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
5 views

When should I stop the object detection model training while mAP are not stable?

I am re-training the SSD MobileNet with 900 images from the Berkeley Deep Drive dataset, and eval towards 100 images from that dataset. The problem is that after ...
1
vote
1answer
21 views

How can I learn tensors for deep learning?

I've seen in most deep learning papers use tensors. I understood what tensors are, but I want to dive into them, because I think that might be beneficial for further studies in Artificial Intelligence....
1
vote
2answers
17 views

Are feature maps merged or are they passed on as they are?

I am unsure about the following parts of the architecture and mechanics of convolution layers in CNNs. Possibly, this is implementation-dependent though. First question: Say I have 2 convolution ...
0
votes
1answer
33 views

If the goal of training of a GAN is to have $P_g=P_{data}$, shouldn't this produce the exact same images?

Referring to the blog, Image Completion with Deep Learning in TensorFlow, it clearly says that we would want a generator $g$ whose modeled distribution fits our dataset $data$, in other words, $P_{...
2
votes
2answers
56 views

What is the difference between a machine learning engineer and deep learning engineer?

What is the difference between a Machine Learning Engineer and Deep Learning Engineer and an AI developer? What would be their daily tasks at the office?
1
vote
0answers
16 views

Improving the performance of a DNN model

I have been executing an open-source Text-to-speech system Ossian. It uses feed forward DNNs for it's acoustic modeling. The error graph I've got after running the acoustic model looks like this: ...
2
votes
0answers
25 views

How can I incrementally train a Yolo model without catastrophic forgetting?

I have successfully trained a Yolo model to recognize k classes. Now I want to train by adding k+1 class to the pre-trained weights (k classes) without forgetting previous k classes. Ideally, I want ...
0
votes
1answer
27 views

Why does keras model get bigger after training?

I notice that I create a model using tensorflow.keras.Sequential(), save it and the file size is around 5 MiB, but after I call ...
2
votes
1answer
20 views

Spikes in of Train and Test error

I learn a DNN for image recognition. During each epoch, I calculate mean loss in the training set. After each epoch, I calculate loss and number of errors over both training and test set. The problem ...
0
votes
0answers
18 views

Join Multiple Tensor from a CNN features extractor [migrated]

I have a mixed neural network. The first part is a CNN that extrapolate features from an image; the OUTPUT shape from this first part is [None, 1, 1, 128] ...
6
votes
1answer
75 views

Suicide Predictor and Locator

Suicide is on the increase in my country and most victims tend to leave early traces from text messages, social media accounts, search engine queries. So I came up with the idea to develop an AI ...
1
vote
0answers
57 views

How do I determine the generalisation ability of a neural network?

I am trying to ascertain if my neural network is able to generalize or if it’s simply using memory/overfitting to solve a task. I would like my model to generalise. Currently, I train the neural ...
2
votes
1answer
46 views

What is the most common practice to apply batch normalization?

For a deep NN, should I generally apply batch normalization after each convolution layer? Or only after some of them? Which? Every 2nd, every 3rd, lowest, highest, etc.?
2
votes
1answer
45 views

How should I detect an object in a camera image?

I would like to create a model, that will tell me if one type of object is in an image or not. So, for example, I have a camera and I would like to see when one object gets into the shot. Object ...
3
votes
1answer
121 views

Can a vanilla neural network theoretically achieve the same performance as CNN?

I perfectly understand that CNN takes into account the local dependency of each pixel to the nearby pixels. In addition, CNNs are spatially invariant which means that they are able to detect the same ...
1
vote
0answers
26 views

How to calculate size and offset of YOLO grid in a fully convolutional network with zero padding? [migrated]

Fully convolutional network with zero padding: I have a fully convolutional network which does not have any padding in convolutional layers. This implies that, after each convolution operation, the ...
1
vote
1answer
31 views

Paper & code for “unsupervised domain adaptation” for regression task

Does anyone know a paper or code that does "unsupervised domain adaptation" for regression task? I saw most of the papers were benchmarked on classification tasks, not regression. I want to do ...
1
vote
0answers
32 views

Is it possible to use adversarial training to learn invariant features?

Given a set of time series data that are generated from different sites where all sites are investigating the same objective but with slightly different protocols. Is it possible to use adversarial ...
0
votes
0answers
18 views

How to implement Multiple Neural network architecture, connected in parallel and series in Keras or Pytorch

Hello Dear StackExchange members, I want to make a deep network as shown in the image. I want each 'network 1 to look at the specific part of the input and I don't want to divide my input beforehand ...
1
vote
0answers
9 views

Inverting intensity on images to enhance image dataset

i just tried to improve my image dataset by inverting the images with a probability of 50% (means white background, black features transforms to black background, white features) I thought this will ...
0
votes
0answers
54 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
11 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, ...
0
votes
1answer
45 views

Is DDPG just for deterministic environments?

I want to develop an AI for continuous space. I reached to DDPG algorithm that takes actions deterministically. If DDPG takes actions deterministically, should the environment also be deterministic? ...
1
vote
1answer
43 views

Is there a neural network method for time-varying directed graphs?

I want to study NN for time-varying directed graphs. However, as this field has developed relatively recently, it is difficult to find new ways. So the question is, is there any NN that can handle ...
-1
votes
1answer
60 views

Which is better to start deep learning and understand it in depth (and not just a simple overview) - pytorch or tensorflow 2.0?

I am beginning to learn deep learning. I recently spoke with an expert in the field. He suggested that I start with pytorch because of these reasons: Keras abstracts the stuff a lot that we will not ...
1
vote
1answer
29 views

How does the CTC loss work?

I am trying to implement CTC loss in Tensorflow, but their documentation is pretty limited. So I am not sure how to approach the problem. I found a good example in Theano: https://github.com/...
3
votes
1answer
24 views

DQN in stochastic environment

I'm trying to apply a DQN to a stochastic environment but i'm having trouble getting it to converge. I found some similar questions asked here, but no solutions yet. I can fairly easy get the DQN to ...
1
vote
0answers
18 views

How to voxelize multiple frames at the time and append them together?

I'm trying to implement this approach for object detection and tracking. In this approach, the first step is voxelize each frame to construct a 3D tensor, the second step is to append multiple voxels ...
1
vote
0answers
11 views

What are some neural network models that can use auxiliary info during training for image segmentation?

What are some deep learning models that can use supplementary information other than RGB channels for image segmentation? For example imagine a poorly shot image of a river (blue) that shows a gap, ...
0
votes
0answers
26 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 ...
0
votes
0answers
13 views

Issues related to RoI Pooling in keras

I am trying to do RoI pooling of an image whose RoI bounding box coordinates are known to me. Can anyone provide me the code for doing the same? I have read many repositories but I didn't get any ...
3
votes
0answers
15 views

What parameters can be tweaked to avoid a generator or discriminator loss collapsing to zero when training a DC-GAN?

Sometimes when I am training a DC-GAN on an image dataset, similar to the DC-GAN PyTorch example (https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html), either the Generator or ...
1
vote
0answers
29 views

What are the benefits of using the state information that maintains the graph structure?

When you applying a graph structured data to the graph convolution network, what are the benefits of using the state information that maintains the graph structure?
2
votes
1answer
45 views

What is the purpose and benefit of applying CNN to a graph?

I'm new to the graph convolution network. I wonder what is the main purpose of applying data with graph structure to CNN?
1
vote
1answer
36 views

Clarifications on “Prioritized Experience Replay” (Deepmind, 2015)

Paper link : Prioritized Experience Replay About the blind cliffwalk setup: Why is the number of possible action sequences equal to 2^N? I cant think of sequences more than (N + 1) where one ...
2
votes
1answer
40 views

How do I locate a specific object in an image?

Some pictures contain an elephant, others don't. I know which of the pictures contain the elephant, but I don't know where it is or how does it look like. How do I make a neural network which ...
2
votes
1answer
141 views

How do I find the distance?

I am looking for solving this problem with training a deep learning-based classifier or image processing techniques. ps. I exactly do not need to know how much is distance, I only need to know whether ...
1
vote
0answers
44 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
1answer
61 views

Reinforcement Learning State Definition

I am quite new to Deep Reinforcement Learning, and I'm trying to define states in a Reinforcement Learning problem. The environment consists of multiple identical elements, and each one of them is ...
0
votes
1answer
29 views

Analysis of Training Loss and Validation Loss Graph

Here I am Showing Two Loss graphs of an Artificial Neural Network. Model 1 Model 2 Blue -training loss Red -val training loss Can you help me to analyse these graphs? I read some articles and ...
4
votes
0answers
49 views

What is the difference between GAT and GaAN?

I was looking at two papers Graph Attention Networks (GAT) by Petar Veličković and GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs by Jiani Zhang. I'm trying to ...
2
votes
1answer
55 views

Adding BERT embeddings in LSTM embedding Layer

I am planning to use BERT embeddings in the LSTM embedding layer instead of the usual Word2vec/Glove Embeddings. What are the possible ways to do that?
1
vote
0answers
11 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 ...
2
votes
1answer
32 views

Decreasing Loss, Constant Accuracy

Problem Statement I've built a classifier to classify a dataset consisting of n samples and four classes of data. To this end, I've used pretrained VGG-19, pretrained Alexnet and even lenet (with ...
0
votes
0answers
19 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
0answers
18 views

How to make a distinction between item feature and environment feature?

Question My data is stock data with features such as stocks' closing prices. I am curious to know if I can put the economy feature such as 'national interest rate' or 'unemployment rate' besides ...
0
votes
2answers
66 views

How do I perform object detection if there is only one type of object?

How do I do object detection (or identify the location of an object) if there is only one kind of object, and they are more of less similar size, but the picture does not look like standard scenes (it ...
2
votes
1answer
22 views

How does ARKit's Facial Tracking work?

iPhone X allows you to look at the TrueDepth camera and reports 52 facial blendshapes like how much your eye is opened, how much your jaw is opened, etc. If I want to do something similar with other ...
0
votes
1answer
29 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 ...
3
votes
1answer
69 views

How can I build an AI with NLP that read stories

I want to do an NLP project but I don't know if it's doable or not as I have no experience or knowledge in NLP or ML yet. The idea is as follows: Let's say we have a story (in the text) that has 10 ...