Questions tagged [machine-learning]

For questions related to machine learning (ML), which is a set of methods that can automatically detect patterns in data, and then use the uncovered patterns to predict future data, or to perform other kinds of decision making under uncertainty (such as planning how to collect more data). ML is usually divided into supervised, unsupervised and reinforcement learning. Deep learning is a subfield of ML that uses deep artificial neural networks.

Filter by
Sorted by
Tagged with
1
vote
0answers
9 views

Reducing the Number of Training Samples for collaborative filtering in recommender systems

I have the following problem: I am doing some research on the accuracy of recommender algorithms that are mostly used nowadays. So, one way to measure their performance is by checking how well they ...
1
vote
1answer
59 views

Is there a neural network method for time-varying directed graphs?

I want to study NN for time-varying directed graphs. However, as this field has developed relatively recently, it is difficult to find new ways. So the question is, is there any NN that can handle ...
2
votes
0answers
13 views

Product Configuration based on user selection of features and other requirements

Is this a scenario that would work well for a ML/Pattern Recognition Model or would it be easier/faster to just filter from a large DB. I am looking to create a system that will allow users to ...
3
votes
2answers
69 views

How to compute the number of centroids for K-means clustering algorithm given minimal distance?

I need to cluster my points into unknown number of clusters, given the minimal Euclidean distance R between the two clusters. Any two clusters that are closer than this minimal distance should be ...
1
vote
1answer
43 views

How does the CTC loss work?

I am trying to implement CTC loss in Tensorflow, but their documentation is pretty limited. So I am not sure how to approach the problem. I found a good example in Theano: https://github.com/...
2
votes
1answer
49 views

Examples of time-varying graph-structured data in real world

I'm looking for examples of time-varying graph-structured data for time-varying graph CNNs. First, I came up with the idea of infection network. Is there anything more? If possible, I want data that ...
1
vote
0answers
21 views

How is the bias caused by a max pooling layer overcome?

I have constructed a CNN that utilises max pooling layers. I have found with these layers that, should I remove them, my network performs ideally with every output and gradient at each layer having a ...
0
votes
0answers
27 views

Which model to use when selecting objects of interest?

I have a set of polygons for each image. Those polygons consist of four $x$ and $y$ coordinates. For each image, I need to extract the ones of interest. This could be formulated as an Image ...
3
votes
0answers
17 views

What parameters can be tweaked to avoid a generator or discriminator loss collapsing to zero when training a DC-GAN?

Sometimes when I am training a DC-GAN on an image dataset, similar to the DC-GAN PyTorch example (https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html), either the Generator or ...
1
vote
1answer
27 views

In NN, as iterations of Gradient descent increases, the accuracy of Test/CV set decreases. how can i resolve this?

As mentioned in the title I'm using 300 Dataset example with 500 feature as an input. As I'm training the dataset, I found something peculiar. Please look at the data shown below. Iteration 5000 |...
1
vote
0answers
17 views

Random graph as input in geometric deep learning on time-varying graph

I want to create a framework that allows GDL to be applied to time-varying graphs. I came up with the Erdos-renyi model as an example of a time-varying graphs. GDL for graphs takes node information ...
3
votes
1answer
48 views

How are exploding numbers in a forward pass of a CNN combated?

Take AlexNet for example: In this case, only the activation function ReLU is used. Due to the fact ReLU cannot be saturated, it instead explodes, like in the following example: Say I have a weight ...
2
votes
0answers
29 views

Where could I find information on the learning methods used in Neurogrid?

I have been searching for more than one week which learning methods were used in Neurogrid. But I only found descriptions of its architecture (chips, circuits, analog and/or digital components, ...
0
votes
0answers
24 views

I am looking for research related to the use of AI and ML in car, aeronautics manufacturing design and safety

I am specifically interested in the topic of edge cases. I have the presentation Edge Cases and Autonomous Vehicle Safety as a starting point, in particular on page 6: Machine Learning (inductive ...
2
votes
1answer
77 views

Why can a fully convolutional network accept images of any size?

On this article, it says that: The UNET was developed by Olaf Ronneberger et al. for Bio Medical Image Segmentation. The architecture contains two paths. First path is the contraction path (...
2
votes
0answers
33 views

What are the benefits of using the state information that maintains the graph structure?

When you applying a graph structured data to the graph convolution network, what are the benefits of using the state information that maintains the graph structure?
2
votes
1answer
45 views

How do I know if my dataset is ready for a machine learning model?

I am new in this area of Machine Learning and Neural Networks. Currently, I'm taking some courses on Udemy and reading a book about it, but I still have one big question regarding data pre-processing. ...
2
votes
1answer
49 views

What is the purpose and benefit of applying CNN to a graph?

I'm new to the graph convolution network. I wonder what is the main purpose of applying data with graph structure to CNN?
0
votes
0answers
27 views

Is predicting day of week straight forward?

I am using python and Xgboost. I have features: activity and location and time stamps of when the activity occurred. I want to predict day of week. Is this straight forward, ie y=day of week, X={...
0
votes
1answer
42 views

How do I classify strings with possibly no meaning?

I am quite new to text classification. Using EAST text detection model, I get multiple strings that aren't words and most often have no meaning. For example, IDs, brand names, etc. I would like to ...
1
vote
1answer
40 views

Sensitivity of neural network to inputs

I am trying to build intution regarding neural networks and their working and this is a question, I am interested in: I understand that we normalise inputs. The reason this is done is to capture the ...
2
votes
1answer
164 views

How do I find the distance?

I am looking for solving this problem with training a deep learning-based classifier or image processing techniques. ps. I exactly do not need to know how much is distance, I only need to know whether ...
1
vote
2answers
58 views

How can I use 1-channel images as input to a CNN?

I need to develop a convolutional neural network whose inputs are 1-channel images, but I dont know how to do it, given that most libraries use 3 channel images. Should I convert my images to RGB? Is ...
0
votes
0answers
34 views

How to approach a problem with infinite solutions

Think Angry Birds kind of game. You need to hit a target at some point by adjusting angle and power. There is infinite number of parabolas that will solve this problem. My problem is not exactly that ...
0
votes
0answers
20 views

why my regression model predict every datapoint to the same value

I am trying to train a SVR but I found that with some combination of features, the trained SVR predict every point in test set to the same value. this problem occurs much more when I use linear kernel ...
0
votes
1answer
30 views

Is there any way to classify Document Image without OCR?

I have multiple invoices images which need to classify invoice types such as fright, utility, goods, etc. Is there any way to classify without OCR?
2
votes
1answer
21 views

How to add variation in the results of a neural networks?

I would like to create a neural network that converts text into handwriting for use with a pen plotter. Before I start on this project, I'd like to be sure that artificial intelligence is the best way ...
2
votes
2answers
50 views

Which online machine learning technique to use for multi-class classification problem with multiple inputs?

I have the following problem. We have $4$ separate discrete inputs, which can take any integer value between $-63$ and $63$. The output is also supposed to be a discrete value between $-63$ and $63$. ...
0
votes
1answer
36 views

Evolving Machine Learning

It seems to me that, right now, the key to making a good Machine Learning model is in choosing the right combination of hyper-parameters. Firstly: Am I right in saying, if a model is able to tune it'...
0
votes
1answer
60 views

How can I stabilise a recurrent neural network used for binary classification?

I’m looking for some help with my neural network. I’m working on a binary classification on a recurrent neural network that predicts stock movements (up and down) Let’s say I’m studying Eur/Usd, I’m ...
4
votes
1answer
36 views

Why are state transitions in MDPs probabilistic rather than deterministic?

I've read that for MDPs the state transition function $P_a(s, s')$ is a probability. This seems strange to me for modeling because most environments (like video games) are deterministic. Now, I'd ...
1
vote
0answers
12 views

Questions regarding rrn-writer by Robin Sloane?

https://github.com/robinsloan/rnn-writer I preface this by saying I do not know much about this topic, only that I have an intense interest in it, so I'm hoping I can make my questions as clear as ...
3
votes
1answer
78 views

How is G(z) related to x in GAN proof?

In the proofs for the original GAN paper, it is written: $$∫_x p_{data}(x) \log D(x)dx+∫_zp(z)\log(1−D(G(z)))dz =∫_xp_{data}(x)\log D(x)+p_G(x) \log(1−D(x))dx$$ I've seen some explanations asserting ...
4
votes
2answers
82 views

What approach should I take to model forecasting problem in machine learning?

I have a dataset which contains 4000k rows and 6 columns. The goal is to predict travel time demand of a taxi. I have read many articles regarding how to approach the problem. So, every writer tell ...
1
vote
1answer
71 views

Why are we using all hyperparameters in RL?

I am new in RL and I am trying to understand why do we need all these hyperparameters. Can somebody explain me why we use them and what are the best values to use for them? total_episodes = 50000 ...
3
votes
1answer
79 views

How can I build an AI with NLP that read stories

I want to do an NLP project but I don't know if it's doable or not as I have no experience or knowledge in NLP or ML yet. The idea is as follows: Let's say we have a story (in the text) that has 10 ...
3
votes
2answers
88 views

Can Machine Learning make economic decisions of human quality or better?

Basically, economic decision making is not restricted to mundane finance, the managing of money, but any decision that involves expected utility (some result with some degree of optimality.) Can ...
2
votes
1answer
55 views

How do I classify an image that contains only polygons?

I have two closed polygons, drawn as connected straight black lines on a white background. I need to classify such images in to three forms Two separate polygons One polygon encloses the other The ...
1
vote
1answer
37 views

Why is expectation used instead of simple sum in GANs?

Why do GAN loss functions use expectation(sum + division) instead of a simple sum?
1
vote
1answer
73 views

Why should each filter have different weights for each input channel?

From the answers to this question In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels?, I got the fact that ...
2
votes
4answers
104 views

How is regression machine learning?

In regression, in order to minimize an error function, a functional form of hypothesis $h$ must be decided upon, and it must be assumed (as far as I'm concerned) that $f$, the true mapping of instance ...
0
votes
1answer
28 views

Ideal score of a model on training and cross validation data

The question is little bit broad, but I could not find any concrete explanation anywhere, hence decided to ask the experts here. I have trained a classifier model for binary classification task. Now ...
1
vote
1answer
55 views

Checking Whether Given Logistic Regression Classifier classifies data

A bank wants to decide whether a customer can be given a loan, based on two features related to (i) the monthly salary of the customer, and (ii) his/her account balance. For simplicity, we model ...
2
votes
1answer
25 views

Calculating Parameter value Using Gradient Descent for Linear Regression Model

Consider the following data with one input (x) and one output (y): (x=1, y=2) (x=2, y=1) (x=3, y=2) Apply linear regression on this data, using the hypothesis $h_Θ(x) = Θ_0 + Θ_1 x$, where $...
3
votes
1answer
49 views

Will BERT embedding be always same for a given document when used as a feature extractor

When we use BERT embeddings for a classification task, would we get different embeddings everytime we pass the same text through the BERT architecture? If yes, is it the right way to use the ...
3
votes
1answer
59 views

How do I identify a monologue or dialogue in a conversation?

How do I identify monologues and dialogues in a conversation (or transcript) using natural language processing? How do I distinguish between the two?
0
votes
0answers
55 views

Super Resolution on text documents

I want to implement super-resolution and deblurring on images from text documents. Which is the best approach? Are there any Git-hub links which will help me to start? I am new to the field. Any help ...
2
votes
2answers
103 views

Do VR, AR and MR use any machine learning or deep learning?

I wonder if Virtual Reality (VR), Augmented Reality (AR) and Mixed Reality (MR) use any machine learning or deep learning? For example in AR, the virtual objects are brought into the real world, does ...
3
votes
1answer
56 views

Can a CNN be trained incrementally?

Like our human brain, we can first learn (train) the handwriting 0 and 1. After the traing (and test) accuray is good enough, we only need to study (traing) the hardwriting 2, Instead of cleaning all ...
2
votes
1answer
299 views

Can we evolve 0 and 1?

Is it possible to combine or create conditional statements of 0 and 1, and optimize with an evolutionary algorithm (given that all computers use a binary system)? There may be an algorithm that maps ...