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]

For questions about Deep Learning (also known as deep structured learning or hierarchical learning.)

1
vote
0answers
9 views

Putting constraints on output of deep neural network

I am training a deep neural network. There is a constraint on an output value of the network. (e.g. Output has to be between 0 and 180) I think some possible solutions are using sigmoid,tanh ...
0
votes
0answers
11 views

How to train a model by accounting for boundary constraints?

I've a robot traverse through a grid layout. Based on the wheel speed difference I classify actions as either straight, left or right. I computed the distances based on the time duration and the speed ...
0
votes
0answers
8 views

Usefulness of Data augmentation for non-overfitting network [NLP]

(Maybe related : Usefulness of Dropout for non-overfitting network) My neural network does not overfit. Using Data augmentation in a non-overfitting network can increase its accuracy ? Note : I'm ...
-1
votes
0answers
12 views

Data augmentation with ImageDataGenerator in Keras - Python

I have tried to use imageDataGenerator for data augmentation for following cnn wich i need to train for 5 different image classes. When i run this code, following error occurred. "Traceback (most ...
1
vote
0answers
10 views

How exactly is equivariance achieved in capsule networks?

I have read quite a lot about capsule networks but cannot understand how the squashed vector would also rotate in response to rotation or translation of the image.A simple example would be helpful.I ...
1
vote
1answer
19 views

Usefulness of Dropout for non-overfitting network

My neural network is simple enough and does not overfit. Dropout is a regularization technique for reducing overfitting in neural networks From Wikipedia Adding Dropout in a non-overfitting ...
1
vote
0answers
11 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
1answer
12 views

Neural Network for OMR?

I've created a neural net using the ConvNetSharp library which has 3 fully connected hidden layers. The first having 35 neurons and the other two having 25 neurons each, each layer with a ReLU layer ...
2
votes
0answers
16 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
0answers
9 views

What is meant by “model discriminability for local patches within the receptive field”?

In the Abstract section of the paper Network In Network, what does the authors actually mean to say?
4
votes
1answer
27 views

What are the ways to calculate the error rate of a deep Convolutional Neural Network, when the network produces different results using the same data?

I am new to the object recognition community. Here I am asking about the broadly accepted ways to calculate the error rate of a deep CNN when the network produces different results using the same data....
1
vote
1answer
29 views

Can we combine multiple different neural networks in one?

I want to make a kind of robotic brain i.e. a big neural network, which includes NLP model (for understanding human voice) , real-time object recognition (so it can identify particular object), face ...
2
votes
1answer
36 views

Asus zenbook with deep learning

Is the laptop Asus ZenBook Pro 90NX0152-M02980 enough to do deep learning model? Specs: Processeur Intel Core i7-7500U (Dual-Core 2.7 GHz / 3.5 GHz Turbo - cache 4 MB) 8 GB Memory SSD M.2 SATA de ...
0
votes
1answer
18 views

Why is there Transition layers in DenseNet?

The DenseNet architecture can be summarize with this figure : Why there is transition layers between each blocks ? In the papers, they justify the use of transition layers as follow : The ...
2
votes
2answers
45 views

How to improve testing accuracy when training accuracy is high?

Following-up my question about my over-fitting network My deep neural network is over-fitting : I have tried several things : Simplify the architecture Apply more (and more !) Dropout Data ...
4
votes
0answers
35 views

Can AI 'fix' heavily compessed videos/photos?

So let's say you had a really nice day in a flight simulator and you are getting videos of this type of quality: This is Full HD (1080p), but heavily compressed. You can literally see the pixels. Now ...
2
votes
1answer
33 views

How to find the category of a technical text on a surface-semantic-level

There are some predefined categories( Overview, Data Architecture,Technical Details, Applications etc). The requirement is to classify the input text of paragraphs into their resp. category. I cant ...
1
vote
1answer
34 views

Deep learning model training and processing requirement for Traffic data

I am a newbie in the deep learning and am looking for advice on predicting traffic congestion events. I have a table for vehicles travel times data, another table with the roads length segmented based ...
0
votes
0answers
45 views

Extract particular pattern from the given text/paragraph using machine or deep learning

If there is given a one paragraph as a input and it extract a string from the paragraph,within a predefined range (i.e. a string that starts with three letters that a always fixed and ends with five ...
1
vote
1answer
42 views

Interpretation of a good overfitting score

As shown below, my deep neural network is overfitting : where the blue lines is the metrics obtained with training set and red lines with validation set Is there anything I can infer from the fact ...
1
vote
3answers
45 views

How to detect a Neural Network will work with the whole dataset?

I want to implement a neural network on a big dataset. But training time is long (~1h30 per epoch). I'm still in the development process, so I don't want to wait such long time just to have poor ...
0
votes
0answers
15 views

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

I'd like to implement a partially connected neural network with ~3-4 hidden layers (a sparse deep neural network?) where I can specify which node connects to which node from the previous/next layer. ...
0
votes
0answers
20 views

GAN and manifold hypothesis

I studied about GAN by using Ian Goodfellow's tutorial on NIPS. And I understand that the strategy of a generator is approximating the probability density function from the training set data points ...
1
vote
1answer
28 views

Weight Normalization paper

I am trying to dissect paper about weight normalization: https://papers.nips.cc/paper/6114-weight-normalization-a-simple-reparameterization-to-accelerate-training-of-deep-neural-networks.pdf ...
0
votes
1answer
15 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 ...
2
votes
1answer
55 views

PPO / TRPO Implementation

So, I recently watched this video on PPO and want to upgrade my actor-critic algorithm written in PyTorch with PPO, but I'am not sure how the new parameters / ...
2
votes
4answers
59 views

Using Convolutional Neural Networks for movement classification

I have programmed my first network for the MNIST dataset. I was wondering what the first approach would be to recognize certain movements. I have read about that the time dimension should be ...
-1
votes
1answer
30 views

How to visualize the time complexity for training a Neural Network

I want to compare the time complexity of two deep neural networks, but I have no idea how to go about it. How do I graphically achieve that with respect to the number of iterations, accuracy or any ...
0
votes
0answers
28 views
1
vote
0answers
23 views

Is PCIe the bottleneck in a deep learning GPU system, so it makes sense to choose Nvidia NV-Link over more Tesla V100 graphics cards?

I'm considering a GPU system for deep learning applications, mainly for training models with large datasets. So I'm not sure whether it makes sense to choose Nvidia NV-Link over more Tesla V100 ...
0
votes
0answers
11 views

Can an RNN be said to be a special case of a message passing neural network?

Can an RNN be said to be a special case of a simple message passing neural network, where one element passes on a message to the next element in the sequence? Or is there more to the definition of a "...
-1
votes
0answers
16 views

Does the graphic become convex or concave in case we have a negative or positive loss in neural network?

For example, we have a positive loss and it's convex and we have a negative loss and it's concave. I know that if we have an MSE as our cost function result is always positive. But what if we have a ...
1
vote
1answer
27 views

Neural Network on EV3 Mindstorm without 3rd Party Software

I am working on a prototype for an Ev3 Neural Network. Because for competitions, we are not allowed to use Bluetooth or Wifi connections, the neural network must be made with the Ev3 block-based ...
1
vote
1answer
29 views

Fundamentally choosing number & size of filters, convolution layers in deep learning

While we train a CNN model we often experiment with number of filters, number of convolutional layers, FC layers, filter size, sometimes stride, activation function, etc. More often than not after ...
1
vote
1answer
48 views

How to find partial derivative of softmax w.r.t logits in python

i have trouble implementing back propogation for multi class classification of CIFAR10 dataset My neural network has 2 layers forward propagation X -> L1 -> L2 weights W are initialized as random ...
2
votes
1answer
47 views

Is a calculus or ML approach to varying learning rate as a function of loss and epoch been investigated?

Many have examined the idea of modifying learning rate at discrete times during the training of an artificial network using conventional back propagation. The goals of such work have been a balance ...
6
votes
1answer
253 views

Loss jumps abruptly when I decay the learning rate with Adam optimizer in PyTorch

I'm training an auto-encoder network with Adam optimizer (with amsgrad=True) and ...
1
vote
1answer
69 views

Compute Jacobian matrix of Deep learning model?

I am trying to implement this paper. In this paper, the author uses the forward derivative to compute the Jacobian matrix dF/dx using chain rule where F is the probability got from the last layer and ...
1
vote
1answer
126 views

Does a solution for Wumpus World with neural networks exist?

The Wumpus World proposed in book of Stuart Russel and Peter Norvig, is a game which happens on a 4x4 board and the objective is to grab the gold and avoiding the threats that can kill you. The rules ...
0
votes
1answer
68 views

Machine learning to predict 8*8 matrix values using three independent matrices

Problem Statement I have 4 main input features. This is a small snippet of the data for clearer understanding. Gate name -> for example AND Gate index_1 -> ...
1
vote
3answers
91 views

What is chaotic behavior and how it is achieved in non-linear regression and artificial networks?

I'm finding it hard to understand the relationship between chaotic behavior, the human brain, and artificial networks. There are a number of explanations on the web, but it would be very helpful if I ...
0
votes
2answers
29 views

CNN Pooling layers unhelpful when location important?

I'm trying to use a CNN to analyse statistical images. These images are not 'natural' images (cats, dogs, etc) but images generated by visualising a dataset. The idea is that these datasets hopefully ...
0
votes
0answers
54 views

Deep learning with a lot of training data

I am building a bidirectional LSTM to do a sequential text-tagging task (particularly, automatic punctuation). Usually, the training is done in iterations, where in each iteration, the entire training ...
3
votes
1answer
44 views

Does balancing the training data set distribution for a neural network affect its understanding of the original distribution of data?

I have a very imbalanced dataset of two classes: 2% for the first class and 98% for the second. Such imbalance does not make training easy and so balancing the data set by undersampling class 2 seemed ...
1
vote
1answer
32 views

Dimensionality of convolutional layers & convolution operations

I am trying to understand the dimensionality of the outputs of convolution operations. Suppose a convolutional layer with the following characteristics: Input map $\textbf{x} \in R^{H\times W\times D}...
1
vote
0answers
31 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 ...
3
votes
2answers
66 views

Can I reduce the “number of weights” in CNN to 1/3 by restricting the input as greyscale image?

In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels? This question helps me a lot. Let, I have RGB input ...
0
votes
1answer
70 views

Should Q values be changing within an epoch/episode or should they change after one episode/epoch?

I am trying to use Deep-Q learning environment to learn Super Mario Bros. The implementation is on Github. I have a neural network that Q values update within an episode for a very small learning ...
5
votes
1answer
60 views

Learning Rate Decay and Exploration Rate Decay

Should I be decaying the learning rate and the exploration rate in the same manner? What's too slow and too fast of an exploration and learning rate decay? Or is it specific from model to model?
2
votes
1answer
45 views

Clarification regarding “Image Crowd Counting Using Convolutional Neural Network and Markov Random Field”

I am currently reading the research paper Image Crowd Counting Using Convolutional Neural Network and Markov Random Field by Kang Han, Wanggen Wan, Haiyan Yao, and Li Hou. I did not understand the ...