Questions tagged [neural-networks]

For questions about a artificial networks, such as MLPs, CNNs, RNNs, LSTM, and GRU networks, their variants or any other AI system components that qualify as a neural networks in that they are, in part, inspired by biological neural networks.

Filter by
Sorted by
Tagged with
2
votes
0answers
72 views

Multiple sets of input in Neural network (or other form of ML)

I'm currently working on a research project where I try to apply different kinds of Machine Learning on some existing software I wrote a few years ago. This software will scan for people in the room ...
6
votes
1answer
356 views

Why not teach to a NN not only what is true, but also what is not true?

I'm not a person who studies neural networks, or does anything that is related with that area, but I have seen a couple of seminars, videos (such as 3Blue1Brown's Series), and what I am always told is ...
2
votes
1answer
546 views

How to change the backward pass for an LSTM layer that outputs to another LSTM layer?

I am currently trying to understand the mathematics in Ger's paper Long Short-Term Memory in Recurrent Neural Networks. I have found the document clear and readable so far. On pg. 21 of the pdf (pg. ...
13
votes
2answers
6k views

How to choose an activation function?

I choose the activation function for the output layer depending on the output that I need and the properties of the activation function that I know. For example, I choose the sigmoid function when I'm ...
3
votes
2answers
1k views

Training Multi class classification (One-vs-all) on Neural network

I am very new to Machine learning and following the course offered by Andrew Ng.I am very confused How we train our neural network on Multi class Classification(suppose take K classes).For K classes ...
4
votes
1answer
349 views

Representing inputs and outputs for a card game neural network

I'm attempting to create an AI for a card game using reinforcement learning. The basics of the game are that you can have (theoretically) up to 35 cards in your hand, you can also have to up to 35 ...
10
votes
4answers
781 views

What are the models that have the potential to replace neural networks in the near future?

Are there possible models that have the potential to replace neural networks in the near future? And do we even need that? What is the worst thing about using neural networks in terms of efficiency?
2
votes
1answer
52 views

Automatic image classification

I'm a complete newbie to NNs, and I need your advice. I have a set of images of symbols, and my goal is to categorize and divide them into groups of symbols that look alike. Without teaching NN ...
1
vote
1answer
27 views

Restoration of localized damaged areas (time signals, but guess also applicable to images)

I am starting to study the capabilities of neural networks for the reconstruction/restoration/... of communication signals. I am feeding my neural network with a signal which has some parts which ...
7
votes
2answers
2k views

Structure of LSTM RNNs

I have some very basic questions here. This is probably because I didn't read the relevant documents closely enough. If I used some terminology incorrectly, please point them out. Thank you! For ...
7
votes
3answers
324 views

CNN's vs Densely Connected NN's

In image classification we are generally told the main reason of using CNN's is that densely connected NN's cannot handle so many parameters (10 ^ 6 for a 1000 * 1000 image). My question is, is there ...
1
vote
1answer
129 views

How should I encode the input which are 5 cards from a deck of 52 cards?

How should I design my input layer for the following classification problem? Input: 5 cards (from a deck of 52 cards) in a card game; Output: some classification using a neural network How ...
4
votes
2answers
272 views

Wrong usage of 'Pose' in Matrix Capsules with EM?

In traditional computer vision and computer graphics, the pose matrix is a 4x4 matrix of the form ...
3
votes
1answer
943 views

Number of Neuron in Q-Learning of Chess

So I just read about deep Q-Learning which is using a neural network for optimization instead of Q-table. I saw the example here: https://yanpanlau.github.io/2016/07/10/FlappyBird-Keras.html and he ...
3
votes
2answers
172 views

How can a neural network learn to play sudoku?

I'm just beginning to understand neural networks and I've performed a couple of successful tests with numerical series where the NN was trained to find the odd one or a missing value. It all works ...
2
votes
1answer
90 views

What are the internal concepts incorporated in IBM's Watson platform? [duplicate]

IBM's Watson acts as a template for developing chat-bots with ease (without coding), but what are the methodologies and concepts that have been used to build it?
3
votes
2answers
198 views

How to build my own dataset and model for an LSTM neural network

I have a sort of mathematical problem and I'm not sure which model I should choose to make an LSTM neural network. Currently in my country, there is a system in which certain groups of researchers ...
5
votes
4answers
133 views

What kind of neural network architecture do I use to classify images into one hundred thousand classes?

I have an image dataset where objects may belong to one of the hundred thousand classes. What kind of neural network architecture should I use in order to achieve this?
4
votes
2answers
2k views

What is the purpose of “reshaping it into the shape the network expects and scaling it so that all values are in the [0, 1] interval.”?

I am a deep learning beginner recently reading this book "Deep learning with Python", the example explains the process of implementing a greyscale image classification using MNIST in keras, in the ...
6
votes
1answer
289 views

What is the importance of the endocannabinoid system for cognitive function?

The endocannabinoid system is a very important function of human biology. Unfortunately, due to the illegality of cannabis, it is a relatively new field of study. I have read a few articles about ...
2
votes
1answer
395 views

Why Feature Scaling for skewed contour?

Why is it that the skewed contour (unscaled features) will result in slow performance of gradient descent? In other words, how (or why) will the gradients end up taking a long time before finding the ...
3
votes
2answers
67 views

How to actually teach the ANN the resulting weights of different training inputs?

I thought I have implemented the code (from scratch, no library) for an artificial neural network (first endeavour in the field). But I feel like I miss something very basic or obvious. To make it ...
4
votes
3answers
179 views

Are Neural Net architectures accidental discoveries?

So recently I have been learning about new NN's which are used for specialised purposes like speech recognition, image recognition, etc. The more I discover the more I get amazed by the cleverness ...
2
votes
1answer
86 views

The analysis of the dynamic behaviour of neural networks involving the application of feedback

I am reading the Simon Haykin's cornerstone book, "Neural Networks, A Comprehensive Foundation, Second Edition" and I cannot understand a paragraph below: The analysis of the dynamic behaviour of ...
2
votes
1answer
77 views

If use the weights from previous iteration of a k-fold cross validation to seed a neural network classifier would I be overfitting?

As is done traditionally, I used k-fold cross validation to select and optimize the hyper parameters of my neural network classifier. When it was time to store the final model for future predictions, ...
29
votes
9answers
5k views

Is artificial intelligence vulnerable to hacking?

The paper The Limitations of Deep Learning in Adversarial Settings explores how neural networks might be corrupted by an attacker who can manipulate the data set that the neural network trains with. ...
1
vote
2answers
1k views

Speeding up CNN training

So I built a CNN without any scientific libraries like TensorFlow or Keras (only NumPy). It is taking a huge amount of time to train. What are some of the tricks and tips followed by people to speed ...
4
votes
3answers
531 views

Why should weights of Neural Networks be initialized to random numbers?

Premise Ok, I know that this question was asked before on ai.SE, on stats.SE and also on SO. So I did my homework in checking before posting my question, but none of them has an answer that fully ...
5
votes
2answers
253 views

What do neural connection weights represent 'conceptually'?

I understand how Neural Networks work and have studied its theory well. My question is at the intricacies of Deep Neural networks and perhaps is a bit beyond common understanding (as I have been told (...
1
vote
0answers
79 views

Object recognition by two or more traits that are orthogonal (informally speaking)

I would really appreciate if someone could comment the following method of training neural nets providing them with some meta data (Making them more color prone only if needed, whereas now they're ...
1
vote
1answer
142 views

Kohonen clustering of flowers

I have a question about output of my SOM network. I have trained my network with diffrent size, learning rate and epochs, but my output always can recognise two big clusters. Iris-setosa and Iris-...
4
votes
1answer
159 views

Regression with more than one output, neural network

Currently in my country, there is a system in which certain groups of researchers upload information on products of scientific interest, such as research articles, books, patents, software, among ...
2
votes
2answers
289 views

How to make a fair comparison of a convolutional neural network (cNN) vs a mutlilayer perceptron (MLP)?

I'm working with deep learning on some EEG data for classification, and I was wondering if there's any systematic/mathematical way to define the architecture of the networks, in order to compare their ...
3
votes
1answer
80 views

Implementing AI/ML in customer service

I am working on a task where I am required to automate the customer service request channel. The process is quite typical. A customer queries about a product via email, the person on the front channel ...
4
votes
1answer
145 views

Which functions can be activation functions?

What are the required characteristics of an activation function (in a neural network)? Which functions can be activation functions? For example, which of the functions below can be used as an ...
4
votes
1answer
80 views

Relative compute time for each type of layer in a neural network

Hello, I would like to know whether this picture from the paper: Distributed Training of Deep Neural Networks: Theoretical and Practical Limits of Parallel Scalability valid? Questions: 1) Does ...
5
votes
1answer
4k views

Cross entropy loss function causes division by zero error

I am building a NN for which I am using sigmoid function as the activation function for the single output neuron at the end. Since sigmoid function is known to take any number and return value between ...
3
votes
1answer
61 views

What are good action outputs for reinforcement learning agents acting in a trading environment?

I am trying to build an agent that trades commodities in a exchange setting. What are good ways to map the action output to real world actions? If the last layer is a ...
1
vote
0answers
171 views

Training RL agent on timeseries trading data with Continous Deep Q or NAF

I am writing an MDP based agent that is supposed to learn to place bids and asks in a trading environment. The system requests 2 values (mWh energy and $, both being positive or negative). Every ...
3
votes
3answers
477 views

What is the most effective way to learn natural language processing online? [closed]

There are many books, courses, etc. out there, but not sure which path to take. So what would be the most effective way (shortest) to learn natural language processing online? p.s. I mean learning ...
1
vote
2answers
481 views

How to decrease accuracy from 99% to 80%~85% using keras for training a model

How do I decrease the accuracy value when training a model using Keras; which parameters can I change to decrease the value? My objective is not to actually decrease it, but just to know which ...
1
vote
1answer
99 views

Is it a valid Deep Neural Network?

For a regression task, I have sequences of training data and if I define the layers of deep neural network to be: Layers=[ sequenceInputLayer(featuredimension) reluLayer dropoutLayer(0.05) ...
5
votes
2answers
72 views

Can translational invariance of CNNs be unwanted if object is likely in certain positions?

Various texts on using CNNs for object detection in images talk about how their translation invariance is a good thing. Which makes sense for tasks where the object could be anywhere in the image. Let'...
1
vote
1answer
459 views

How are IOUs for ground truth boxes in YOLO calculated?

I know how IOU works during detection. However, while preparing targets from ground truth for training, how is the IOU between a given object and all anchor boxes calculated? Is the ground truth ...
3
votes
1answer
81 views

Is there a way to predict points on a map?

I have a data set with historical information of some events (let's say event A and event B),these events describe the discovery of land mines, the coordinates of the event and the date of the event; ...
1
vote
0answers
51 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: ...
7
votes
2answers
3k views

Why do we prefer ReLU over linear activation functions?

The ReLU activation function is defined as follows $$y = \operatorname{max}(0,x)$$ And the linear activation function is defined as follows $$y = x$$ The ReLU nonlinearity just clips the values ...
5
votes
2answers
776 views

Artificial Intelligence in Data Compression

What is current research in artificial intelligence and machine learning in the field of data compression? I have done my research on the PAQ series of compressors, some of which use neural networks ...
3
votes
1answer
523 views

what's the definition of singularity in the context of neural networks?

The following paper explains the use of skip connections to break the singularity in deep networks. But, I have not fully understood what singularity is. https://arxiv.org/pdf/1701.09175v8.pdf Any ...
0
votes
1answer
59 views

Teaching a NN to manipulate pseudoRNG over a long time scale?

For speedrunning purposes, I am trying to train a neural network to identify human-executable ways to manipulate pseudo-RNG (in Pokemon Red, for the interested). The game runs at sixty frames per ...

1
21 22
23
24 25
32