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
2answers
17 views

how to speed up YOLOv3 detection speed?

I want to implement YOLO V3. I want to know which framework will give me a faster result. what are the advantages of implementing YOLO V3 on darknet framework vs Keras framework?
3
votes
2answers
47 views

How to use AI to depth map video?

To be honest, I had no idea where to put this question, but it's sure that it's related to AI. I want to build an application which uses camera, and by the movement it can calculate the -camera's ...
4
votes
1answer
89 views

Paradigm shift in Machine Learning

This is a very general question, so I do not expect any specific answer. I was reading some Tweets about NeurIPS 2018, and came upon this video from NVIDIA. At around 0.37, she says: ... If you ...
0
votes
1answer
24 views

How to get a binary output from a Siamese Neural Network

I'm trying to train a Siamese network to check if two images are similar. My implementation is based on this. I find the Euclidian distance of the feature vectors(the final flattened layer of my CNN) ...
0
votes
1answer
14 views

Can a LFSR be approximated by a Neural Network?

I was wondering whether a LFSR could be approximated by a NN (output or current state). We know that a LFSR is called linear in some sort of mathematical sense, but is that true? Considering it ...
0
votes
2answers
27 views

Keras giving memory allocation error and running extremely slow

I am working on character recognition using convolutional neural networks. I have 9 layer model and 19990 training data and 4470 test data. But when I am using keras with Tensorflow backend. When I ...
1
vote
0answers
28 views

How to encode Azul game state as NN input

Question to NN practicioners. I'd like to encode Azul board game state as an input to NN, let's focus on 2-player variant for a while. There are 5 round "Factories" on the table (7 on picture, ignore ...
-1
votes
0answers
10 views

Training a combined deep and shallow network

I want to train a combined deep and shallow neural network, say a 20 block ResNet, with a 2-layer dense network that takes the output of the ResNet and combines it with auxiliary input in the first ...
2
votes
1answer
35 views

How do randomly initialized neural networks behave?

I am wondering how the output of randomly initialized MLPs and ConvNets behave with respect to their inputs. Can anyone point to some analysis or explanation of this? I am curious about this because ...
0
votes
1answer
33 views

DQN exploration strategy for large grid-world environment

My task involves a large grid-world type of environment (grid size may be $30\times30$, $50\times50$, $100\times100$, at the largest $200\times200$). Each element in this grid either contains a 0 or a ...
0
votes
0answers
31 views

Deep apply to patient clustering

I'm currently doing a computer engineer internship in the field of artificial intelligence. I would like you to criticize my work. Also I have more specific questions that I will put at the end of ...
0
votes
0answers
22 views

Attention mechanism

I'm having problems implementing Bahdanau attention mechanism in a custom seq2seq (encoder-decoder) architecture. So far I reached this point: ...
0
votes
2answers
32 views

Neural network architecture for function approximation

We have convolutional neural networks and recurrent neural networks for analysing images and sequential data, respectively. What is the main architecture used for function approximation? (e.g. a ...
3
votes
1answer
55 views

are there any Machine Learning algorithms for comparing files

So, in situations where some output-data-chunks could change without changing the input data from time to time, it could be challenging to automate the testing process. My question is, are there any ...
0
votes
2answers
32 views

Can I detect unique people in a video?

I am having a video feed with multiple faces in it. I need to detect each face and the gender as well and assign the gender against each person. I am not sure how to uniquely identify a face as Face1 ...
0
votes
0answers
18 views

Deep Learning for Counting Object Pixels

I am new to deep learning and python/tensorflow, and am working on a project to measure object length in an image. I have been using the Tensorflow Object Detection API for training an object ...
1
vote
2answers
59 views

For forecasting and trading control, given limited data, what AI approaches are well matched?

I'm working on stock price prediction and automatic or semi-automatic control of trading. The price trends of these stocks exhibit recurring patterns that may be exploited. My dataset is currently ...
0
votes
1answer
19 views

Reduce the effect of excessive zeros

I am working on an autoregression problem where I use sequential LSTM. My target is well defined, but I think I am facing a problem with the features. As the features were non-stationary, then I ...
0
votes
0answers
16 views

How to use AI to generate similar questions from a base question?

I am looking for methods/techniques I can use to generate a set of similar questions based on a base question. The generated questions should be answered by the exact same answer to the base question. ...
-1
votes
1answer
43 views

DQN it's not working properly

I'm trying to build a DQN to replicate the DeepMind results. I'm doing with a simple DQN for the moment, but it isn't learning properly: after +5000 episodes, it couldn't get more than 9-10 points. ...
-1
votes
0answers
27 views

How to build an AI that suggests source texts automatically when given a debate argument as input?

Take a site like this: http://www.thesquabbler.com/design/ (just an approximate design to explain the concept), where users add debate topics and then for and against arguments to them. The key is ...
0
votes
1answer
58 views

Can BERT be used for sentence generating tasks?

I am a new learner in NLP. I am interested in the sentence generating task. As far as I am concerned, one state-of-the-art method is the CharRNN, which uses RNN to generate a sequence of words. ...
0
votes
1answer
20 views

What are some limitations of using Collaborative Deep learning for Recommender systems?

Recently I worked on a paper by Hao Wang- Collaborative Deep learning for Recommender Systems which uses a two way tightly coupled method, Collaborative filtering for Item correlation and Stacked ...
4
votes
1answer
28 views

Alpha zero before move 8

The Alpha zero paper says that the The first set of features are repeated for each position in a T = 8-step history. So what happens before the first 8 moves? Do they just repeat the starting position?...
-2
votes
0answers
37 views
0
votes
0answers
14 views

Zero inflated binomial for excessive zeros

That photo shows that we have a trend. However, the trend is not exceptional because there is too much zeros in the target set and the features. MSE Loss / criterion on data $(x,y)$ Current ...
0
votes
0answers
9 views

Deep leaning classification models for scratch vs no scratch aka binary classification (Not Cats & Dogs)?

Tensor-flow hub models been tried so far, gives 50%-80% accuracy on unknown dataset. What can be done to solve classification task with 100% accuracy for sub-categories such as black surface with ...
2
votes
0answers
40 views

Setting learning rate as negative number for wrong train cases

I was watching a video which tells a bit about reinforcement learning, and I learnt that If the robot makes wrong movement then they train the network with negative learning rate. From this method, ...
5
votes
5answers
179 views

Where can I discuss with deep learning beginners?

I did some self-study to learn Neural network, object detection, and deep learning. Now I started implementing YOLOv3. I am looking for some website that I can communicate with people and make friends ...
0
votes
0answers
11 views

Combining Two CNN's [migrated]

I Want to Combine Two CNN Into Just One In Keras, What I Mean Is that I Want The Neural Network To Take Two Images And Process Each One in Separate CNN, and Then Concatenate Them Together Into The ...
2
votes
0answers
55 views

Regarding L0 sparsification of DNNs proposed by Louizos, Kingma and Welling

I am reading the paper on $\ell_0$ regularization of DNNs by Louizos, Welling and Kingma (2017) (Link to arxiv). In Section 2.1 the authors define the cost function as follows: $$ \mathcal{R}\left( \...
0
votes
0answers
29 views

How to train a stock trading neural network so that the 'profit' parameter is maximized?

I am watching some beginner level video training on neural networks using Tensorflow / Keras to get a better understanding of how they work and how to best implement them. I have some questions on ...
0
votes
1answer
38 views

Is it possible to use a feed-forward neural network to predict the actions in reinforcement learning?

I have done a lot of research on the internet about Reinforcement Learning and I found encountered methods of Reinforcement Learning: Q-Learning and Deep Q-Learning. And I have developed a vague idea ...
0
votes
1answer
50 views

Feature learning vs feature engineering vs feature learning and engineering

With the advancement of deep learning and a few others automated features learning techniques, manual feature engineering started becoming obsolete. Any suggestion on when to use manual feature ...
-1
votes
2answers
82 views

What are the prerequisites for starting out in Deep Learning?

I am new in artificial intelligence and want to getting start with deep learning in Python. I know about the basics of Python. What should i have to learn more?
1
vote
0answers
46 views

How does Hindsight Experience Replay learn from unsuccessful trajectories

I am confused by how HER learns from unsuccessful trajectories. I understand that from failed trajectories it creates 'fake' goals that it can learn from. Ignoring HER for now, if in the case where ...
0
votes
0answers
12 views

Terrain Heightmap Dataset For Training

I'm building an application that utilizes machine learning to generate terrain heightmaps based on labels. For example, if the input label is "forest", the application shall generate a heightmap that ...
0
votes
0answers
29 views

Any suggestions or information about how the latest NVIDIA QUADRO RTX 5000 might do with deep learning?

Any idea if the latest Quadro RTX 5000 might outperform or be comparable to the Titan V or XP?
1
vote
0answers
24 views

Use of backpropagation for weight updates in a combination of 2 neural networks

Every neural network updates its weights through back-propagation. How is back-propagation used for updating weights in a combination of 2 or more neural networks (e.g.:CNN-LSTM, GAN-CNN, etc.). For ...
-1
votes
0answers
31 views

Why my initial loss is bigger than the expected?

I am trying to perform a simple binary classification with a neural network on the make_moons dataset. Because of random initialization, I expect the first values to be equally splited between ...
-2
votes
3answers
93 views

How are artificial neural networks different from normal computers?

I have been given this question that how neural networks are different from normal computers? But after searching alot i still couldnt get the best reason on it which makes my point clear, so how ...
0
votes
0answers
19 views

What are intelligent agents and how they are use in artificial intelligence?

How we will describe intelligent agents in artificial intelligence and their use in artificial intelligence field?
2
votes
1answer
84 views

Significance of depth of a deep neural network

How is a feed-forward neural network with few hidden layers and lots of nodes in those hidden layers different from a network with a lot of hidden layers but relatively lesser nodes in those hidden ...
0
votes
0answers
15 views

How to train a multi inputs deep learning model using every combination of inputs?

I am beginner in deep learning. I want to create a multi inputs CNN model in Keras. The model takes two inputs of images to give the two images class. The two images from differnt datasets that have ...
1
vote
1answer
52 views

Why do we need artificial intelligence?

How we will explain the best usage and need of artificial intelligence although now its has brought revolution in technology and other fields?
1
vote
1answer
19 views

Overfitted model performs better in test set

There are two models for the same task: model_1: 98% accuracy on training set, 54% accuracy on test set. model_2: 48% accuracy on training set, 47% accuracy on test set. From the statistics above we ...
1
vote
0answers
34 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
12 views

Is there any deep learning object detection algorithms that can work without bounding boxes annotated data?

For example Haar Cascade can be trained using only positive and negative examples, you don't need any bounding box annotations. But it not a deep learning approach. Another example can be the most ...
1
vote
1answer
49 views

Chess policy network

I am interested in making a simple chess engine using neural networks. I already have a fairly good value network but I can't figure out how to train a policy network. I know that Leela chess zero ...
0
votes
0answers
13 views

Impact of changing margin loss with cross entropy loss in capsule networks

What are the impacts if one changes margin loss with cross entropy loss in capsule networks for mnist classification? Intuitive answers are welcome