Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

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 sorts of Probabilistic Graphical Models.

0
votes
0answers
11 views

Data Representation for sequential input NN

The essence of the problem I want to model is to go from input sequences(length n) to a "distance matrix"(nxn). Although for this distance matrix we are not actually predicting $n^2$ values because it ...
0
votes
0answers
6 views

Approach fpr extracting/cropping features images using deeplearning and no annotations

Let's say I want to have a bunch of images of hats from videos. How would I priniciple build something that would learn to recognize, and crop or bound box hats? I heard you need a dataset with ...
1
vote
0answers
14 views

Moroccan License Plate Recognition (LPR) using OpenCV and Tesseract

I'm working on a project about recognizing moroccan license plates which look like this image : Moroccan License Plate Please how can I use OpenCV to cut the license plate out and Tesseract to read ...
0
votes
0answers
5 views

How can I find a large dataset of medical images for cancer classification [migrated]

I am looking for a large image dataset >20K to be used for cancer classification algorithm. Where can I look given that all public available datasets are maximum 1K in size which is much less than ...
1
vote
0answers
11 views

Reasons why training error can go up after more training?

In the context of deep-learning, I understand why the test or validation error can go up with more training: this is the result of overfitting. I also can think of one reason why even the training ...
2
votes
1answer
22 views

Multivariate Time Series Binary Classification

I have continuous (time series) data. This data is multivariate. Each feature can be represented as time series (they are all calculated on daily basis). Here is an example. ...
2
votes
0answers
25 views

Comparison between addition and multiplication function in deep neural network? [on hold]

I designed a specific Convolution Neural Network to study in the area of image processing. The network has a part that there are two tensors which have to be transformed into a tensor in order to be ...
1
vote
0answers
8 views

What is the interpretation of the expectation notation in the GAN formulation?

I'm confused about the expectation notation in the context of GAN loss functions. The GAN loss for the discriminator is binary cross-entropy. ie: is this real or not. real = $D(x)$ (ie: give ...
1
vote
0answers
24 views

Deeplearning without an objective function?

In this article, the author talks about how deeplearning models no longer are trained for an objective function that humans specify, but find their own objective function. Specifically, he is talking ...
0
votes
0answers
8 views

Deep Learning Book Manifold Learning Example need to be explained

I was learning neural network using the book "Deep Learning" by Ian Goodfellow, Yoshua Bengio and Aaron Courville.I section 14.6 the author makes an example of figure 14.6 and it says: Blockquote ...
0
votes
1answer
6 views

Sequence to sequence RNN model, maximum number of training size

So when running this example script from Keras repo (https://github.com/keras-team/keras/blob/master/examples/lstm_seq2seq.py), I found that we can easily run into out of memory for the input or ...
1
vote
0answers
14 views

Lidar Data augmentation

I am working on Object Segmentation using Lidar 3D point clouds, basically using Kitti dataset. However, the dataset is imbalanced for classes cyclists and pedestrians. So, I am looking for ways to <...
0
votes
0answers
10 views

LSTM Multi-state forecast

I follow several tutorials about LSTM multi-step forecast to solve my problem. My problem: I have a time series of price about 3 months (Jan 2018 to Mar 2018) and I assume there are seasonal. So, my ...
1
vote
0answers
7 views

ArcFace loss in siamese architecture?

Can anyone please help me implement arcface loss function in siamese architecture for face recognition problem?
1
vote
0answers
12 views

Training regression LTSM model with features having more than one value per time

Dataset of amount of #Alarms, on weekly basis, there are 37 weeks. The feature data set connected to the each week, have more than one value. ...
1
vote
0answers
18 views

Tool For Multi-Label Image Classification

I am currently working on a project that requires multi-label image classification. The best way to achieve this seems to be through Binary Relevance. I was intending to use a convolutional neural ...
1
vote
0answers
14 views

How to use Zero-Shot Learning on text?

Zero-shot learning used to predict the unseen classes using the attributes for each image. For example, we feed the model pictures of horses and pandas. The model will learn how horses look like and ...
2
votes
0answers
17 views

Time Series Forecasting RNN: Masking Values

Suppose you have missing values in a time series E.g. : t1 x1 y1 t2 ? ? t3 x3 y3 t4 ? ? t5 x5 y5 You are trying to forecast this time series using a recurrent ...
1
vote
0answers
32 views

Tensorflow Deep learning network not utilizing GPU?

I have a Nvidia GeForce GT 755M (PC), which I heard should be at least functional for running deep learning models. But when I train my model (DCGAN) and check the task manager process info (Win 10) I ...
0
votes
1answer
15 views

Is there any text similarity databse available for phrases?

I want to train my application for phrase similarity. I want my model to predict similarity score for phrases as shown in below examples. ex- ...
0
votes
0answers
11 views

can we use deep learning in Microsoft bot framework

I am aware of several bot frameworks like google's dialog-flow, microsoft bot framework and etc., from whatever i read so far, i see that these are retrieval based chatbots. I am wondering if we can ...
3
votes
1answer
19 views

What's the correct reasoning behind solving the vanishing/exploding gradient problem in deep neural networks.?

I have read several blog posts where the solution to solve the vanishing/exploding gradient problem in a deep neural network is suggested to be using Relu activation function instead of tanH & ...
3
votes
1answer
25 views

How large of a value should a weight have in a neural network?

If you're assigning random values to the weights in a neural network before back-propagation, is there a certain maximum or minimum value for each weight ( for example, 0 < w < 1000 ) or can ...
1
vote
2answers
35 views

What does the “Loss” value given by Keras mean?

I setup my neural net to use mean square error as shown below. To my understanding (and from reading the documentation) this means that if the correct result of a row is 0.7 and the net predicts 0.8 ...
2
votes
1answer
26 views

Calculating saliency maps for text classification

I'm following the text classification with movie reviews TensorFlow tutorial, and wanted to extend the project by looking, for a certain input, which words influenced the classification the most. I ...
0
votes
0answers
12 views

Long range dependency dataset

I am doing a project concerning formal languages and I want to relate them to DL structures. In this regard, I am looking for datasets that include enough long-range dependency for the use of ...
0
votes
0answers
13 views

Can we do convolutions on binary mask inputs?

I am training a vehicle trajectory prediction algorithm using Deep MaxEnt Inverse Reinforcement Learning (https://arxiv.org/abs/1507.04888). My intention is to have as input to this algorithm a top-...
1
vote
1answer
17 views

Can I use the Softmax function with a binary classification in deep learning?

I want to create a deep learning model (CNN) for binary classification, can I used the softmax function instead of the sigmoid function in binary classification? Adding the classification layer to ...
1
vote
1answer
21 views

Perceptron Learning Rule

I am new to Machine Learning and Data Science. By spending some time online, I was able to understand the perceptron learning rule fairly well. But I am still clueless about how to apply it to a set ...
2
votes
0answers
11 views

Video Classification frame rates [closed]

I am building a Deep learning model for vibration, I have video inputs and I want to analyze this video for vibrations and categories these vibrations into various classes of vibrations, what ...
4
votes
3answers
79 views

How to get accuracy, F1, precision and recall, for a keras model?

I want to compute the precision, recall and F1-score for my binary KerasClassifier model, but don't find any solution. Here's my actual code: ...
0
votes
1answer
22 views

Is it possible to decode which neuron represent which feature and why does it represent it?

In a neural network, Each neuron in the network represents some part of non-linear feature of the input. Ex: Like in mnist data, Consider the stem of number 9 is cut into multiple pieces and different ...
1
vote
0answers
14 views

Dealing with Error in Neural Network input

When you are building a neural network in which the input values are known to have error is there a way to incorporate this into the network? I.e one value of the input features may have a known small ...
0
votes
0answers
10 views

Implementation of Siamese network

What would be the ideal ratio of positive, negative image pairs, and the number of image pairs to classify if two images are of same person in Siamese network ?
0
votes
0answers
15 views

How does single image normalization help face recognition model training?

I knew why/how batch image normalization help model training,but How does single image normalization help face recognition model training?
1
vote
0answers
22 views

How to choose best model checkpoint when training deep learning model on all the data?

When training a final model for production, it's often recommended to train on all available data (train + dev + test), as discussed here. I'm training a deep learning model. I typically save and use ...
0
votes
0answers
17 views

The Question is about Deep Learning how to skip intro in movies

I want to skip the introduction and post credit scenes (such as..,Namecard scenes )in movies using deep learning.How do do it by using Tensorflow object detection api. Is it possible to do that using ...
0
votes
0answers
9 views

Extract weight matrix of Convolutional Neural Network in MATLAB

I try to train Convolutional Neural Network via MATLAB and want to know the weight matrix and bias vector in each layer. The network works well but when I type "layer(2).Weights" it returns "[ ]". ...
1
vote
1answer
26 views

Why do most GAN (Generative Adversarial Network) implementations have symmetric discriminator and generator architectures?

For example, if the discriminator is a vanilla network of n layers, each with n(i) units, then, typically, the generator will also be a vanilla network of n layers, each with n(n-i) units (except the ...
0
votes
1answer
21 views

What does the below phrase in the lstm blog mean? - Data Science

I am a newbie to data science. I was reading this blog When I was half way through, I came into this sentence Further, each series of data has been partitioned into overlapping windows of 2.56 ...
1
vote
0answers
56 views

Changing padding values in Keras

What is the influence of changing the padding value with its borders, I might miss vocabulary because I can't find many papers about this alternative. Also I'd be interested in doing this in Keras, ...
3
votes
0answers
70 views

Solving an ODE using neural networks (via Tensorflow)

I'm very new to deep learning (coming from a math PDE background), but I'm trying to solve some ODEs using a neural network (via tensorflow). I've solved some simple ones like $u'(x)+u(x) = f(x)$ with ...
1
vote
1answer
15 views

Predicting of the function values

There is a function: $f(t,x,y,z)$, where $t$- time, $x,y,z$- some arguments. The values of $f$ for $t\in [a,b]$ are known (100 samples). What is the most accurate way of predicting the value of $f$ ...
-1
votes
0answers
14 views

Real data passes as input to discriminator (GANs)

As I was following the GANs for my project and came across that real data and the fake data that is generated by the generator are fed into the discriminator. What's the purpose of the real data that ...
2
votes
1answer
29 views

NLP text autoencoder that generates text in poetic meter

I would like to create an NLP autoencoder that happens to only generate text that conforms to a poetic meter, for example 'iambic pentameter'. That is, the output should be a series of clauses which ...
0
votes
0answers
6 views

What is a “mean-field reconstruction” in contrastive divergence learning?

I am reading the following paper: An Efficient Learning Procedure for Deep Boltzmann Machines by Salakhutdinov and Hinton. In Algorithm 3, page 1987, there is a term which is "contrastive divergence ...
0
votes
0answers
16 views

LeNet-5 - combining feature maps in C3 layer

Famous LeNet-5 architecture looks like this: The output of layer S2 has dimension: 10x10x6 - so basically an image with 6 convultions applied to it to derive features. If each dimension was again ...
0
votes
0answers
13 views

How to combine audio and video features to be used in video captioning?

I am currently working on implementation of video captioning task and i need to combine video and audio features, i used ResNet model to extract video features and another model to extract audio ...
0
votes
0answers
17 views

Identify specify areas in the text

I'd be interested in identifying various areas in the text message. Let's say I have a text containing some introduction, then there is a poem and at the end there are some urls to some web pages. I'...
0
votes
0answers
13 views

How to use SLAM on other sensor other than camera?

I have a sensor that reads electromagnetic field strength from each position. And the field is stable and unique for each position. So the reading is simply a function of the position like this: <...