Questions tagged [deep-learning]

For questions related to deep learning, which refers to a subset of machine learning methods based on artificial neural networks (ANNs) with multiple hidden layers. The adjective deep thus refers to the number of layers of the ANNs. The expression deep learning was apparently introduced (although not in the context of machine learning or ANNs) in 1986 by Rina Dechter in the paper "Learning while searching in constraint-satisfaction-problems".

648 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
1
vote
0answers
736 views

Applying a 1D convolution for 4D input

i'm trying to implement this paper and I'm stuck for quite some time now. Here is the issue: I have a 3D tensor and has (180,200,20) as dimension and I'm trying ...
1
vote
0answers
16 views

Binary annotations on large, heterogenous images

I'm working on a deep learning project and have encountered a problem. The images that I'm using are very large and extremely detailed. They also contain a huge amount of necessary visual information, ...
1
vote
0answers
32 views

Which model to use when selecting objects of interest?

I have a set of polygons for each image. Those polygons consist of four $x$ and $y$ coordinates. For each image, I need to extract the ones of interest. This could be formulated as an Image ...
1
vote
1answer
379 views

Could the normalisation of the inputs make the neural network insensitive to changes in the inputs?

When using neural networks (NNs), we often normalized the inputs. I think this is done to equally capture the changes in any input feature, that is, if any feature takes huge values and other features ...
1
vote
0answers
52 views

How High and Low frequency filters effect activation in the next layer?

Generally, we come across terms such as High Frequency and Low frequency filters in Convolutional Neural Networks (CNN). In regards to this highlighted statement, in 'S1' section of this paper by ...
1
vote
0answers
14 views

Questions regarding rrn-writer by Robin Sloane?

https://github.com/robinsloan/rnn-writer I preface this by saying I do not know much about this topic, only that I have an intense interest in it, so I'm hoping I can make my questions as clear as ...
1
vote
0answers
32 views

Why such a big difference in number between training error and validation error?

Question Why such a big difference between my 'Train loss' and 'Validation loss' as shown in the picture below? Is it a signal that my codes are wrong and my trained network is wrong as well? Some ...
1
vote
1answer
53 views

Why feeding the correct output as input during training of seq2seq models?

So, I've read about seq2seq for time-series and it seemed really promising, but when I went to implement it, all the tutorial I've found use the correct output as input to the decoder phase during ...
1
vote
0answers
59 views

How can I interpret the following error graph?

I am training a neural network which produces the following errors (epoch number on the x axis). I have some questions regrading interpreting it. When I say ...
1
vote
0answers
256 views

Super Resolution on text documents

I want to implement super-resolution and deblurring on images from text documents. Which is the best approach? Are there any Git-hub links which will help me to start? I am new to the field. Any help ...
1
vote
0answers
37 views

One end to end Neural network or many task-specific ones?

Is it better to train one neural network for a dispersed labeled data with large number of classes or first classify data by unsupervised learning then train each part by a separate NN? I mean by ...
1
vote
0answers
32 views

High variance in performance of q-learning agents trained with same parameters

I am training an agent to play a simple game using double deep q learning. However, the variance in agent performance is very high, even for agents trained with same model parameters. For example, I ...
1
vote
0answers
24 views

Would this NN for my chip outputs work?

I'm a grad student from EE. So, basically, there's an electrical circuit that is supposed to output "0" or "1" by exactly 50 to 50 chance. It generates a number of big arrays of 0s and 1s, each of ...
1
vote
0answers
112 views

DQN not able to learn in a game where other agents perform random walks

I am making a school project where I should develop any kind of game where I can have one reactive agent and one agent based on machine learning competing with each other. My game consists of a ...
1
vote
0answers
21 views

Creating a zero element in embedding space

I have some variable length input vectors for my own use case of a 'stylistic transfer'-esque process, and I am wondering if anyone knows of a way to engineer an input that maps to a 0 element in ...
1
vote
0answers
78 views

Simple weakly supervised Object localizetion using keras. How to visualize the results?

I am following this link : Weakly-supervised-object-localization to create heatmap of the region in an image where the CNN looks to identify the class. As per the above mentioned repository , ...
1
vote
0answers
29 views

Is anyone able to reproduce Hinton's matrix capsule networks?

I've been working on Hinton's matrix capsule networks for several months. I searched each corner of the internet. But I couldn't find anyone that can reproduce Hinton's matrix capsule network. Can ...
1
vote
0answers
53 views

What is the best method to deal with heterogeneous multi agent system MAS?

Heterogeneity: Based on the heterogeneity of agents MAS can be divided into two categories namely: homogeneous and heterogeneous. Homogeneous MAS include agents that all have the same characteristics ...
1
vote
0answers
42 views

how to add the pool4 to the 2 x conv7 in FCN-16s using keras?

Now I'm using tensorflow.keras to implement the FCN-16s, this picture may be different with others, you should focus this it add ...
1
vote
0answers
19 views

One dimension deconvolutions or fully connected layers?

I’ve created a variational autoencoder to encode 1-dimensional arrays. The encoding is done through 3 1d-convolutional layers. Then, after the sampling trick, I reconstruct the series using 3 fully ...
1
vote
0answers
17 views

Is there a way to compare the similarities among different graphs and then cluster them using Unsupervised learning?

I have a dataset about (240000,23). For my task, I have to use an unsupervised learning method and apply it on every single column separately in order to detect anomalies that might exist. I have pre-...
1
vote
2answers
94 views

Running 2 NEAT nets on the same observations

So i have been playing around with neat-python. I made a program, applying neat, to play pinball on the Atari 2600. The code for that can be found in the file ...
1
vote
0answers
75 views

Dialects classification using deep learning

Dialects differ a lot between cities in my country, Syria. People sometimes express themselves using different local phrases and idioms which refer to the same topic. So, I came up with the idea of ...
1
vote
0answers
47 views

How can/should I use AI to populate a game (in the game theory sense) from text input

I'm wanting to conduct game theoretic analyses of ongoing conflict situations (e.g. the US/North Korea negotiations; Syrian conflict; etc) as reported in the news media. I believe that AI may help me ...
1
vote
0answers
32 views

Any guidance on learning rate / batch size for noisy data (high Bayes error rate)?

Is there any guidance available for training on very noisy data, when Bayes error rate (lowest possible error rate for any classifier) is high? For example, I wonder if deliberately (not due to memory ...
1
vote
0answers
39 views

Why is the learning rate is already very small (1e-05) while the model convergences too fast?

I am training a video prediction model. According to the loss plots, the model convergences very fast while the final loss is not small enough and the generation is not good. Actually, I have test ...
1
vote
0answers
21 views

How to train chat bot on infinite non-stationary data?

I have continual simulated data of million sentences of two simulated persons talking to each other in a room and I want to model one of the persons speech. Now, during this period things in the room ...
1
vote
0answers
464 views

Experiment shows that LSTM does worse than Random Forest… Why?

LSTM is supposed to be the right tool to capture path-dependency in time-series data. I decided to run a simple experiment (simulation) to assess the extent to which LSTM is better able to understand ...
1
vote
0answers
17 views

Sample from a distribution inside a NN layer

Is it possible to sample from a distribution inside a neural network forward function? Assume that there is a NN and a sample is needed to be derived from it at every forward-pass to randomly set a ...
1
vote
0answers
18 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: <...
1
vote
0answers
67 views

How does the norm of a weight matrix changes during training?

I have a neural network $F(W,x): \mathbb{R}^d \rightarrow \mathbb{R}^k$ with $L$ layers, $m$ neurones per layer, ReLu activation, softmax on the last layer and $n$ datapoint. My loss function is the ...
1
vote
0answers
80 views

Using Artificial Intelligence for Robot movement instead of regular Inverse Kinematics

I am currently working with classical roboticists who insist on inverse kinematics, and what I (perhaps mistakenly) call the old way of thinking about robots accomplishing tasks. Much of the ...
1
vote
0answers
20 views

Is discrete reading in neural turing machines differentiable?

For a neural turing machine, there is an attention distribution over the memory cells. A read operation consists of multiplying the memory cell's value by its respective probability, and adding these ...
1
vote
0answers
36 views

Are Neural Network layers resistent to noise?

Let's consider a classic feedforward neural network $F$ with input dimension $d$, output dimension $k$, $L$ layers $l_i$ with $m$ neurons each. ReLu activation. This means that, given a point $x \in ...
1
vote
0answers
59 views

Image Segmentation Prediction with cropping 256x256 grids is very slow

I have only a limited dataset (<25) with large-sized images (>1500x2000) and their pixelwise labels. The aim is to find unusual patterns in this industry dataset and highlight them. To generate ...
1
vote
0answers
31 views

a question about Zeiler's paper “Deconvolutional Networks”

In "4.1 Learning multi-layer deconvolutional filters" section, the last paragraph says that "Since our model is generative, we can sample from it. In Fig. 3 we show ...
1
vote
0answers
87 views

RNN and LSTM for discovering time lag

Is there a good reference / tutorial for using RNN/LSTM to determine lag interval for 2 time series? E.g. I have {x_n}, {y_n} and I want to figure out by how much does {x_n} typically lags behind {y_n}...
1
vote
0answers
23 views

input annotations quality check for large scale image data

while dealing with image data at very large scale, there are different sources where data is coming from. Often, we do not have any control over quality of labels/ annotations. I already do use ...
1
vote
0answers
26 views

If there are several computers on a subnet, can training time be reduced by distributing the work across them?

We have multiple computers and the ability to ssh between them. What are options using either Java, C/C++, JavaScript, or Python to distribute our learning tasks? We will be using DCNN, DQN, and LSTM ...
1
vote
3answers
969 views

How to create Partially Connected NNs with prespecified connections using Tensorflow?

I'd like to implement a partially connected neural network with ~3 to 4 hidden layers (a sparse deep neural network?) where I can specify which node connects to which node from the previous/next layer....
1
vote
1answer
824 views

Add training data to YOLO post-training

(Cross-posting here from the data science stack exchange, as my question didn't get any replies. I hope it's okay!) I've been playing around with YOLOv3 and obtaining some good results on the ~20 ...
1
vote
0answers
46 views

How does the degree of neuronal realism affect computing in a deep learning scenario?

Neurons can be simulated using different models that vary in the degree of biophysical realism. When designing an artificial neuronal network, I am interested in the consequences of choosing a degree ...
1
vote
0answers
50 views

How recurrent neural network work when predict many days?

I use recurrent neural network, RNNs have to get input one value per step and it will show one value output. If I have daily sale demand time series data. I want to predict sale demand for three ...
1
vote
0answers
49 views

Data to Google Machine Learning

I have a database with hundreds of questions and answers. Would you like to know how I can work on this data in Google Cloud? I have a social network where I have these questions and answers, and I ...
1
vote
0answers
53 views

How to create a task-graph based neural network?

I'm trying to design a neural network with a task hierarchy. This is my idea so far: ...
1
vote
0answers
45 views

How to combine heterogeneous image features extracted with different algorithms for similar image retrieval?

Say I have access to several pre-trained CNNs (e.g. AlexNet, VGG, GoogleLeNet, ResNet, DenseNet, etc.) which I can use to extract features from an image by saving the activations of some hidden layer ...
1
vote
0answers
37 views

Atrous (Dilated) Convolution: How one can compute responses of arbitrarily high dimensions in DCNN?

According to this paper (page 4, bottom-right), atrous convolutions can be used to compute responses of arbitrarily large dimensions in Deep Convolutional Neural Networks. I do not understand how ...
1
vote
1answer
196 views

Why does the size reduce to $6 \times 6$ in the capsule networks?

I want to experiment with capsule networks on facial expression recognition (FER). For now, I am using fer2013 Kaggle dataset. One thing that I didn't understand in capsule networks was in the first ...
1
vote
0answers
48 views

How to calculate Adaptive gradient?

In the FaceNet paper there mentions an gradient algorithm called 'AdaGrad'(Adaptive Gradient) referenced to this paper which has apparently been used to calculate the gradient of the Triplet Loss ...
1
vote
0answers
103 views

Modelling odd-even distinction of an integer with neural networks

Will it be possible to model the problem of odd-even distinction of an integer (not binary string representation) using neural networks?

1
7 8
9
10 11
13