Questions tagged [artificial-intelligence]

Artificial Intelligence (AI) is a topic in computer science that deals with the study / creation of intelligent machines. Use this tag for on-topic questions that have an AI aspect.

Filter by
Sorted by
Tagged with
2
votes
1answer
148 views

Transfer Function on Neural Network

Do different Transfer Function produce different prediction in neural network model? How do we know which transfer function suitable for the data we used?
0
votes
0answers
19 views

Optimizing individuals by direct comparison (fitness is dependent on other individuals)

I'm participating in an AI challenge and would like to use machine learning or genetic algorithms to optimize my strategy. The strategy is represented by a list of floats (size=7) which are weights ...
0
votes
1answer
50 views

Deep learning Model

Is this model good in terms of Accuracy? Test accuracy is better than training. Training accuracy = 98.55% and Test accuracy = 99.16%.
1
vote
1answer
537 views

What is the update rule for hidden layer if softmax activation function is used?

I am trying to understand how backpropagation works. I understood the basic concepts and became familiar with derivation of equations for sigmoid activation function. Specifically for hidden layers, ...
4
votes
0answers
516 views

How does a maze game / directed paths map to a Neural Network?

I am trying to understand how a maze game's possible paths and possible moves are mapped out in a Neural Network. Let's take this example here: http://cdn.intechopen.com/pdfs-wm/10916.pdf Agent can ...
3
votes
1answer
50 views

Looking for interdisciplinary research topic [closed]

TL;DR: Are there any areas that combine (1) statistics/ML, (2) computation theory, (3) set/type theory, and (4) real/functional analysis? I apologize if I did not accurately categorize the domains ...
1
vote
1answer
718 views

Bayesian updating logNormal distribution

I have a question regarding statistical updating. Basically I have a probability density function of a random variable X and, at each time step, I obtain a new sample $x_i$ belonging to this ...
0
votes
1answer
66 views

Reinforcement learning actions and decisions

What RL does actually update in order to reach always a desired output? Is it true that the inputs (or the Agent actions) have to be re-updated whenever an RL reaches a bad output (or decision) based ...
1
vote
2answers
65 views

How do I cluster/group people together given their durations for an given event?

I am new to machine learning and do have a very large dataset for a set of 100 people over a period of 1 year. and the goal is to find out who are buddys based on their lunch times. I have the ...
13
votes
0answers
828 views

Bayesian Q-learning

Suppose that, for every state $s$, there is a set of actions $\mathcal{A}(s)$ that can be chosen in that state. Let $Q(s, a)$ denote the expected utility of choosing action $a \in \mathcal{A}(s)$ in ...
1
vote
1answer
151 views

Fuzzy logic and Artificial Intelligence

Is it correct to classify fuzzy logic under Artificial Intelligence i.e. can fuzzy logic be considered a concept under the purview of of AI. If not how can we classify fuzzy logic.
4
votes
1answer
891 views

Mixing Convolutional Neural Networks and “regular” Feed Forward Neural Networks

I've just been watching some computerphile videos on ANNs. And in one of them the guy talked about figuring out the price of a house according to a picture. At that moment an idea came into my head. ...
3
votes
1answer
3k views

Is there a heuristic for determining the size of a fully connected layer at the end of a CNN?

For example, in VGG/OxfordNet, the fully connected (dense) layers that precede the final classification layer are of size 4096. Similarly, in an AlexNet ... the number of neurons in the network’...
2
votes
1answer
725 views

Ideal sample class ratio for training CNN for 2 class classification

What should the ratio of the positive to negative samples be if I am training a CNN for binary classification?
0
votes
1answer
605 views

Perfect recall and spurious states in hopfield networks

In Hopfield networks, one can apparently load perfect recall into the network (by having enough neurons compared to patterns). (Source) However, at the same time, it appears that spurious states (i.e....
1
vote
1answer
428 views

Differences between precision and recall

If you developed two classifiers for an intrusion detection system (IDS) to detect worms in a network, and the precision and recall are 90% and 40% respectively for the first, and 60% and 80% ...
2
votes
2answers
2k views

Is it possible to make the non-separable data more separable by any methods of feature selection, extraction or transformation?

Could these data (in the figure below) be separated by any means of feature extraction, transformation, or it's just a waste of time to make the three classes separable if they "in fact" weren't ...
1
vote
3answers
5k views

How to achieve a nonlinear decision boundary?

What would be the architecture of the neural net that would produce the following nonlinear decision boundary? Will the hidden layer compute some nonlinear combinations of inputs? or it will create ...
1
vote
0answers
78 views

Alternatives to Job Sequencing using Optimization

I have to N jobs to be assigned in a sequence to a Machine/User. I know using optimization technique we can find an optimal sequence. But in my case there are lot of parameters (some to be minimized (...
1
vote
1answer
200 views

what would be the suitable machine learning algorithm for Pattern/Event Detection for the following Time Series Data?

Time Series Data Plot Please refer to the above link to understand the Data View. Background for the data : It is the data of a single variable from a machine like Bulldozer(Pressure of the ...
0
votes
1answer
122 views

RandomForest failing to learn single-factor, 'linearly separable' model

I am using randomForest (the R package) to train a multi-factor, binary- classification model. In trying to dissect performance, I started feeding in individual factors to see how the RF treated them....
1
vote
1answer
262 views

What does make SVM a “soft computing” method?

Soft computing is defined in [1] by the capability of "operating with uncertain, imprecise and incomplete information in a manner that reflects human thinking". So, based on my limited understanding, ...
2
votes
1answer
2k views

When implementing dropout in neural networks with SGD, how does one calculate the gradient?

Specifically, I know that in SGD one sums all the gradients for weights/biases for each minibatch and divides by the mini batch size, would one do the same thing for dropout networks? Or would they ...
1
vote
1answer
845 views

Questions about understanding convolutional neural network (with Tensorflow's example)

I've recently seen tutorials from google's tensor flow. It was about convolutional network and way of convolution way slightly different from what I first learned. https://www.tensorflow.org/...
3
votes
1answer
4k views

Activation Function for First Layer Nodes in an ANN

In an artificial neural network, neurons take inputs from their previous layer, transform this signal using an activation function (in my case, the sigmoid function), and send this transformed signal ...
0
votes
1answer
106 views

Is it possible to predict stock values using one year stock data

I'm building a project that gathers the maximum amount of historic data about a certain company and try to predict its future market stock values. I have company's 1 years stock values like ...
93
votes
5answers
69k views

What is the difference between off-policy and on-policy learning?

Artificial intelligence website defines off-policy and on-policy learning as follows: "An off-policy learner learns the value of the optimal policy independently of the agent's actions. Q-learning ...
0
votes
1answer
652 views

Motivation behind parameter sharding for Downpour SGD

Why does the Downpour model shard the parameters into separate groups? Is there any advantage of making one cluster responsible for changing only certain parameters?
0
votes
1answer
1k views

Spark MLLib's Word2Vec cosine similarity greater than 1

On the spark implementation of word2vec, when the number of iterations or data partitions are greater than one, for some reason, the cosine similarity is greater than 1. In my knowledge, cosine ...
93
votes
8answers
74k views

Objective function, cost function, loss function: are they the same thing?

In machine learning, people talk about objective function, cost function, loss function. Are they just different names of the same thing? When to use them? If they are not always refer to the same ...
4
votes
1answer
407 views

Do models for artificial neural network growth, e. g. adaptive hidden layers, exist?

Let's say we have a trained neural network that works. Training was performed with a set of given inputs and outputs (with training/validation division). Now a new input node or output node is to be ...
2
votes
1answer
155 views

Interactive reinforment learning in R

Which library in R allows to do interactive temporal (depending on sequence of events) learninig? I need to perform a task similar to game plaing as shown in this example: http://cs.stanford.edu/...
5
votes
0answers
333 views

Interpreting hidden layer representations in ANNs

I'm using the fann library for writing an Artificial Neural Network in C++. I trained my network for the task of recognizing faces inside a set of 128x128 .png images, using three different algorithms:...
4
votes
2answers
181 views

How are game difficulty levels programmed in TD gammon?

I understand that Temporal Difference player is trained by making it play against itself. In such a case, how are game difficulty levels programmed? Can fewer training iterations successfully create ...
5
votes
1answer
2k views

Q-Learning stuck on a nearly toy problem

I'm using Q-Learning to train a MDP-based form filling dialogue manager. Right now it operates in a nearly toy setup with the total of 210 states (generally corresponding to form filling progress) and ...
0
votes
2answers
1k views

Text Pattern Recognition - Model building using R

I have a training dataset which has two columns which has around 70 values. “PNRNo” whose values like UT767G, CADA, 4I9I59, 4BH5TW…(typical PNR number patterns) I have created one more factor ...
4
votes
2answers
6k views

What is the difference between Sigmoid neurons and Stochastic binary neurons?

Both have the same equation : the logistic unit. Sigmoid output a ral-valued number between 0 and 1 and Stochastic binary neuron a probability between 0 and 1 too. Apart from the name/type given to ...
2
votes
2answers
80 views

How effective is randomly/algorithmically generating exorbitant amounts of training data for a neural network?

There are some problems of which the generating of data is easy whereas the inverse is not. For example, use a 3D game engine to render some randomly generated objects with some random changes and ...
2
votes
1answer
155 views

Why are Hinton's multilayer deep-learning networks stochastic?

First I'll sum up my intuitive (beginner) understanding of his deep-learning architecture. A short summary can be listened to on Coursera in the 5 minute video. We start with several layers of ...
3
votes
1answer
104 views

What Percent of Neural Network is used while processing a single image [closed]

What percent (on average) of entire Neural network (say, AlexNet) is actually used while processing a single image. There should only a very small amount of network that should actually be utilized ...
3
votes
2answers
1k views

Are fixed bias neurons or biased neurons better?

When building an artificial neural network, there seems to be two differing philosophies in usage of biases. There are those groups that propose neural networks with a fixed bias neuron with a ...
5
votes
2answers
3k views

In a neural network, do biases essentially need updates when being trained?

While building a neural network with one hidden layer, the question arose whether or not to update the biases during backpropagation. I'm basically trying to save up on memory, so my question was and ...
24
votes
4answers
5k views

What can we learn about the human brain from artificial neural networks?

I know my question/title is not very specific, so I will try to clearify it: Artificial neural networks have relatively strict designs. Of course, generally, they are influenced by biology and try to ...
0
votes
3answers
653 views

Basic ANN questions [closed]

So I've just recently gotten into artificial neural networks, and I have a couple of questions that I can't seem to find addressed anywhere. Firstly, this one is more specific to image recognition, ...
4
votes
1answer
84 views

Having trouble creating my Neural Network inputs

I'm currently working on a neural network that should have N parameters in input. Each parameters can have M different values (discrete values), let's say {A,B,C,…,M}. It also has a discrete number of ...
0
votes
1answer
159 views

Opportunities in machine learning and computational intelligence [closed]

I'm not sure this is the right site to post my question. If not, please direct me to the right one. I'm interested in machine learning and computational intelligence. I've spent the last year of my ...
-2
votes
1answer
2k views

Somebody explain Training, Testing and Validation Test of Artificial Neural Network [duplicate]

What is the procedure of Training, Testing and Validation Test? Explain it thoroughly. Or give some link for related articles
5
votes
5answers
3k views

Find Neural Network Inputs Given Outputs

I've trained a neural network with two inputs, a single hidden layer with two neurons, and one output using a bipolar sigmoid activation function. If a single input is known, how would I determine the ...
-1
votes
1answer
697 views

Types of artificial intelligence with good results [closed]

I have been looking into artificial intelligence for some time now. I am wondering what branches are still in active research and have some good/interesting results. The two that I have looked in so ...
1
vote
0answers
84 views

Which ML algorithm is suitable for the following problem?

Assume i have x states each defined by an n-dimensional feature vector. In addition i have a set of actions which can be taken in each state resulting in a state action score. What would be an ...