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
2 answers
1k views

What are the “training error” and “test error” used in deep learning papers?

I have heard of the terms "training" and "test error" in the context of classification quite often, but I am not sure I know what they mean. This article writes: Training Error: ...
0 votes
1 answer
58 views

Neural Network does not learn regression

I have the following setup: 2 input neurons (I1, I2) 2 output neurons (O1, O2) 1 hidden layer with 3 neurons (H1, H2, H3) loss function = mse optimizer = Adam the values from I1 range from 0 - 100 ...
1 vote
2 answers
645 views

Using categorical and continuous variables in Deep Learning

I would like to apply a MLP to some business seller data. I found that the data is a mix of both categorical and continuous features. For what I read it is not advisable to feed a neural network with ...
0 votes
1 answer
309 views

How to find the class name of a new image from the pre-trained model

I would just like to get the class names of the predictions. I can get the class names on the images that I trained the model. But if I predict an image (say which is not trained but already belongs ...
0 votes
1 answer
78 views

How to choose architecture of neural network for concrete task?

How to systematically choose the architecture of a neural network (NN) for a concrete task? For example, I am solving classification task with 3 classes (NN should recognize pandas, dogs and cats). ...
0 votes
1 answer
110 views

When will the mlp give constant prediction?

I have a regression task (to predict price for finanical market.) I build a mlp to do the regression. I found mlp will stop at giving a constant prediction, which i think it's useless. Does this mean, ...
1 vote
1 answer
338 views

Can LSTM be used for non time series data?

I have a dataset - This is a TOR network traffic dataset with labels added as TOR/ Non TOR. I want to run an LSTM on it and classify it as Tor/Non Tor. Is that possible since this is not a time ...
0 votes
1 answer
148 views

What is the best way of combining audio and visual data to make predictions?

I am trying to predict the probability of a disease by using audio and images, the audio and the images do not come from the same source. I am thinking of combining the outputs (maybe average them) of ...
0 votes
1 answer
583 views

Embedding layer before LSTM layer

I am toying around with a clustering and churn prediction framework, cluschurn which they deployed in production at Snap, Inc. In their research paper, paper_link, they use 14 days of user data and ...
0 votes
0 answers
4 views

What is effect of having more edges on a GCN helps learning?

I am using a Graph2Seq GNN. For my case, I am using GCN as my encoder. For my graph, on the average: I have around 500 nodes in the graph per data point. In the current graph, on average, a node is ...
1 vote
1 answer
354 views

Is it possible to train for precision in Tensorflow?

Can I train a binary classifier in Tensorflow to maximize precision?
3 votes
1 answer
218 views

Why KL Divergence instead of Cross-entropy in VAE

I understand how KL divergence provides us with a measure of how one probability distribution is different from a second, reference probability distribution. But why are they particularly used (...
4 votes
3 answers
8k views

How many parameters in a Conv2d Layer?

I was following andrew-ng coursera course on deep learning and there's a question that has been asked there which I couldn't figure out the answer for? Suppose your input is a 300 by 300 color (RGB) ...
0 votes
2 answers
563 views

Why there is Different accuracy for two same trained model?

Trained the same model twice with the same dataset, the same parameters (Epochs, Batch Size, Learning rate, etc..). But both trained model shows different train as well as test accuracy on the same ...
1 vote
1 answer
54 views

What is feat_dynamic_real, feat_static_cat and feat_static_real in gluonTS models?

What is feat_dynamic_real, feat_static_cat and feat_static_real in gluonTS models? When do we use these features while running the model? Can someone provide an example for the same?
2 votes
1 answer
303 views

Comparison between approaches for timeseries anomaly detection

After various days of research, I could take a global picture of the existing methods to perform anomaly detection on time series, namely: Forecasting with Deep Learning. Eg. RADM or LSTM model ...
2 votes
1 answer
1k views

While retraining a pretrained model, getting: ValueError: Input 0 is incompatible with layer flatten_1: expected min_ndim=3, found ndim=2

My model summary is: ...
0 votes
0 answers
4 views

Does Field of View in Camera affects the performance of Keypoint detection and semantic segmentation model?

I have two cameras to capture images for training keypoint detection and semantic segmentation model. One camera has smaller field of view and the other has larger field of view. Let's say, I capture ...
0 votes
1 answer
50 views
+250

Predict parallel time intervals

I have the following problem. There is a service station that can provide service for a number of vehicles at the same time. The service data looks like this: ...
1 vote
1 answer
64 views

Neural net that takes sets as inputs

I'm interested in a neural net that takes a complete set as an input. For example: the net takes as an input a set of m 1-dimensional points and predicts a histogram of this set (e.g. as a vector ...
2 votes
1 answer
107 views

How to approach different image resolutions in deep learning for regression problem?

I have an image dataset of various resolutions and using regression DNN model with fixed n*n input resolution. As model learns certain positions in the image, I've been using zero padding to fit ...
2 votes
1 answer
2k views

How to resize MNIST images to fit AlexNet model

I am using the keras API to load in the MNIST dataset. My problem is I need to use AlexNet as my algorithm. Understanding the AlexNet model, I require to start with 277x277 images but the MINST ...
1 vote
4 answers
2k views

Time series analysis vs linear regression

I am working on developing an algorithm which will predict the future traffic for the restaurant. I am confuse that which of the two: Linear regression or time series analysis I should use as the base ...
2 votes
2 answers
369 views

How to interpreter Binary Cross Entropy loss function?

I saw some examples of Autoencoders (on images) which use sigmoid as output layer and BinaryCrossentropy as loss function. The ...
35 votes
3 answers
28k views

What does Logits in machine learning mean?

"One common mistake that I would make is adding a non-linearity to my logits output." What does the term "logit" means here or what does it represent ?
0 votes
1 answer
13 views

How to build correct dataset for ann classifier?

I have x signals each with 5000 rows. Each signal x has its own one output in range from 1 to 6 (categories). So for example signal x1 has output 2, signal x2 has output 1 ... How can I build X and Y ...
0 votes
1 answer
135 views

How is the hidden state of a GRU initialized

This is a GRU. Now, what will be the value of $h_t$, at $t$=$0$. That is, what will be the value of the hidden state at just the starting?
0 votes
0 answers
14 views

Machine/Deep learning model for object labeling in Check Images?

I am currently facing an issue with identifying sections within a check images, something like object identification. Initially it seemed I could use YOLOv5, because it is good with object detection. ...
1 vote
1 answer
172 views

Handling a large dataset consisting of npy files

I have a high number of npy files (448 files) each consisting of around 12k frames (150x150 RGB images) which together make the input to my neural network (X). However, since it is impossible to load ...
5 votes
2 answers
13k views

What can be the cause of a sudden explosion in the loss when training a CNN (Deeplab)

I am training the following deeplab CNN: https://github.com/tensorflow/models/tree/master/research/deeplab During training I see the following loss: The first 50k steps of the training the loss is ...
1 vote
2 answers
115 views

Use distribution probability as a feature in ML model

I built an LSMT model to predict sick cows. I also have risk factors like cow size and height (static risk factor) that I want to combine into the ML model. I found that size is geometrically ...
1 vote
1 answer
68 views

computer science student - asking for some machine learning guiding (voice cloning)

I have chosen my synopsis topic for my second last semester. I want to make a text-to-speech program, that speaks with the voice of a game character. I have worked with machine learning in my class, ...
3 votes
1 answer
65 views

How can I know the name of the features selected by a Deep Belief Network?

I want to use DBN to reduce the 41 features of nslkdd dataset after transforming nominal data to numeric the number of features increases from 41 to 121 . I used 3 RBMs (121-50-10) now I want to know ...
0 votes
0 answers
9 views

How to debug a neural network

After training wide& deep model for recommendation, weights of final layer becomes 0 leading to score of 0 for all inputs. I would like to know why this is happening and try weight initialization, ...
1 vote
1 answer
49 views

DL model to assess quality of image

I have an idea but I am not certain that it can be modeled in a DL architecture. Let's say we have images of different qualities based on color patterns and their assessment as labels in a range from ...
1 vote
2 answers
268 views

Can siamese model trained with euclidean distance as distance metric use cosine similarity during inference?

If I have 3 embeddings Anchor, Positive, Negative from a Siamese model trained with Euclidean distance as distance metric for triplet loss. During inference can ...
2 votes
1 answer
2k views

how to use multiple generator in keras fit_generator()

I want to train the multi-input model on a set of images. I use ImageDataGenerator.flow_from_directory() and fit_generator in ...
0 votes
0 answers
24 views

What does the learning curve indicate?

I am training a deep learning model for traffic prediction. When I use 10 months of data for training (validation split: 10%) and 2 months for testing. The loss curve looks like this: . and the ...
0 votes
1 answer
23 views

Advice for Deep Learning on a laptop without a dedicated GPU

My laptop has a 16gb ram, ryzen 7 processor, ssd etc. But it doesn't have an nvidia gpu. It is said that one can train models on the cloud but for 'inference' the physical laptop should have at least ...
5 votes
1 answer
3k views

Gradient flow through concatenation operation

I need help in understanding the gradient flow through a concatenation operation. I'm implementing a network (mostly a CNN) which has a concatenation operation (in pytorch). The network is defined ...
2 votes
1 answer
3k views

What is the difference between shuffle in fit_generator and shuffle in flow_from_directory?

I am using Keras to create a deep learning model and I would like to know that what is the difference between shuffle argument in ...
0 votes
0 answers
4 views

Bending Training Loss, what could be the cause?

Hello, during training of one of my models, I observe the following training (blue) and test (orange) loss patterns. At first, the training loss increases, then bends and starts decreasing. Just ...
0 votes
0 answers
10 views

How to do a batch trainning of Pytorch model without using Dataloader?

I am doing a time series data training. I have to pad 0s to the data so the sequences have the same length. Because of 0s are padded, I have to mask them during the training, for Keras, it is simply ...
1 vote
1 answer
70 views

Error when checking target: dimensions error in CNN-LSTM model for multivariate time series forecasting

I'm making a CNN-LSTM model to forecast multivariate time series: ...
1 vote
1 answer
13 views

Certain Image Augmentation Prevent Unet Model from Learning

I am training a Unet model for cell image segmentation from microscopy images. In order to help the model generalize better to different microscopes, I attempted to apply brightness augmentation to ...
2 votes
2 answers
464 views

Suggestions for guided NLP online courses - Beginner 101

I would like to know from the data science community here for suggestions on nlp courses. I am new to NLP area and would like to take up a course which covers from basic to advanced concepts such as ...
0 votes
2 answers
51 views

feature normalisation problem

I am very new to ML and have limited knowledge about it. I am having issue in feature normalization process. I have understood from the post that we need to normalize the training features and scale ...
0 votes
0 answers
6 views

How to evaluate reliably a model using fastai

I’m new to fastai and don’t quite well grab some concepts. There are some questions I have : When using fit_one_cycle, a result table is obtained at the end. How is the error_rate in this case ...
1 vote
2 answers
17 views

Can you use a trained image segmentation model to label more training data for itself?

Labeling images for semantic segmentation can be expensive. Is it viable to train a model (such as Unet) to a good accuracy and then use this model to label more images to be used as further training ...
1 vote
2 answers
247 views

Statistical significance test in deep learning for regression problems

I was reading the tutorial "Statistical Significance Test for comparing ML algorithms", where it suggests to use k-fold and apply the appropriate statistical test. Suppose that I have a train set and ...

1
2 3 4 5
92