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".

Filter by
Sorted by
Tagged with
0
votes
0answers
52 views

Can I train a neural network with multiple datasets (e.g. 25)?

I want to create a neural network that I can train with many datasets (e.g. 20 - 25 datasets). Can I use transfer learning for this? Or is there a better approach than this?
5
votes
1answer
109 views

Can GANs be used to generate something other than images?

AFAIK, GANs are used for generating/synthesizing near-perfect human faces (deepfakes), gallery arts, etc., but can GANs be used to generate something other than images?
1
vote
1answer
67 views

What should the output of a neural network that needs to classify in an unsupervised fashion XOR data be?

XOR data, without labels: [[0,0],[0,1],[1,0],[1,1]] I'm using this network for auto-classifying XOR data: ...
3
votes
1answer
235 views

Are tabular reinforcement learning methods obsolete (or getting obsolete)?

While learning RL, I came across some problems where the Q-matrix that I need to make is very very large. I am not sure if it is ever practical. Then I research and came to this conclusion that using ...
0
votes
0answers
35 views

Suggestion for an Enterprise search engine: What are all the way I can use machine learning/dnn/nlp to enhance elasticsearch results?

We are building an enterprise search engine for about 130,000 documents. It includes FAQs, Small articles to 3-4 page documents, all of them are stored in structured JSON. We were originally planning ...
0
votes
1answer
49 views

How do we make our outputs to have the same size as the true mask?

When we are doing multi-label segmentation tasks, our y_true (the mask) will be (w, h, 3), but, in our model, at the last layer, ...
0
votes
0answers
47 views

Predict probability of user making a conversion

My dear friends, In the past couple of years I read a lot about AI with JS and some libraries like TensorFlow. I have great interest in the subject but never used it on a serious project. However, ...
0
votes
0answers
39 views

Using a neural network in a microcontroller to recognize air-written letters and numbers

Recently I finished a project which combined stm32f030r8 microcontroller and MPU9250 sensor to create a system which would detect orientation on all 3 axis using a combination of accel data, gyro data ...
1
vote
1answer
58 views

Is there a way to get landmark features automatically learned by a neural network?

Is there a way to get landmark features automatically learned by a neural network without having to manually pre-label them in the images that are being fed into the network?
1
vote
1answer
71 views

Why would the learning rate curve go backwards?

I'm working on recognizing the numbers 3 and 7 using the MNIST data set. I'm using cnn_learner() function from fastai library. When I plotted the learning rate, the ...
1
vote
0answers
46 views

Advantages of training Neural Networks based on analytic success criteria

What is the reason to train a Neural Network to estimate a task's success (i.e. robotic grasp planning) using a simulator that is based on analytic grasp quality metrics? Isn't a perfectly trained NN ...
0
votes
0answers
43 views

CIFAR-10 can't get above 10% Accuracy with MobileNet, VGG16 and ResNet on Keras

I'm trying to train the most popular Models (mobileNet, VGG16, ResNet...) with the CIFAR10-dataset but the accuracy can't get above 9,9%. I want to do that with the completely model (include_top=True) ...
1
vote
1answer
96 views

What is the purpose of a Neural Network in Reinforcement Learning when we have a Q-learning update rule?

I'm confused as to the purpose of training a neural network (NN) for reinforcement learning (RL) tasks such as Gridworld. In RL tasks, namely q-learning, we have a q-learning update rule, which is ...
0
votes
2answers
126 views

Practical skills in AI

For the past month I have been studying machine/deep learning, thus I have completed both the machine learning course and the deep learning specialization by Prof. Andrew Ng on coursera. In these ...
1
vote
1answer
200 views

Why do we need target network in deep Q learning? [duplicate]

I already know deep RL, but to learn it deeply I want to know why do we need 2 networks in deep RL. What does the target network do? I now there is huge mathematics into this, but I want to know deep ...
1
vote
1answer
43 views

Do the order of the features ie channel matter for a 1d convolutional network?

Do the test dataset feature order and inference (real world) feature order have to be the same as the training dataset? For example, if features are in the order (a,c,b,e,d) for the training dataset, ...
0
votes
0answers
28 views

How do I get my DCGAN to generate a number of fake images?

I have a Deep Convolutional Generative Adversarial Network (DCGAN) that trains on the CIFAR dataset. When I finish the training (100k epochs), how can I make my network generate 1000 fake images? I ...
1
vote
0answers
33 views

Could a quantum computer perform vectorized forward propagation in deep networks?

Forward propagation in Deep Neural Networks In the "Forward Propagation in a Deep Network" video on Coursera, Andrew NG mentions that there's no way to avoid a for loop to loop through the ...
1
vote
0answers
68 views

Why are these same neural network architecture giving different results?

I tried the first neural network architecture and the second one, but keeping all other variables constants, I am getting better results with the second architecture. Why are these same neural network ...
0
votes
2answers
154 views

Why isn't the loss of my neural network reduced after 2500 iterations?

I have developed a basic feedforward neural network from scratch to classify whether image is of cat or not cat. It works fine, but after 2500 iterations, my cost function is not reducing properly. ...
0
votes
1answer
44 views

Can I use augmented data in the validation set?

I am trying to predict nursing activity using mobile accelerometer data. My dataset is a CSV file containing x, y, z component of acceleration. Each frame contains 20-second data. The dataset is ...
2
votes
0answers
60 views

What is a heatmap in the CornerNet paper?

I have been working on understanding how CornerNet works, but I couldn't figure out a few parts about the architecture. First, the authors mention that there are 3 distinct parts to be predicted as a ...
0
votes
1answer
67 views

Is my understanding of back-propogation correct?

I am trying to learn backpropagation and this is what I know so far. To update the weights of the neural network you have to figure out the partial derivative of each of the parameters on the loss ...
0
votes
0answers
49 views

What are the differences between backbones, frontends, models and architectures in applied deep learning?

Context I'm trying to dive into deep learning for tasks on images, and trying to figure out how to reuse some well-known structures* that have been published, mainly on github. ( *Here, structure can ...
2
votes
0answers
66 views

Inaccurate masks with Mask-RCNN: Stairs effect and sudden stops

I've been using matterport's Mask R-CNN to train on a custom dataset. However, there seem to be some parameters that i failed to correctly define because on practically all of the images, the bottom ...
1
vote
1answer
29 views

When adding a feature is useless?

"simple" issue: I'm building a model, where from a feature set A I want to predict a target set C; I need to understand if another feature set B, together with A, can improve my model ...
2
votes
1answer
101 views

Which paper introduced the term “softmax”?

Nowadays, the softmax function is widely used in deep learning and, specifically, classification with neural networks. However, the origins of this term and function are almost never mentioned ...
1
vote
0answers
43 views

How is depth perception (e.g. in autonomous driving) addressed without using a Lidar or Radar unit?

For practical applications, like autonomous driving, depth perception is needed to make useful decisions. How is this normally addressed without using a LIDAR or RADAR unit (but using a camera)?
1
vote
0answers
50 views

Is it necessary to label the background when generating the labelled dataset for semantic segmentation?

When I label images for semantic segmentation (using u-net, if that matters), is labeling the background (anything I am not interested in) necessary? Will it improve the network's performance?
0
votes
0answers
23 views

Different result from k-cross validation model and Train-Validation-Test split model ? (AI fresher question)

I am starting to learn about Neural Network and I have come into one problem that I am still learning how to figure it out. I have a dataset with shape (105,96) (105 samples and 95 first column as ...
0
votes
0answers
22 views

Best ROC threshold for classifier?

Suppose I have a neural network $N$ that produces the output probabilities $[0.3, 0.8]$. Normally, I would specify a threshold of 0.5 for the argmax of the prediction, let's say, second arg > 0.5 ...
0
votes
0answers
30 views

How to feed the LSTM with different length for the latest time step?

I am having a training data set for a time-series dataset like below: ...
2
votes
1answer
79 views

Why are RNNs used in some computer vision problems?

I am learning computer vision. When I was going through implementations of various computer vision projects, some OCR problems used GRU or LSTM, while some did not. I understand that RNNs are used ...
3
votes
1answer
100 views

Is it possible to classify resistors using ResNet50?

I want to train ResNet50 model using resistor images like below: I tried it by collecting data from google images and there were quite few. So accuracy was very low (around %10) but I wonder If it is ...
2
votes
1answer
51 views

What does it mean when a model “statistically outperforms” another?

I was reading this paper where they are stating the following: We also use the T-Test to test the significance of GMAN in 1 hour ahead prediction compared to Graph WaveNet. The p-value is less than 0....
0
votes
1answer
47 views

96.91% accuracy on MNIST after 2 hours of training using custom made neural net library. Ways to improve?

I wanted to understand back-propagation so I made a basic neural network library. I used momentum, with learning rate = $0.1$, beta = $0.99$, epochs = $200$, batch size = $10$, loss function is cross ...
0
votes
0answers
22 views

Computational difference between ANN and Pattern Matching

Conceptually, if you had an internal 3d model of all objects in CV you could do a scan matching algorithm. This algorithm would be ridiculously computationally intensive, but it would have a high ...
0
votes
0answers
46 views

Why are YOLO Darknet weights so heavy?

I have been trying to understand how YOLO Darknet works, and for the most part reading the documentation and checking the code helps me understand. But when it comes to the weight file, I can't find ...
2
votes
0answers
77 views

Should batch normalisation be applied before or after ReLU?

I know that there has been some discussion about this (e.g. here and here), but I can't seem to find consensus. The crucial thing that I haven't seen mentioned in these discussions is that applying ...
1
vote
0answers
31 views

How to measure/estimate the energy consumption of CNN models during testing?

Does someone know a method to estimate / measure the total energy consumption during the test phase of the well-known CNN models? So with a tool or a power meter... MIT has already a tool to estimate ...
1
vote
0answers
59 views

I need help understanding general back propagation algorithm

In section 6.5.6 of the book Deep Learning by Ian et. al. general backpropagation algorithm is described as: The back-propagation algorithm is very simple. To compute the gradient of some scalar z ...
0
votes
1answer
31 views

How is it possible to get the output size of `n` Consecutive Convolutional layers? [closed]

Given network architecture, what are the possible ways to define fully connected layer fc1 to have a generalized structure such as ...
1
vote
1answer
45 views

How will the input be preserved as we go deeper in CNN, where dimensions decrease drastically?

Our length of feature representation decreases as we go deeper into the CNN, I mean to say that horizontal and vertical lengths decrease while depth(channels) increase. So, how will the input be ...
0
votes
1answer
73 views

Why is non-linearity desirable in a neural network?

Why is non-linearity desirable in a neural network? I couldn't find satisfactory answers to this question on the web. I typically get answers like "real-world problems require non-linear ...
0
votes
0answers
14 views

Do we train the spatial net and temporal net separately in two stream CNN for action recognition from video frame?

In two-stream CNN paper, they have the following network architecture: We can use a simple average or multiclass linear SVM for the class score fusion. In the case of averaging the outputs of two ...
2
votes
1answer
53 views

Do transformers have success in other domains different than NLP?

Everybody knows how successful transformers have been in NLP. Is there known work on other domains (e.g that also have a sequential natural way of occurring, such as stock price prediction or other ...
0
votes
0answers
42 views

How is centralised training and decentralised execution in multi agent reinforcement learning implemented?

In the paper Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning, it is written We allow centralised training but require decentralised execution, from which follows that the policies ...
0
votes
0answers
21 views

Which model structure is best suited to build a Math OCR (img2latex)? RAM, DRAM, CRNN or Attention OCR?

I am trying to build an OCR which can read the Mathematical equations just like MAthPix and im2markup. im2markup by HarvardNLP seems like a good model but the thing is that it is built using Torch and ...
1
vote
1answer
55 views

Why does my “entropy generation” RNN do so badly?

I'm new to relatively RNNs, and I'm trying to train generative and guessing neural networks to produce sequences of real numbers that look random. My architecture looks like this (each "circle&...
0
votes
0answers
35 views

Reinforcement Learning Diagnostic: Total reward doesn't converge

I'm implementing DDQN in my toy scenario. During training, I'm surprised to see that the total reward doesn't converge and have a tendency to degrade. What could be the problem? Here's the picture: ...

1
5 6
7
8 9
29