Questions tagged [deep-learning]

a new area of Machine Learning research concerned with the technologies used for learning hierarchical representations of data, mainly done with deep neural networks (i.e. networks with two or more hidden layers), but also with some sort of Probabilistic Graphical Models.

Filter by
Sorted by
Tagged with
0
votes
0answers
14 views

What is the difference between a “cell” and a “layer” within neural networks?

So I understand what "layers" are. If you have 5 layers in your model, your data basically gets transformed 5 times via 5 activation functions. The number of "neurons" within a ...
0
votes
0answers
5 views

How do Deep Q networks actually converge

The whole idea of DQNs is converging to our target values, but in supervised learning these values are the unbiased true values In reinforcement learning, the target value is also a prediction, so how ...
0
votes
1answer
14 views

What is keras tuner?

I have implemented a deep learning model using Keras library. A lot of data scientists said use Keras tuner to increase model performance. I am bit confuse what is Keras tuner and when should I use ...
0
votes
1answer
23 views

Can someone explain to me the structure of a plain Recurrent Neural Network?

I have seen pictures of RNNs and LTSMs, and they usually look like this: Here the task is to take a sentence and make a prediction of some sort. What are each of the green squares? Are each of them ...
0
votes
0answers
14 views

What are the differences between Knowledge Graph Embeddings (KGE) and Graph Neural Network (GNN)

From page 3 of this paper Knowledge Graph Embeddings and Explainable AI, they mentioned as below: Note that knowledge graph embeddings are different from Graph Neural Networks (GNNs). KG embedding ...
0
votes
0answers
24 views

In a double Deep Q network what would happen if we switch the roles of both networks

We normally use the online network for action selection and the target network for evaluation , would there be a difference if we switched the roles? Because in the case Of Double Q learning, we ...
0
votes
0answers
8 views

Finding bounding box coordinates in Object Detection

In some of the OpenCV implementations for object detection , I don't understand how the co-ordinates of the bounding box of an object are extracted from the image. For example , In Object Detection ...
0
votes
0answers
12 views

Multi-class classification issue using Keras Found input variables with inconsistent numbers of samples: [20000, 4] [closed]

My goal is to create a model for detecting different brands of beer bottles. I've been following this example/tutorial https://www.kaggle.com/prateek0x/multiclass-image-classification-using-keras for ...
1
vote
1answer
22 views

What are “downstream models”?

In the ResNeSt paper they say on page 4: "despite their great success in image classification, the meta network structures are distinct from each other, which makes it hard for downstream models ...
0
votes
1answer
32 views

How to use text as an input for a neural network - regression problem? How many likes/claps an article will get

I am trying to predict the number of likes an article or a post will get using a NN. I have a dataframe with ~70,000 rows and 2 columns: "text" (predictor - strings of text) and "likes&...
-3
votes
0answers
28 views

how to train a model using many data sets in machine learning and obtain a final model [closed]

I want to apply auto-encoder for de-noising the time-series data. So I have some doubts in my mind that I need clarifications. I have 100 training data sets and I just want to train a supervised model ...
0
votes
1answer
23 views

Which GUI library to use with Deep Learning [closed]

I have completed basics Deep Learning course from coursera using Tensorflow and Keras. Now I want to apply GUI to it. So which library should i learn: 1.PyQt 2.Kivy 3.Tkinter Are there libraries which ...
2
votes
0answers
33 views

Multiple features in LSTM

It's clear how LSTM works with 1 feature. But what happens if the number of features is > 1? According to the answer proposed here, Keras creates a computational graph that executes the sequence ...
0
votes
0answers
25 views

Why the training loss increases, and predict everything as '1' or '0'

Those two pictures are from two similar experiments using same code. I am fine-tuning a pretrained-Bert model to do a binary text classification task, the dataset is 50% positive vs 50% negative, so ...
0
votes
0answers
10 views

How to specify version for dependencies so that each one is compatible and stays within a size limit?

I am trying to deploy a web app to Heroku. The free tier is limited to 500 MB. I am using my resnet34 model as a .pkl file. I create model with it using the fastai ...
0
votes
0answers
12 views

Training images for gender and and age detection from face

Can someone please tell me if it is feasible to train my own set of facial images to detect gender and age without using any cloud architecture or paying some amount of money ? And , on an average how ...
0
votes
0answers
11 views

What are image-wise nearest neighbour classifier and pixel-wise nearest neighbour classifier?

I'm reading the paper "Few-Shot Semantic Segmentation with Prototype Learning", and on the figure 2, page 5, there is a image-wise nearest neighbour classifier but it doesn't explain what is....
0
votes
1answer
21 views

Suitable neural network type to classify text in images

I have images that contain text and I am not sure what is the type of NN that can do the job for me. Basically, it will have to read the images and understand the text in order to be able to classify ...
0
votes
0answers
27 views

Performance worsen when normalizing on CNN

I am facing quite a strange behaviour. As far as I have understood, especially when dealing with CNN, feature normalisation/ standardisation, should help the model at converging faster. Now, I am ...
0
votes
1answer
21 views

Extract data from facebook

I am learning about social media analysis. I am aware that we can extract the data from twitter using hashtags and API. Ex; If I use #covid19, I will get all tweets ...
1
vote
1answer
41 views

Can mini-batch gradient descent outperform batch gradient descent? [duplicate]

As I was reading and going through the second course of Andrew Ng's deep learning course, I came across a sentence that said, With a well-turned mini-batch size, usually it outperforms either ...
0
votes
0answers
15 views

Classification on numerical features using Deep learning [closed]

I have manually extracted features for around 5000 images from Image processing algorithm. I would like to use these features for Anomaly detection using Deep learning methods. I have already used ...
0
votes
0answers
23 views

Entity Recognition to extract question,options and diagrams from a question paper? [duplicate]

Here is a sample question paper. I want to extract questions, their options and diagrams for the corresponding question(if any). Thinking of doing entity recogntion for the same. But I am not sure if ...
0
votes
1answer
19 views

How do I predict a class for each time step using the information from previous timsteps

I have a classification problem but different than usual. I have to provide 3 outputs (each of them either 0 or 1) for every input of 3 timesteps and 10 features. What model architecture or approach ...
2
votes
1answer
83 views

Which deep learning network would be suitable for classifying this kind of text data?

I have some experience with images and have played around with image classification using CNN's but have limited knowledge when it comes to text data. The input that I currently want to classify is ...
1
vote
1answer
30 views

image_dataset_from_directory VS flow_from_directory

What is the main diffrence between flow_from_directory VS image_dataset_from_directory in keras? which one should I use?
0
votes
0answers
4 views

Using AutoEncoder for Greedy Layer-Wise Pretraining [Convolutional Neural Networks]

I am trying to implement greedy layer-wise pretraining for Convolutional Neural Network binary classifier using AutoEncoders. However, I am a little bit confused regarding the logic of implementation. ...
0
votes
0answers
17 views

Using flow_from_dataframe with multiple inputs

I was wondering if it is possible to use the flow_from_dataframe on Keras with multiple inputs. I have a Dataframe with 3 ...
0
votes
1answer
28 views

How do we know a neural network test accuracy is good enough when results vary with different runs?

In every paper I read about prediction models, the training accuracy and the test accuracy (sometimes also the validation accuracy) is stated as a discrete number. However, in experience, depending on ...
2
votes
1answer
40 views

“Change the features of a CNN into a grid to fed into RNN Encoder?” What is meant by that?

So in the paper for OCR pr LaTex formula extraction from image What You Get Is What You See: A Visual Markup Decompiler, they pass the features of the CNN into RNN Encoder. But there is problem that ...
0
votes
1answer
16 views

Does training of neural networks follow the same order in each epoch?

Each epoch uses the weight from the end of the previous epoch(correct me if I am wrong). Is the updating of parameters after each batch always in the same order? To rephrase, are the batches always in ...
1
vote
1answer
30 views

Binary classification using images and an external dataset

I currently have a project in which I must create a binary classifier to detect defective products. I have image data which has already been labeled (each part has been labeled as a pass or fail), as ...
0
votes
1answer
45 views

How to grid search feature selection and neural network hyperparameters in the same grid?

I'm using the GridSearchCV () class from scikit to perform hyperparameter optimization in a sequential neural network. I've built a pipeline to also find the best ...
1
vote
1answer
32 views

When does Adam update its weights?

I have a dataset with at least 70% of labels incorrect. I'd expect that incorrect labels would compensate each other while true labels will be taught properly (given a very large dataset). For example,...
0
votes
0answers
19 views

How to use AutoEncoders or VAE for initializing custom CNN architecture?

I would like to use AutoEncoder or VAE in order to learn set of features which I can use to initialize training procedure of a custom CNN architecture that I've build. Here is the code: ...
-1
votes
1answer
10 views

Does YOLO give preference to color over shape or vice-versa while detecting an object?

If you train your YOLO model only on grayscale images to detect car, then would it able to recognise a car in a colored image also. If so, then can I assume that YOLO consider only object shape not ...
-1
votes
1answer
21 views

How can I predict the true label for data with incomplete features based on the model learned by data with complete features? [closed]

for example, the model was learned by training data with complete features (f1,f2,f3,f4,f5,f6) but, I wonder the model can test data with incomplete features (f1,f2,f3) to attach true label into these ...
0
votes
0answers
10 views

How to create a Question bank out of several Question papers?

I have many questions papers. I want to extract all the questions out of them so as to create a question bank. The issue is that all the question papers are not in the same format. I tried using ...
0
votes
1answer
23 views

Which is the best method for Neural Network Layers in Keras [closed]

In keras we can create neural network layers in many ways. 1. Sequential API. for example model=sequential() 2. Functional for example ...
1
vote
0answers
28 views

Accuracy gain vs amount of data in Neural Networks

There's a theoretical question I tackled upon in the excellent book Neural Networks and Deep Learning by Michael Nielsen, which I would love to discuss about. The ...
0
votes
0answers
32 views

1D convolutional neural network validation improvement

I created 1D CNN in Keras, but I'm having issues with validation loss and accuracy. I have 24k records, 22 features. Is my model overfitting or what is going on so validation loss and accuracy is ...
2
votes
1answer
23 views

Is providing class weight to neural network enough for imbalanced binary classification?

I have a highly imbalanced binary classification problem, probably 95:5 for two classes. I don't want to perform resampling as the data is already huge and training it would just take more time. (I'm ...
1
vote
1answer
24 views

Augmenting the validation set in Ensemble Model

I have 8 models which I have trained on 90% of my set (training set) and tracked its performance on the loss of the validation set (10% of the original set). I want to generate an ensemble model by ...
0
votes
1answer
23 views

Deep Q-learning, how to set q-value of non-selected actions?

I am learning Deep Q-learning by applying it to a real world problem. I have been through some tutorials and papers available online but I counldn't figure out the solution for the following problem ...
0
votes
0answers
13 views

Are the equations following equations derived for the delta of weights in back propagation correct?

Specifically, I am wondering about summing the partial derivative of error in relation to the previous node's output for all superseding layers. My network is a 4 layer feed forward network; layer one ...
1
vote
1answer
24 views

Learning the uncertainty of a ML algorithm

I have a regression GAM (General Additive Model) and I want to learn its epistemic uncertainty( the variance of my residuals or predictions as a function of my input). I have already used a bayesian ...
0
votes
0answers
8 views

Can I predict different size of test image on my trained Unet model

I have one image,where top left corner of the image (784,448,3) is used for test image and remaining area is used for training where overlapping patches of size (112,112,3). I have trained my Unet ...
1
vote
1answer
27 views

The difference between data science and algorithm development

I see a lot of job opportunities in the field of data science but I'm not sure the difference between a data scientist and deep learning algorithm developer. Can someone explain that to me?
0
votes
0answers
23 views

Is it logical to get this result from LSTM time series forcasting?

I was training my LSTM for time series prediction and my script is: ...

1
2 3 4 5
66