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
5 views

Visualization of how K means clustering is used to select K anchor boxes?

I was having trouble understanding how K means clustering is used to select K anchor boxes. We have ground-truth boxes and we run K means clustering on them using IOU as a metric. There is no good ...
0
votes
1answer
12 views

how to get the classe names in an image classifer after predection?

I made an image classifier of 80 classes of handwritten numbers then I tested my model and it worked pretty fine, the only problem that I have now is the display of the correct names of these classes. ...
0
votes
1answer
22 views

Problem when using Autograd with nn.Embedding in Pytorch

I am in trouble with taking derivatives of outputs logits with respect to the inputs input_ids. Here is an example of my input: ...
1
vote
0answers
16 views

If mean absolute loss is not differentiable, how it can be used in neural networks? which majorly are trained using back-propagation

If Mean Absolute Error (MAE) loss is not differentiable, how can it be used in neural networks? which majorly are trained using back-propagation I am wondering if MAE is not differentiable how they ...
1
vote
1answer
21 views

How to approach deep learning CV/Resume parser using Convolutions?

I'm currently looking to invest some time on how to make a resume parser using deep learning. I need some initial ideas (or) approaches on how to put together things at first, where to start. If you ...
1
vote
1answer
13 views

Image classification model only predicting one class

I'm trying to build a deep learning model to predict image classes from the Kaggle competition. I'm using the Xception model as the top layers and then putting the last layer into a dense layer with ...
0
votes
0answers
18 views

Load training data sequentially to avoid memory error

How can I load data of shape: X_train : (4864,6989) X_test : (2085, 6989) y_train : (4864, 270) y_test : (2005, 270) into the memory? I have 16 GB of RAM. What ...
0
votes
1answer
31 views

Binary Classification of a ship Dataset

I want to create a ship detection classifier from a dataset that is formed by 4000 photos(3072*2048).Basically i want to classify the dataset to ship-image and no-ship. I am thinking of 2 solutions- ...
1
vote
1answer
14 views

Convolutional neural network block notation

The paper by He et al. "Deep Residual Learning for Image Recognition" illustrates their residual network in Figure 3 as follows: I am not a neural network expert, so could somebody please explain to ...
-1
votes
2answers
21 views

ValueError: Error when checking input: expected dense_9_input to have 2 dimensions, but got array with shape (60000, 28, 28)

I'm doing a regular detection of numbers from photos with MNIST, but when i try to fit my model, it doesn't work, and it dispayed this message... ...
1
vote
0answers
11 views

Recursive Transfer Learning

Is there any methodology called Recursive Transfer Learning? For example, let's consider a situation that we have a lack of data while training a convolution neural network (CNN) for object detection ...
1
vote
0answers
14 views

LSTM features classification output

I am very new at this, so I might be wrong about my choice of model, but my problem is the following. I am trying to generate music, hence the reason I am using an LSTM. I have the following sequence ...
0
votes
0answers
11 views

Time series regression

I m new in the domain of machine learning. I m here to ask for some elucidation. I have a data set presented as a time series( from a strain sensor coming from a wind turbine). In this time series, ...
0
votes
0answers
12 views

How to deal with discrete variables in Multivariable Time Series forecasting?

I am tackling this time series forecasting problem to basically predict number of sales in the future training dataset looks like this: ...
0
votes
0answers
11 views

Time series problem with LSTM is not predicting correctly

. My Initial dataset looks like this: Text sample of Dataset: ...
0
votes
0answers
6 views

Is data leakage in time series due to both I's of the IID principe or only one?

I am sure that the Independent part of the IID principle gives you data leakage because of the correlation. But the identical part I am not so sure. Identical in time series means that your data is ...
0
votes
0answers
10 views

How can I change the loss function when the shape of my data changes?

Since my data is too large, I use pd.read_csv('',chunksize=). I am using categorical_crossentropy as my loss function, however, ...
0
votes
0answers
8 views

Difference between using BERT as a 'feature extractor' and fine tuning BERT with its layers fixed

I understand that there are two ways of leveraging BERT for some NLP classification task: BERT might perform ‘feature extraction’ and its output is input further to another (classification) model ...
0
votes
0answers
14 views

Further Classification by function [closed]

I am a bit confuse and stuck at a problem, may be someone can guide me in right direction I am doing an analysis and have 3 datasets, supporting, against and neutral, or in simple say negative, ...
0
votes
1answer
11 views

Feature-to-parameter mapping in neural networks

For neural networks, can we tell which parameters are responsible for which features? For example, in an image classification task, each pixel of an image is a feature. Can I somehow find out which ...
6
votes
1answer
195 views

A the end of a big DS project, should I make trained models available on GitHub?

I almost completed two big Data Science personal projects based on Deep Learning. They are the fanciest models I've implemented up to now, and I'm pushing all my code on GitHub. Do you advice to ...
2
votes
1answer
23 views

What is the current best state of the art algorithm for graph embedding of directed weighted graphs for binary classification?

Sorry if this is a newbee question, I'm not an expert in data science, so this is the problem : We have a directed and weighted graph, which higher or lower weight values does not imply the ...
1
vote
1answer
31 views

How to remove background (watermark) logo from image

I have been scratching my head for a while. What I have is a scanned PDF document with text and water marked logo at the back as in the below image. I want to do OCR over this, which becomes very ...
0
votes
0answers
8 views

How can I detect the frame from video streaming that contains the clearest shot of a graffiti on city walls?

I am working on a graffiti detection project. I need to analyze data stream from a camera mounted sideways on a vehicle to identify graffiti on city walls and notify authorities with the single best ...
0
votes
0answers
15 views

LOGICS: GAN with image as input instead of a noise vector

i am having an idea for a single-class classifier. I don't know if this is a logical "short circuit", though. The idea is the following: Instead of a noise vector, i use a "noise-image" as input for ...
0
votes
0answers
11 views

Approximate evaluation for deep learning architecture

When train on big dataset for deep learning architecture, like imagenet, it takes long time to judge whether our new neural network architecture is good, say for image classification. Is there a way ...
-1
votes
0answers
10 views
1
vote
0answers
43 views

Sudden drop of score in the last few episodes

I was following this tutorial about lunar lander and deep Q learning with Tensorflow 2 and I noticed something odd. The problem was actually solved at episode 476 but then the score went from 259.90 ...
1
vote
0answers
11 views

What is the better model architecture and setting when using merge layers?

I am building a deep learning model with dense, dropout, and merge layers. The inputs will be N sentences' feature encoded by BERT (768 dim) and then each will go into the same dense layer as the ...
1
vote
1answer
15 views

Model selection metric for validation phase in deep learning

I have been taught that for each epoch in training, we perform a training phase, and then a validation phase where we decide whether the new set of parameters is better than the current best. This ...
0
votes
1answer
17 views

Train a deep learning model in chunks/sequentially to avoid memory error

How do I train/fit a model in chunks so as to escape the dreaded memory error? ...
2
votes
1answer
20 views

What are machine learning/deep learning models for generating contextually related words and synonyms?

I have a task to work on models for finding synonyms and contextually related words. For example, if I enter: 'car' it should generate -> 'vehicle' 'sun' and 'sea' could generate 'beach', or some ...
0
votes
0answers
14 views

How to find out what each of the layers in NN does?

I have a very simplified view of Neural Networks - you give it input and expected output, and all the rest is a black box. Is it possible to find out, especially in language models, what each layer ...
1
vote
0answers
15 views

How can I know my GAN does converge?

I am training my GAN, and by looking at the loss curves of the generator and discriminator, I think I am going on the right way because from this blog, my curves look reasonable: A stable GAN will ...
-2
votes
1answer
25 views

what is learning rate in neural network?

When I am creating a model using Keras we should define the learning rate(lr) in that optimizer method Please refer to the below code. ...
0
votes
0answers
14 views

Can a convolutional neural network or an autoencoder deal with an input of complex values (complex numbers instead of real numbers)?

I saw in a model that they did consider the complex numbers as 2-D numbers before using Convolutional Neural Networks. However for the autoencoder, as much as i know, it can not deal with 3D, Am i ...
0
votes
0answers
14 views

Index tensor must have same dimensions as input tensor

I am trying to train a DQN to do optimal energy scheduling. Each state comes as a vector of 4 variables (represented by floats) saved in the replay memory as a state tensor, each action is an integer ...
0
votes
1answer
18 views

LSTM loss value not change, accuracy stucked at 50%

I'm using LSTM for time series prediction, my data is highly skewed, with class weight 197.16865807 : 0.50127117 With ...
1
vote
1answer
16 views

Convolution and Pooling as Infinitely strong priors

I am currently reading about Convolutional Neural Networks in Deep Learning Book. I am stuck on section 9.4 titled "Convolution and Pooling as Infinitely String Priors". Could someone please ...
0
votes
1answer
21 views

Conv1D specify output chanels in tensorflow 2.1

Hello I'm trying to implement the "Tacotron Towards end to end" paper and in the Encoder CBHG - a Conv1D bank of K=16, conv-k-128-ReLU “conv-k-c-ReLU” - denotes 1-D ...
1
vote
0answers
28 views

Is the “training loop” used in AlphaGo Zero the same as an “epoch”?

I am confused about the training stage of AlphaGo Zero using the data collected from the selfplay stage. According to an AlphaGo Zero Cheat Sheet I found, the training routine is: Loop from 1 to 1,...
0
votes
0answers
17 views

Flair Custom NER

I'm working on a problem in the domain of NER. I have a dataset wherein I need to have custom tags for different entities. I don't know how to start or even where to start. I know that there are ...
1
vote
0answers
13 views

Are there any existing model weights for buildings segmentation from aerial images?

I'd like to test some deep learning techniques to extract buildings footprint from aerial imagery. I've found many references related to this problem (here, or here), but only providing the model ...
0
votes
0answers
5 views

How to use regularizer in AllenNLP?

Apology if this sounds a bit lame. I am trying to use Allennlp for my NLP tasks and would like to use regularization to reduce overfitting. However from all the online tutorials, all the regularizers ...
1
vote
1answer
23 views

How to code a simple forward propagation of recurrent neural networks?

I know the theory behind recurrent neural networks or RNN but I am confused about its implementation. This is an rnn equation I got from the web, I tried to code the forward propagation alone in ...
0
votes
0answers
34 views

Jupyter Notebook stuck on loading without giving any output

I've recently trained a model which has achieved 99% accuracy on training and 96% on validation data. It is a model which uses images to successfully distinguishes between 120 classes of fruits. I've ...
4
votes
2answers
64 views

Discrimination vs Calibration - Machine Learning Models

I came across a new term called Calibration while reading about prediction models. Can you please help me understand how different it is from ...
0
votes
3answers
28 views

Would it be okay to stop training my neural network?

When the validation error of my Neural Network that I am trying to train is slowly decreasing but not by much, is it okay to stop train the network at that point, or do I need to increase the training ...
2
votes
1answer
17 views

Why encode pitch as one-hot encoding instead of ordinal encoder?

looking at the state-of-the-art publications on deep learning for synthesizing audio one can see that they always resort to encoding pitch as a one-hot vector. I'm curious what the advantage is on ...
1
vote
0answers
14 views

What is regularization in machine learning? [closed]

What is regularization in machine learning? Why do we need this in machine learning?

1
2 3 4 5
60