Questions tagged [neural-networks]
The neural-networks tag has no usage guidance.
44 questions
22
votes
4
answers
6k
views
How do AI developers for LLM fix bugs when the LLM misbehaves, given that they cannot control what the LLM learns from the data?
The traditional non AI software with if-then-else and loop statements can be fully controlled. In contrast, machine learning software behaviour is unpredictable since the developer cannot control what ...
- 331
3
votes
1
answer
116
views
Is the output of all kinds of machine learning models binary or can the end values be interpreted in other ways?
I'm just wrapping my head around the topic and building a simple neural network from scratch as I go. I'm trying out different data types to hold weights, values and biases as well as different ...
- 221
-2
votes
1
answer
91
views
Can't understand activation function
I have been trying to learn neural networks from scratch
(in Python). Wherever they talk about neural networks, I don't get the meaning of activation of a neuron, and need to understand the basic ...
- 105
-2
votes
1
answer
87
views
When to update neural network model in production?
I have a trained neural network about to go into production, and am wondering about when to update it with new data.
Say, if the "Similar questions" banner when asking a question is ...
- 23
-1
votes
1
answer
138
views
Can somone explain facebook starspace?
I have googled enough for days but i cant find a clear intuitive document about this embedding technique.
In their paper they say : We present StarSpace, a general-purpose neural embedding model that ...
-2
votes
1
answer
236
views
Is there a way to get rid of loop for layers in a neural network
I have being learning about deep neural networks and how the increase in hidden layers give better results. but the problem that i found was we usually get rid of loops in calculations by using ...
- 111
0
votes
1
answer
193
views
How to end a sentence in neural networks
I have a simple neural-network which can create new text out of words which are likely to come after a specific word.
The code lacks of comma placement and punctuation.
It also can't transform a ...
- 121
3
votes
1
answer
4k
views
Distinction between AI, ML, Neural Networks, Deep learning and Data mining
I have recently started exploring the field of machine learning (ML). I think I understand the difference between ML and AI at high level, but I wanted to understand more accurately the differences ...
- 457
3
votes
0
answers
94
views
Software design strategy for a machine learning tool that outputs a subset of the text input (Information Extraction)?
Let's say I have thousands of pdfs that are each about 30k words written in conversational English. In each of the pdfs there is a name / names of a person/people who snowboard. There are also many ...
- 39
0
votes
1
answer
314
views
How do you evolve a neural network?
I've read about NEAT/Evolutionary Artificial Neural Networks/Genetic Algorithms.
I understand the concept of choosing the fittest neural networks and breeding them to produce another one, but how ...
- 220
2
votes
2
answers
826
views
Test Driven Development for Stochastic algorithms?
this is similar, but no the same as this post, which was the closest question I could find on this. I don't even see that answer as satisfactory for the question asked in that thread let alone TDD. ...
- 1,310
0
votes
3
answers
207
views
Can I train further a trained neural network only with some new character?
I would like to make a semi-automatic OCR software for offline handwritten documents, where the OCR tries to recognize the words and the user has the ability to correct the fails of the recognizer by ...
1
vote
1
answer
834
views
How to have a neural network deal with a variable size input
I'm trying to write a program in Python that will take an input of a .wav (sound) file, and determine whether the user is saying "yes" or "no".
The issue is that the sound files are not always the ...
- 677
4
votes
1
answer
522
views
Double neural network architecture for starcraft AI programming endeavour
Please take a look at this AI system architecture proposal:
As you can see this is a multi-agent AI system for starcraft brood war that utilizes BWAPI AI framework, and I proposed this idea for the ...
- 43
2
votes
1
answer
294
views
Creating a neural network to solve inequality
I am just testing out a simple neural network with a single neuron. To classify if a number X between 1..10 is greater than a number N. N is a constant for example N=3.
Given my input X and a ...
- 263
0
votes
1
answer
880
views
How to run 2-layer perceptron to solve XOR
XOR is not solvable by using a single perceptron with standard scalar product and unit step function.
This article suggests using 3 perceptron to make a network:
http://toritris.weebly.com/perceptron-...
- 103
6
votes
2
answers
13k
views
What is identity mapping in neural networks
I came across the term identity mapping in some papers about neural networks but am not sure what it is supposed to mean in that context.
I'm guessing it means to map a sort of input to an output?
I ...
- 171
4
votes
2
answers
3k
views
Why do convolutional neural networks use so much memory?
I heard that one of the main problems applying neural style to high resolution images is the huge amount of memory that would use.
Also I just configured a network using tiny-cnn
This is my ...
- 608
6
votes
2
answers
6k
views
Why my Neural Network Accuracy is 100%?
I wanna ask about Neural Network.
I have a research and programming about Neural Network using Backpropagation algorithm for prediction. My input data using binary form. But, i'm still confuse, ...
- 63
1
vote
0
answers
48
views
How do you feed sets of connected data elements to an artificial neural network?
I'm currently working on a neural network to try to predict movements of electricity prices in a big city with multiple power companies to choose from. I know from a friend in the industry that power ...
- 1,169
3
votes
2
answers
218
views
Neural networks: No solutions for test data possible?
So there are two ways of teaching a neural network as far as I am aware of.
You supply the AI with test data and the correct solution to the problem. After some time the network will be able to get ...
- 297
5
votes
1
answer
8k
views
What are the practical uses of a neural network?
Even as an outsider to neural network development, they still seem to be a hot topic... I get lots of projects I see being starred on my GitHub homepage relating to neural networks.
These projects ...
user160274
3
votes
1
answer
5k
views
Vector input for Artificial Neural Network?
My problem is fairly complex, so here is a similar, simplified example.
Let's say you wanted to predict the Miles Per Gallon (fuel consumption) of a car, based on the following information: you have ...
- 37
26
votes
4
answers
11k
views
Calendar/Planning algorithm
I'm facing a problem I'm not sure how to approach. I have to generate a calendar for employees, each of them having specific work constraints (some personal, some common)
What I'm working with :
I ...
- 2,183
2
votes
1
answer
107
views
To what values should you initialize the neurons and connection strengths in a neural network?
The values of all of the neurons in my neural network are initialized to 0 and the connection strengths between the neurons are set to randomly generated floats, between 0 and 1. I have seen other ...
- 290
3
votes
1
answer
177
views
How can you write an activation function in a neural network to handle a layer architecture of arbitrary dimensions?
I am making a neural network in Clojure that can take an array of integers,and return a data structure representing the layers of a neural network: so (make-layers [1 4 5]) would evaluate to:
[[0] ...
- 290
1
vote
1
answer
525
views
An Introductory Tutorial for Neural Net Backpropagation with Simplified Math
I built a neural net, and planned on optimizing the weights using a genetic algorithm. I was informed though, that this isn't a good idea, and to look into backpropagation.
I searched around, and ...
- 2,663
2
votes
1
answer
942
views
Is the output of a neural net supposed to have had the activation function applied to it?
TL; DR:
Is the output from a feed-forward neural a direct result of the activation function?
I.e: If the activation function is the sigmoid function, will the output always be between 0 and 1?
I'm ...
- 2,663
1
vote
0
answers
79
views
How to evaluate a recurrent connection in an artificial neural network?
I just can't understand how should I compute the output of a neural network, which contains a recurrent connection.
So here is an example:
(i_1,2 are the input values, w_1,2,3,r are the ...
- 119
3
votes
1
answer
134
views
What parallelization methods can make neural nets train faster?
A fairly straightforward way (on a theoretical level, at least) of parallelizing artifical neural networks (ANNs) would be to divy up the batches of training examples during every epoch so that ...
- 1,881
2
votes
1
answer
510
views
What type of neural network is suitable for simulating brain of virtual organism? [closed]
A while ago I was experimenting with evolving virtual creatures using neural network + genetic algorithm, but that didnt go well (simulation speed was too slow, mainly because bad programming habbits ...
- 29
1
vote
0
answers
1k
views
Neural network converges to 0.5 for XoR
I'm coding a neural network in C for an OCR project. Before testing with character recognition, I'm making it learn the XoR operation. Although, the results I'n getting always converges to 0.5 instead ...
- 143
0
votes
2
answers
121
views
Could one sample be enough for a perceptron training?
I need to compare a picture and decide whether or not it is similar to another one. In this case, I would like to use a simple perceptron that compares pixelmaps of both pictures. But I have only very ...
- 4,936
2
votes
1
answer
253
views
Support Vector Machines as Neural Nets?
This is more of a conceptual question.
I have learned about Neural Nets, and I have some clue as to how Support Vector Machines work. I read somewhere however that given the appropriate kernel (is ...
- 131
1
vote
2
answers
741
views
Neural network input preprocessing
It's clear that the effectiveness of a neural network depends strongly on the format you give it to work with. You want to pre-process it into the most convenient form you can algorithmically get to, ...
- 263
5
votes
2
answers
381
views
How to solve this problem- Neural Net? Fuzzy? Other?
Hi I have a programming problem that I would like to solve using some artificial intelligence technique. I really dont know where to start. I would like some guidance as to what methodology to pursue.
...
- 153
1
vote
1
answer
2k
views
How to design a calculator from scratch [closed]
A basic calculator can perform a wide variety of operations. How does the claculator 'get' the concept of adding two numbers in the same way a human does? I dont think people that make claculators ...
- 1,195
7
votes
5
answers
619
views
Type of AI to tackle this problem?
I posted this on stackoverflow but want to get your recommendations as well as a user on overflow recommended I post it here.
I'm going to say from the beginning that I am not a programmer, I have a ...
- 173
1
vote
1
answer
67
views
Create association between informations
I deployed a project some days ago that allow to extract some medical articles using the results of a questionnaire completed by a user. For instance, if I reply on questionnaire I'm affected by ...
- 503
0
votes
3
answers
3k
views
Can neural network discover rng patterns
Can neural network find connections beetween numbers generated by random number generator without knowing about it's seed and predict this rng's next numbers with more sucess then randomly guessing? I ...
- 111
6
votes
1
answer
167
views
How to determine the source of a request in a distributed service system?
Map/Reduce is a great concept for sorting large quantities of data at once. What to do if you have small parts of data and you need to reduce it all the time?
Simple example - choosing a service for ...
- 561
2
votes
4
answers
2k
views
Sign Language Recognition [closed]
I am a final year undergraduate student of Information Technology. My team and I have taken up "Sign Language Recognition" as our Final Year Project. We have just started with it and we are in the ...
- 599
11
votes
3
answers
14k
views
What is a Neural Network in simple words [closed]
Can you please explain neural networks in simple words with an example?
- 541
5
votes
3
answers
869
views
Can symbolic AI 'learn' a data model?
Perceptrons, a simple form of supervised machine learning, must be trained with a set of known good inputs before they can "learn" by adjusting internal weights assigned to inputs, based on the ...
- 380