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
1answer
216 views

while re-training a pre-trained model, I'm facing this issue RuntimeError: You must compile your model before using it

model summary: RuntimeError: You must compile your model before using it. It says that the model needs to be compiled. But as far i know, if i compile a model, all the previous trained data will be ...
0
votes
2answers
242 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
1answer
55 views

Basis expansion for regression using neural network?

I am trying to approximate a nonlinear function using a neural network. There are 3-4 input units. The network is struggling a bit to generalize the function outside the vicinity of the training data ...
0
votes
0answers
7 views

How to use Mean squared error as the loss function on CIFAR 10

I have tried using MSE on Resnet50 for the CIFAR10, no matter how I change the output layer like dense(1, relu)/dense(1, sigmoid). The model failed to converge in the training. What is the correct way ...
1
vote
1answer
63 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, ...
0
votes
0answers
6 views

Train LSTM model with similar cyclic sequence

I am using keras LSTM to predict a seq2seq of 2 variables. I have test results for 50 subjects with ±20 tests per subject. the data is a 2 variable sequence with shape (101,2). as you can see, the ...
1
vote
0answers
17 views

Why is val accuracy 100% within 2 epochs and incorrectly predicting new images? (1,000 images per class when training)

My CNN tensorflow model reports 100% validation accuracy within 2 epochs. But it incorrectly predicts on single new images. (It is multiclass problem. I have 3 classes). How to resolve this? Can you ...
1
vote
1answer
366 views

Why is IoU said to be non-differentiable?

I have been trying to find an answer online but I couldn't really find one. If anyone could help me I would appreciate it
0
votes
0answers
10 views

Regressing over tiny floats with Neural Networks

I am trying to regress over very small floats - of the magnitude [1e-2, 9e-3]. They're mostly in this range. Using simple ...
5
votes
0answers
1k views

Fine tuning accuracy lower than Raw Transfer Learning Accuracy

I've used transfer learning on Inception V3 with ImageNet weights on Keras with Tensorflow backend on python 2.7 to create an image classifier. I first extracted and saved the bottleneck features from ...
5
votes
0answers
137 views

How to predict advantage value in deep reinforcement learning

I'm currently working on a collection of reinforcement algorithms: https://github.com/lhk/rl_gym For deep q-learning, you need to calculate the q-values that should be predicted by your network. There ...
3
votes
1answer
63 views

What Models should i try for this problem?

I need some advice for a problem i'm working on with automobile data. The vehicles provide a series of codes at every second which are bieng stored, though it can vary how many. For example , at time ...
2
votes
1answer
127 views

Understanding the text from the paper 'Efficient BackProp' by Yann LeCun

Sorry, I just started in Deep Learning, so I am trying my best not to assume anything unless I am absolutely sure. Going through comments here someone recommended this excellent paper on ...
3
votes
3answers
4k views

What is the best way to read SQL dataset in to Tensorflow?

What is the best way to read SQL database in to Tensorflow? Currently, I am using Postgres on server and developed DL algorithm on Tensorflow using Jupyter Lab. How can I import data into Jupyter Lab ...
1
vote
1answer
568 views

Combining image and scalar inputs into a neural network

I'm looking at the best way of combining CNN with image input and a scalar value. I know that one of the ways is to concatenate flatten layer with this scalar value. But flatten layer consist for ...
2
votes
2answers
130 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 ...
1
vote
0answers
22 views

RNN/LSTM architecture for mapping one input variable to three output variables per timestep

I am trying to make a regressor that maps an timeseries with one input variable per timestep to 3 output variables per timestep. I am doing this to be able to predict the three output-variables in a ...
7
votes
2answers
131 views

Why deep learning models still use RELU instead of SELU, as their activation function?

I am a trying to understand the SELU activation function and I was wondering why deep learning practitioners keep using RELU, with all its issues, instead of SELU, which enables a neural network to ...
1
vote
1answer
660 views

Validation loss keeps fluctuating about training loss

I am training a Keras model for multi-target regression by using a custom loss function with the goal of getting predictions accurate to below 0.01 with respect to ...
1
vote
1answer
56 views

Best practices to modelize top layers over CNN

I'm fine-tuning a InceptionResnetv2 network to get a features extractor, so I'm training a classical classifier with my data (one label/data, i'm using a softmax). I would like to know how to choose ...
4
votes
1answer
45 views

Why is a general/original softmax loss not preferred in FR (face recognition)?

In some papers I've read that softmax loss is not preferred in FR since it does not give a good inter-class and intra-class margins, but could not understand 'why?'. So can someone explain, why ...
2
votes
1answer
140 views

Reinforcement Learning on real time data over a web server

Question: is it possible to implement a reinforcement learning model over a NodeJS server? This server would be receiving binary forms of data (open /close; yes/no) in real time. The objective for ...
3
votes
1answer
62 views

Train ML algorithm to find edges

I have input RGB images as follows: I have a dataset of manually annotated images highlighting the outline(edges) from the input images I am attaching an example. My aim is to train a ML algorithm ...
1
vote
0answers
9 views

Looking for multi output image datasets

I'm looking for image datasets that have multiple labels. So far I could only find one dataset of age, sex and ethnicity prediction but I'm looking for something a little less known than that one. ...
2
votes
1answer
266 views

How to get same accuracy with identical models in Keras and Tensorflow?

As we all know Keras backend uses Tensorflow and so it should give out some kind of results when we provide the same parameters, hyper-parameters, weights, and biases initialization at each layer, but ...
1
vote
0answers
4 views

How to define a graph in GNN? [closed]

I am new to graph neural network (GNN). Without knowing a graph in advance, how can we possibly form an adjacency matrix? Assume there are 3 nodes (vertices): A, B, & C. There are could be many ...
1
vote
2answers
448 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 ...
1
vote
1answer
1k views

LSTM-Model - Validation Accuracy is not changing

I am working on classification problem, My input data is labels and output expected data is labels I have made X, Y pairs by shifting the X and Y is changed to the categorical value ...
1
vote
1answer
16 views

spot/stain growth in image classification problems

I am working on a problem with images where we are monitoring development of spot in certain region of image. We are able to classify spot present(NOK) or not present(OK) successfully if initially ...
0
votes
0answers
17 views

Siamese netwroks - how to choose loss function?

I have read several articles about siamese netwroks, and I understand that there are 3 different types of loss functions: ...
1
vote
1answer
27 views

Points to remember when embarking on an organization-wide turn to AI solutions

In our organization, we are currently in the phase of building up team, skills to automate and implement AI based solutions. So, we are very early in this AI journey. Right now, we are also working on ...
0
votes
2answers
34 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
1answer
291 views

Loading a model with attention layer and custom metric

I have a neural network with SeqSelfAttention (https://pypi.org/project/keras-self-attention/). Also I implemented a custom metric for F1. Then I saved the model without problems, but when the model ...
1
vote
2answers
230 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 ...
0
votes
0answers
24 views

Fake News Detection Classifier approach

I have the dataset related to any domain like sports, entertainment, politics, etc. I just want to know that the approach I am using for fake news detection is valid or not. As I do not want to use ...
68
votes
7answers
130k views

Cross-entropy loss explanation

Suppose I build a neural network for classification. The last layer is a dense layer with Softmax activation. I have five different classes to classify. Suppose for a single training example, the <...
1
vote
0answers
16 views

Difference between the architectures of semantic and instance segmentation

My question is about the difference between the architectures of semantic segmentation and instance segmentation models. So, as far as I understand, a semantic segmentation model is making pixel-wise ...
0
votes
1answer
30 views

Storing masks in jpg format

I've created masks(numpy array with 0,1 as values) and tried exporting this array to jpg using matplolib but it's not exporting the values as it is. I'm getting a range of pixel values in resulting ...
0
votes
2answers
41 views

Is reinforcement learning analogous to stochastic gradient descent?

Not in a strict mathematical formulation sense but, would there be there any key overlapping principals for the two optimisation approaches? For example, how does $$\{x_i, y_i, \mathrm{grad}_i \}$$ (...
1
vote
1answer
55 views

How to find Neural Network ZOOs?

I have heard about the term Neural Network ZOOs, which are supposed to be repositories where there are a lot of pre-trained neural network models for many different applications, but I'm struggling to ...
3
votes
4answers
143 views

Why are deep learning models unstable compare to machine learning models?

I would like to understand why deep learning models are so unstable. Suppose I use the same dataset to train a machine learning model multiple times (for example logistic regression) and a deep ...
1
vote
2answers
969 views
+50

Machine learning algorithm for Low dimension input to high dimension output

I am plaining on training a network for body generation, i.e. given some specific measurement,(5 features) the output will be the a set of vertices representing the obj of the bodies. I am wondering ...
0
votes
0answers
26 views

Important features for detecting malware on the network

I am trying to build a model (Machine Learning) in order to detect malicious network traffic. At first, I am trying classify network traffic as malware or benign. After predicting the malware part, I ...
1
vote
1answer
54 views

which Model to apply on panel data where unique id has 6-8 records and total records are 2,000,000?

I am new to such panel data where I have multiple observation for same ID in different Quarter and I am not sure what kind of machine learning algorithm I can apply. I have data from Q1-18 till Q4-...
0
votes
0answers
28 views

What ML model to train on when using an adaptive learning rate - the most recent or the one with the least validation loss?

I am currently implementing an adaptive learning rate for a neural network, meaning the learning rate gets reduced (e.g., halves) every time the validation error plateaus for 3 epochs (exemplary, ...
1
vote
1answer
35 views

How to decrease LSTM RMSE?

I am using an LSTM model to predict the next measurement of a sensor. The dataset looks as follows: There are approximately 13000 measurements. My code for the LSTM looks as follows: ...
0
votes
0answers
10 views

How can I reduce overfitting in CNN model for image classification, even after data augmentation?

its my first time posting here. I'm trying to build a CNN model that identifies fruits from a dataset of apples, bananas, mixed fruits, and oranges. So far, one of the things I have done to prevent ...
0
votes
3answers
102 views

Can this problem be solved using deep learning?

I want to predict price of used cars. I have data like this: Is this problem suitable for deeplearning or Should I use XGBOOST, RandomForest etc.? I used one hot approach for nominal features and ...
0
votes
1answer
19 views

Logarithmic scale for a learning curve [closed]

I'm plotting the learning curve with Python with the following code: ...

1
2 3 4 5
84