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
3answers
3k views

When using neural networks to detect features in an image, how can locate that specific feature in the original image?

I understand how a neural network can be trained to recognise certain features in an image (faces, cars, ...), where the inputs are the image's pixels, and the output is a set of boolean values ...
41
votes
3answers
27k views

How can neural networks deal with varying input sizes?

As far as I can tell, neural networks have a fixed number of neurons in the input layer. If neural networks are used in a context like NLP, sentences or blocks of text of varying sizes are fed to a ...
0
votes
2answers
3k views

Simple text recognition with neural network [closed]

In my attempt at trying to learn neural network and machine learning I'm am trying to create a simple neural network which can be trained to recognise one word from a given string (which contains only ...
12
votes
2answers
583 views

Should deep residual networks be viewed as an ensemble of networks?

The question is about the architecture of Deep Residual Networks (ResNets). The model that won the 1-st places at "Large Scale Visual Recognition Challenge 2015" (ILSVRC2015) in all five main tracks: ...
3
votes
1answer
416 views

Which neural networks can be used only for storing and retrieving information?

Is there a neural network(NN) system or architecture which can be used for only storing and retrieving information. For example; to store whole Avatar movie in HD format inside a neural network and ...
9
votes
4answers
7k views

How to classify data which is spiral in shape?

I have been messing around in tensorflow playground. One of the input data sets is a spiral. No matter what input parameters I choose, no matter how wide and deep the neural network I make, I cannot ...
8
votes
3answers
1k views

Do deep learning algorithms represent ensemble-based methods?

Shortly about deep learning (for reference): Deep learning is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep ...
14
votes
3answers
949 views

Has anyone thought about making a neural network ask questions, instead of only answering them?

Most of the people is trying to answer question with a neural network. However, has anyone came up with some thoughts about how to make neural network ask questions, instead of answer questions? For ...
2
votes
1answer
770 views

Are FFNN (MLP) Lipschitz functions?

My question is regarding standard dense-connected feed forward neural networks with sigmoidal activation. I am studying Bayesian Optimization for hyper-parameter selection for neural networks. There ...
3
votes
2answers
100 views

Are ANNs just highly distributed lossy compression schemes?

Conceptually speaking, aren't artificial neural networks just highly distributed, lossy compression schemes? They're certainly efficient at compressing images. And aren't brains (at least, the ...
6
votes
5answers
291 views

Emulating human brain - with analogous NN chips

Considering the answers of this question, emulating a human brain with the current computing capacity is currently impossible, but we aren't very far from it. Note, 1 or 2 decades ago, similar ...
15
votes
1answer
341 views

Differences between backpropagation techniques

Just for fun, I am trying to develop a neural network. Now, for backpropagation I saw two techniques. The first one is used here and in many other places too. What it does is: It computes the ...
9
votes
2answers
691 views

Power efficiency of human brains vs. neural networks

How big artificial neural networks can we run now (either with full train-backprop cycle or just evaluating network outputs) if our total energy budget for computation is equivalent to human brain ...
1
vote
1answer
167 views

How can thought vectors be used outside of an Artificial Neural Network (ANN) context?

We hear a lot today about how thought vectors are the Next Big Thing in AI, and how they serve as the underlying representation of thought/knowledge in ANN's. But how can one use thought vectors in ...
4
votes
1answer
175 views

What can be done to correct for sampling bias introduced from (noisy) training data while training a DNN?

The obvious solution is to ensure that the training data is balanced - but in my particular case that is impossible. What corrections can one perform in such a scenario? I know that my training data ...
6
votes
1answer
145 views

How do Artificial Neural Networks store data compared to Biological Neural Networks?

Do scientists know by what mechanism biological brains/biological neural networks store data? I was thinking about @kenorbs question about implanting nanobots to build an AGI on top of human wetware. ...
9
votes
4answers
2k views

How does using ASIC for the acceleration of AI work?

We can read on Wikipedia page that Google built a custom ASIC chip for machine learning and tailored for TensorFlow which helps to accelerate AI. Since ASIC chips are specially customized for one ...
4
votes
2answers
467 views

Can neural networks be better than human experts at prediction of greyhound racing results?

Were there any studies which checked the accuracy of neural network predictions of greyhound racing results, compared to a human expert? Would it achieve a better payoff?
13
votes
2answers
361 views

How should I encode the structure of a neural network into a genome?

For a deterministic problem space, I need to find a neural network with the optimal node and link structure. I want to use a genetic algorithm to simulate many neural networks to find the best network ...
1
vote
1answer
97 views

What are the approaches to teach AI to how to render html page based on its source code?

I'm wondering, instead of implementing new web browsers over and over again with millions line of code which is very difficult to manage, would it be possible to use ANN or GA algorithm to teach it ...
3
votes
1answer
33 views

Research for misbehavior detection in WiFI networks

I'm looking for research which discusses misbehavior detection in public internet access networks using ANN approaches. So it can be used by ISP to detect suspicious users connected to their network.
1
vote
1answer
145 views

What are the minimum requirements to call something artificial neural network?

I've found this short Python code which implements neural network in 11 lines of code: ...
2
votes
1answer
724 views

Using AI capabilities for coding review [closed]

Are there any existing approaches for using artificial neural networks (ANN) or evolutionary algorithm (EA) for detecting coding standard violations? Which one would be more suitable? I don't have ...
8
votes
2answers
120 views

How do evolutionary algorithms have advantages over the conventional backpropagation methods?

How does employing evolutionary algorithms to design and train artificial neural networks have advantages over using the conventional backpropagation algorithms?
2
votes
3answers
148 views

How exactly is the value of each node determined? Is it the same formula throughout the network?

When it comes to neural networks, it's often only explained what abstract task they do, say for example detect a number in an image. I never understood what's going on under the hood essentially. ...
16
votes
1answer
341 views

Could a Boltzmann machine store more patterns than a Hopfield net?

This is from a closed beta for AI, with this question being posted by user number 47. All credit to them. According to Wikipedia, Boltzmann machines can be seen as the stochastic, generative ...
4
votes
2answers
4k views

Which neural network has capabilities of sorting input?

I believe normally you can use genetic programming for sorting, however I'd like to check whether it's possible using ANN. Given the unsorted text data from input, which neural network is suitable ...
1
vote
1answer
78 views

How close we are to replacing guide dogs with AI?

Were there any successful attempts to replace poor guide dogs used for blind people with AI to achieve similar rate of success? I guess dogs could be easily distracted and not reliable for every ...
3
votes
2answers
103 views

How to separate image recognition from logic?

For example I would like to implement transparent AI in the RTS game which doesn't offer any AI API (like old games), and I'd like to use image recognition algorithm for detecting the objects which ...
69
votes
8answers
11k views

Do scientists know what is happening inside artificial neural networks?

Do scientists or research experts know from the kitchen what is happening inside complex "deep" neural network with at least millions of connections firing at an instant? Do they understand the ...
13
votes
2answers
574 views

How can I automate the choice of the topology of a neural network for an arbitrary problem?

Assume that I want to solve an issue with a neural network that either I can't fit to already existing topologies (perceptron, Konohen, etc) or I'm simply not aware of the existence of those or I'm ...
9
votes
3answers
475 views

Is it beneficial to represent a neural net as a matrix?

A neural network is a directed weighted graph. These can be represented by a (sparse) matrix. Doing so can expose some elegant properties of the network. Is this technique beneficial for examining ...
5
votes
1answer
2k views

How to avoid falling into the “local minima” trap?

How do I avoid my gradient descent algorithm into falling into the "local minima" trap while backpropogating on my neural network? Are there any methods which help me avoid it?
3
votes
2answers
63 views

Is there a way to define the boundaries of the optimal size of a training set?

At a related question in Computer Science SE, a user told: Neural networks typically require a large training set. Is there a way to define the boundaries of the "optimal" size of a training set ...
3
votes
2answers
3k views

Can PHP be considered as a serious programming language for AI? [closed]

I read some information1 about attempts to build neural networks in the PHP programming language. Personally I think PHP is not the right language to do so at all probably because it's a high-level ...
11
votes
1answer
257 views

What are the advantages of complex-valued neural networks?

During my research, I've stumbled upon "complex-valued neural networks", which are neural networks that work with complex-valued inputs (probably weights too). What are the advantages (or simply the ...
34
votes
5answers
21k views

How does Hinton's “capsules theory” work?

Geoffrey Hinton has been researching something he calls "capsules theory" in neural networks. What is this and how does it work?
9
votes
2answers
779 views

How much of Deep Mind's work is actually reproducible?

Deep Mind has published a lot of works on deep learning in the last years, most of them state-of-the-art on their respective tasks. But how much of this work has actually been reproduced by the AI ...
6
votes
1answer
2k views

Did Minsky & Papert know that multilayer perceptrons could solve XOR?

In their famous book entitled "Perceptrons: An Introduction to Computational Geometry", Minsky and Papert show that a perceptron can't solve the XOR problem. This contributed to the first AI winter, ...
6
votes
2answers
471 views

What are the limits to what can be learnt using a backpropagation neural network?

In 1969, Seymour Papert and Marvin Minsky showed that Perceptrons could not learn the XOR function. This was solved by the backpropagation network with at least one hidden layer. This type of ...
10
votes
3answers
383 views

Are neural networks and its variants the only way to reach true artificial intelligence?

According to my knowledge most of the current artificial intelligence study uses of some kind of neural network or its variants. A good example would be DeepMind's alphago which I believe is a deep ...
4
votes
1answer
72 views

Can abstractive summarization be achieved using neural networks?

Text summarization is a long-standing research problem that was "ignited" by Luhn in 1958. However, a half century later, we still came nowhere close to solving this problem (abstractive ...
13
votes
2answers
218 views

Optimal number of layers in a neural network?

How to decide the optimum number of layers to be created while implementing a Neural Network (Feedforward, back propagation or RNN)?
17
votes
3answers
1k views

Are there any computational models of mirror neurons?

From Wikipedia: A mirror neuron is a neuron that fires both when an animal acts and when the animal observes the same action performed by another. Mirror neurons are related to imitation learning, ...
23
votes
5answers
14k views

Is it possible to train the neural network to solve math equations?

I'm aware that neural networks are probably not designed to do that, however asking hypothetically, is it possible to train the deep neural network (or similar) to solve math equations? So given the ...
9
votes
2answers
2k views

Can autoencoders be used for supervised learning?

Can autoencoders be used for supervised learning without adding an output layer? Can we simply feed it with a concatenated input-output vector for training, and reconstruct the output part from the ...
2
votes
2answers
232 views

Can we ever achieve hypercomputation using recurrent neural networks?

It is proved that a recurrent neural net with rational weights can be a super-Turing machine. Can we achieve this in practice ?
3
votes
1answer
242 views

In what ways can connectionist A.I. be integrated with GOFAI?

In what ways can connectionist artificial intelligence (neural networks) be integrated with Good Old-Fashioned A.I. (GOFAI)? For instance, how could deep neural networks be integrated with knowledge ...
8
votes
2answers
614 views

What's the difference between hyperbolic tangent and sigmoid neurons?

Two common activation functions used in deep learning are the hyperbolic tangent function and the sigmoid activation function. I understand that the hyperbolic tangent is just a rescaling and ...
4
votes
1answer
100 views

What is the significance of weights in a feedforward neural network?

In a feedforward neural network the inputs are fed directly to the outputs via a series of weights. What purpose do the weights serve and how are they significant in this neural network?