paper, section 5.2. 5.2. EfficientDet for Semantic Segmentation, the authors say we modify our EfficientDet model to keep feature level $\{P2, P3, ..., P7\}$ in BiFPN, but only ...
0
votes
0answers
18 views

Is it possible that a deep neural network, with some variations, can be used for multiple tasks?

I am asking this question on deep neural network architectures only. If you want to restrict the domain of tasks then you can choose computer vision for this question. Suppose there is an architecture ...
0
votes
0answers
39 views

Is it effective to use deep learning method to produce a 1D signal as output from a 2D image as input?

I have a 1D signal that will produce a 2D image after some image processing algorithm. Would it be possible and effective to use deep learning method to reproduce the 1D signal if I have the 2D image ...
0
votes
1answer
54 views

What is the benefit of using a neural network instead of a look-up table in this case?

Assuming one has collected the 24 pairs of the input-output datasets for a target system: One can create a simple lookup table to describe the input-output behavior and utilize this as a controller. ...
1
vote
2answers
48 views

How to make NN distinguish between two types of functions (data)?

I have a neural network which is trying to predict two types of functions in a noisy setting. The input is an array, and the output is also an array. The two types of functions I am trying to predict ...
0
votes
0answers
31 views

Is my calculation of the partial derivative of the cost function with respect to a single weight in the first layer correct?

I'm trying to understand the chain rule of backpropagation. This is what I understood. Is it correct? $$ \frac{\partial E }{ \partial w} = \sum_{i} \frac{\partial E }{ \partial a_i^{(l)} } (\sum_{j} \...
0
votes
0answers
29 views

Could anyone please explain this sentence about training in parallel?

One way to reduce the computational complexity of hidden state recurrences is to connect a unit's hidden state to the prior unit's output rather than its hidden state. The resulting RNN has a lower ...
0
votes
0answers
19 views

How to train a FCNN with audio spectrogram images?

I'm working on an audio dereverberation deep learning model, based on the U-net architecture. The idea of my project came from image denoising with autoencoders. I feed the reverberated spectrogram to ...
0
votes
0answers
12 views

Is there some algorithms to get rid of pulses of noise in a video?

At about 0:12, 0:19, 0:21, 0:22 and 0:23 into the video, there are lots of pulses of noise. Is there some algorithms to get rid of them automatically?
0
votes
1answer
60 views

Generating automatic sports commentary (NLG)

I am trying to develop a "simple" announcer for sports segments that mainly consists of events like goals, fouls, substitutions, and many other events that could happen in many sports. The ...
1
vote
0answers
17 views

How to align or synchronize Youtube caption with audio accurately

I need to use the automatic caption from Youtube to precisely isolate excerpts from the video aligned to text and generate the dataset to train a model in French. So I've already written the script, ...
1
vote
2answers
80 views

Is it true that batch size of form $2^k$ gives better results?

I am confused among the following in selecting the batch size for my model. #1: powers of 2 I generally see that batch sizes are in powers of two: 32, 64, 128, 256. #2: maximum GPU Suppose my GPU ...
1
vote
1answer
34 views

How does the classification head of EfficientDet work?

EfficientDet outputs classes and bounding boxes. My question is about both but specifically I am interested in the class prediction net part. In the paper's diagram it shows 2 conv layers. I don't ...
1
vote
1answer
37 views

Triplet Loss- Three forward pass and one backward pass(Propagation)

I am trying to build a CNN model based on the concepts of Contrastive Learning. In specific based on Triplet loss. I have 5 different class labels and I create triplets such that in a triplet, two ...
0
votes
0answers
19 views

Model Architecture for Mapping Audio from Low-Quality Space to High-Quality

I am doing a side project, where I am planning on recording with a bad mic and a good mic concurrently, and am trying to make a model to map your low quality audio to the high quality space. First ...
2
votes
0answers
27 views

Is there any way to force one input have more effect on model?

Now I am working on building a deep learning model for a regression problem. I used 50 inputs and try to add one new categorical input. The problem is that this one input is much more important than ...
1
vote
0answers
20 views

a loss for binary step function data

I have some data with ground truth that looks like a binary step function, where part of it is 0 and part is one. An example for the GT can be like ...
1
vote
1answer
37 views

Does higher FLOPS mean higher throughput?

I understand that FLOPS means floating-point operations per second, and throughput is the number of inputs (for example, images) per second. If a model has higher FLOPS, it means it performs faster. ...
0
votes
0answers
10 views

Can Dynamical Variational Auto-encoders be trained on and used to generate static 2D images?

Is it possible to train dynamical variational autoencoders, such as Kalman Variational Autoencoders (KVAE), Recurrent Variational Autoencoders (RVAE), or Disentangled Sequential Autoencoders (DSAE) on ...
-1
votes
1answer
49 views

Is my dataset a time series dataset? and should I use an LSTM?

I have a dataset where I am recording temperature after every 4milliseconds till 500 and another feature "conductivity value". The length of the dataset is around a 1000 rows. I need to find ...
0
votes
1answer
25 views

Deep Learning Architecture where outputs from two different inputs are used for error calculation

Is there a deep learning architecture where outputs of the same model with two different inputs are used for error calculation (backpropagation)? Workflow: Input1 -----> Model ------> Output1 ...
0
votes
0answers
23 views

Transfer learning on YOLOv5 for character and shape detection

The task is to detect rotated alphanumeric characters embedded on colored shapes. We will have an aerial view of the object (from a UAS: Unarmed Aerial System), something of this sort: (One Uppercase ...
0
votes
0answers
22 views

How do I apply non-max suppression for 2-classes problems?

I have basic knowledge about non-max suppression and I know how it works for multiple classes, but what if I want to get a prediction for two classification problems? I give you an example. So I have ...
0
votes
0answers
16 views

Is there any subtle difference between recursive computation and recurrence computation?

Consider the following excerpt paragraph taken from the section titled "Unfolding Computational Graphs" of the chapter 10: Sequence Modeling: Recurrent and Recursive Nets of the textbook ...
1
vote
1answer
37 views

When does an RNN use the connections that help in going backward in time?

Consider the following paragraph taken from chapter 10: Sequence Modeling: Recurrent and Recursive Nets of the textbook named Deep Learning by Ian Goodfellow et al mentioning the connections of RNN to ...
0
votes
0answers
23 views

What does "statistical strength" mean in this context?

Consider the following excerpt from a paragraph taken from chapter 10: Sequence Modeling: Recurrent and Recursive Nets of the textbook named Deep Learning by Ian Goodfellow et al regarding the ...
1
vote
0answers
28 views

Reinforcement Learning applied to Optimisation Problem

Problem Statement: We are given an optimisation problem; with production centres, source airport, destination airports, transfer points and finally delivered to the customers. This is better explained ...
0
votes
0answers
45 views

If the model always underfits, do I really need a larger model?

I train my neural network on random points generated for a data set that theoretically consists of approximately $1.8 * 10^{39}$ elements. I sample (generate) tens of thousands of random points on ...
0
votes
0answers
13 views

XLMRoberta loss remains constant over iterations for TokenClassification task

I have created a simple XLMRoberta model for token classification. The task is to predict the quality of translation for each token/word. The data looks something like this, where the first sentence ...
0
votes
0answers
27 views

What is the meaning of "The linear model can now describe the function as increasing in $h_1$ and decreasing in $h_2$"?

In the famous Deep Learning book by Goodfellow et al., it is mentioned on page 169 in the caption of Figure 6.1 that The linear model can now describe the function as increasing in $h_1$ and ...
2
votes
1answer
55 views

What does "Gau" in GauGAN stand for?

GauGAN is a neural network architecture from NVIDIA that can create realistic images from semantic maps (and nowadays also textual descriptions).
1
vote
1answer
60 views

What exactly is embedding layer used in RNN encoders?

I am reading about RNN encoders. I came across the following line from this code. And I am facing difficulty in understanding the theoretical details regarding it. ...
0
votes
1answer
26 views

What is a "mask" in the context o RNN-based encoders?

While reading source code related to RNN encoders, I've come across the term mask as input to the encoder. What exactly is it?
0
votes
0answers
10 views

Including Object scale/dimension information in features generated by a CNN

I am working on a project where one of the tasks I need to do is to create embeddings for sketches. The sketches in question here are CAD Sketches. Being CAD sketches, the dimension information of the ...
0
votes
0answers
33 views

How to improve accuracy of CNN used for facial micro-expression analysis

From the paper (1) Facial expression analysis using CNN, the results using CNN show a 65% and 62% accuracy respectively, for emotion classification and state of mind identification. Proposed Method: ...
1
vote
1answer
53 views

Which pre-processing steps are necessary for Deep Learning models to solve a document classification problem?

I have created a data set with 30.000 text documents (each text file is rather small with respect to its length), which are labelled with 0 and 1. Using this data set, I want to train machine learning ...
1
vote
0answers
12 views

Are there any recommendations on initialising a single parameter in deep learning?

I want to initialize a parameter, which is a single real number in my model. If you want the role of the parameter in the model, you can assume it as the parameter to multiply with the output of the ...

1
2 3 4 5
33