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.

708 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
3
votes
0answers
83 views

What is the difference between random and sequential sampling from the reply memory?

I was working on an RL problem and I am confused at one specific point. We use replay memory so that the network learns about previous actions and how these actions lead to a success or a failure. ...
3
votes
1answer
99 views

When to use RMSE as opposed to MSE and vice versa?

I understand that RMSE is just the square root of MSE. Generally, as far as I have seen, people seem to use MSE as a loss function and RMSE for evaluation purposes, since it exactly gives you the ...
3
votes
0answers
24 views

Reverse engineering controller sensitivity/aim for several games ie acceleration curves, deadzones, etc

A machine learning project I am working on requires me to interface with an Xbox controller connected to a PC. The implementation must do the following two things: Record the joystick input from the ...
3
votes
0answers
161 views

What are the differences between CRF and HMM?

What I know about CRF is that they are discriminative models, while HMM are generative models, but, in the inference method, both use the same algorithm, that is, the Viterbi algorithm, and forward ...
3
votes
0answers
38 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, ...
3
votes
0answers
39 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?
3
votes
2answers
119 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 $63$. ...
3
votes
0answers
420 views

What is the right formula for weight update rule in Logistic Regression using stochastic gradient descent

Apologies for the lengthy title. My question is about the weight update rule for logistic regression using stochastic gradient descent. I have just started experimenting on Logistic Regression. I ...
3
votes
0answers
83 views

What are stable ways of doing online machine learning?

I am trying to deploy a machine learning solution online into an application for a client. One thing they requested is that the solution must be able to learn online because the problem may be non-...
3
votes
0answers
28 views

How do we ensure that training GANs will fall in the desirable Nash equilibrium?

One Nash equilibrium of every GANs model has is when the generator creates perfect samples indistinguishable from the training data and the discriminator just output 1 with probability 1/2. And I ...
3
votes
0answers
46 views

Is there any formal test for linear separability of 2-class data?

SVM is designed for two-class classification problem. If the data is not linear-separable, a kernel function is used. I want to know if there is exists any method that will indicate if the data is ...
3
votes
0answers
22 views

Backpropagation: how to take into account different samples quality

I have a NN I'd like to train using supervised learning. Some samples of the training set, however, have better "quality" than others, so I'd like the algorithm to pay "special attention" to them. As ...
3
votes
0answers
120 views

What are the differences between learning by analogy, inductive learning and explanation based learning?

I have heard of the concepts of learning by analogy (which is quite self-explanatory), inductive learning and explanation-based learning. I tried to learn about inductive learning and explanation-...
3
votes
0answers
121 views

Does an advanced Dialogue state tracking eliminate the need of intent classifier and slot filling models in dialogue systems/ chatbots?

I am learning to create a dialogue system. The various parts of such a system are Intent classifier, slot filling, Dialogue state tracking (DST), dialogue policy optimization and NLG. While reading ...
3
votes
1answer
137 views

Integration of Sentiment analysis in CRM

What is the process for integrating sentiment analysis in a CRM? What I am searching for is a system which analyzes the customer comments or reviews using the CRM and finds out the customer sentiment ...
3
votes
0answers
593 views

Getting worse performance when training a pre-trained model with the existing class

I am training pre-trained SSD-InceptionV2-Coco to detect the "car", which is one of the classes in mscoco label. I train the model with ~50k sample from KITTI, 500k iteration with batch size 2. I ...
3
votes
0answers
221 views

What is the relation between the definition of learnability of Vapnik and Gold and learnability of neural networks?

Gold showed that a language can be learned only if it contains a finite set of sentences. We know that deep neural networks can implement any function. Does this contradict the Gold's result? What ...
3
votes
0answers
274 views

How do I make and use a dataset for StackGAN

So I am currently trying to create a program that when provided a list of descriptive words or a passage of text, would create a piece of abstract art based on the feelings evoked by those words. I ...
3
votes
0answers
39 views

Is there a general adversarial network that can take multiple low quality images to create a higher quality image?

Is there a general adversarial network that can take multiple low quality images of a subject to create a higher quality image of the subject? SRGANS just take a single low res image and make it high ...
3
votes
0answers
210 views

Can anybody explain such behavior of accuracy and loss of my Net(caffe)?

I used this project for example(framework - caffe, arhitecture of net - mod of AlexNet, 400 images are used for training). I have this result: or this: Solver: ...
3
votes
0answers
863 views

Neural networks and number theory

Can neural networks be used to study (elementary) number theoretic problems? What are examples where this has been done in the past? Or is there on the contrary an understanding that neural networks ...
3
votes
1answer
150 views

Is gradient descent scale invariant or not?

I know we should scale the input and output (assuming regression task) before we feed it to the neural network. Then the gradient descent will give the better minima much faster. But I have subtle ...
3
votes
1answer
117 views

If neurons are only defined for values between 0 and 1, how does ReLU differ from the identity?

I'm struggling to understand the underlying mechanics of CNNs so any help is appreciated. I have a network with a ReLU activation function which does perform signifigantly better than one with sigmoid....
2
votes
0answers
20 views

ReLU function converging to local optimum in one case and diverging in the other one

I implemented a simple neural network with 1 hidden layer. I used ReLU as activation function for the hidden layer and the output layer just uses the linear function. To check my implementation I ...
2
votes
0answers
26 views

Is optimizing weighted sum multi objective tasks considered a multi-task learning?

I have two sequence prediction tasks, finding $\vec{\pi} \in \Pi$ and $\vec{\psi} \in \Psi$. Each sequence has its own objective function, i.e. $f_1(\vec{\pi})$ and $f_2(\vec{\psi})$. The input for ...
2
votes
0answers
76 views

Taking a machine learning model to production\deployment

I've designed a machine learning model for the predictive maintenance of machines. The data used for training and testing the ML model is the data from various sensors connected to various parts of ...
2
votes
0answers
73 views

How would we get a good estimation of the asymptotic performance of machine learning algorithms?

The following question is from the webbook Neural Networks and Deep Learning by Michael Nielson: How do our machine learning algorithms perform in the limit of very large data sets? For any given ...
2
votes
1answer
41 views

Is $(y_i - \hat y_i)x_i$, part of the formula for updating weights for perceptron, the gradient of some kind of loss function?

A post gives a formula for perceptron to update weights I understand almost all the parts of it, except for the part $(y_i - \hat y_i)x_i$ where does it come from? Is it the gradient of some kind of ...
2
votes
0answers
38 views

Identifying rotating and resizing letters with background noise

I'm trying to complete a captcha, and here is what it looks like: Between captchas the calligraphy of the letters is the same, but the letters may be resized and rotated. And the background noise (...
2
votes
0answers
14 views

How could an attacker poision the training data?

I came across the following definition of Backdoor attack (in this paper): These attacks are accomplished in two steps. First, special patterns are embedded in the targeted model during the training ...
2
votes
0answers
38 views

Loss function to minimize the distance between sets

Are there references or links to examples about loss functions "Distance Metrics" which could be used to minimize the distance between two sets for a neural network. More precisely, this ...
2
votes
0answers
16 views

Predicting the the motion of a 3D object when the motion of a set of markers is known

trying to figure out where to get started with this: I have a few hundred CT images where certain three-dimensional features in the image (anatomy) are moving in a correlated fashion with a set of ...
2
votes
0answers
34 views

Is there a technique for analyzing the relationship between time-series clusters?

I have two time-series datasets (temperature and speed of the vehicle). I will use Agglomerative Hierarchical Clustering and DTW to cluster both datasets. I am looking for a technique (like regression ...
2
votes
1answer
66 views

When exactly am I overfitting -- contradicting metrics

I am training an object detection machine learning pipeline. Among the many metrics provided out of the box by tensorflow object detection API, I look at total_loss and DetectionBoxes_Precision/mAP@....
2
votes
0answers
56 views

How many papers about AI / ML were published in the recent years?

I am trying to formulate an argument at work saying the disruption in AI/ML is very high and that it is hard to stay "state of the art". I would like to support that hypothesis by numbers. ...
2
votes
0answers
53 views

What is the effect of K in K-NN on the VC dimension?

What is the effect of K in K-NN on the VC dimension? When K increases, is the VC dimension decreased or increased, or we can't say anything about this? Is there a reference book that discusses this?
2
votes
0answers
67 views

Is there any known technique to determine a graph from a 1D signal pattern?

I'd like to evaluate the possibility of using a Machine/Deep Learning technique as a sort of pattern recognition and parameters estimation. The problem I want to address can be stated as follows: Let'...
2
votes
0answers
30 views

NN to find arbitrary transformation

Problem description I'm creating a clock with 4 seven-segment LED displays. In an effort to get more familiar with tensorflow, I figured I should try to drive this clock with use of a Neural Network. ...
2
votes
0answers
23 views

What are some of the main high level approaches to applying ML on kinematic sensor data?

I've just started a project which will involve having to detect certain events in a stream of kinematic sensor data. By searching through the literature, I've found a lot of highly specific papers, ...
2
votes
0answers
52 views

Reinforcement learning and Graph Neural Networks: Entropy drops to zero

I am currently working on an experiment to link reinforcement learning with graph neural networks. This is my architecture: Feature Extraction with GCN: there is a fully meshed topology with ...
2
votes
0answers
42 views

How to train/update neural networks faster without a decrease in performance?

I noticed that there are many studies in recent years on how to train/update neural networks faster/quicker with equal or better performance. I find the following methods(except the chips arms race): ...
2
votes
0answers
33 views

In the Binary Flower Pollination Algorithm (using the sigmoid function), is it possible that no feature is selected?

I'm trying to use the Binary Flower Pollination Algorithm (BFPA) for feature selection. In the BFPA, the sigmoid function is used to compute a binary vector that represents whether a feature is ...
2
votes
0answers
23 views

Why does the loss stops reducing after a point in this Transformer Model?

Context I was making a Transformer Model to convert English Sentences to German Sentences. But the loss stops reducing after some time. Code ...
2
votes
0answers
61 views

Statistical method for selecting features for classification

I'm working on a classifier for the famous MNIST handwritten data set. I want to create a few features on my own, and I want to be able to estimate which feature might perform better before actually ...
2
votes
0answers
103 views

Generating fake faces containing specific features with GANs

I'm trying to understand how DeepFakes are generated and so far I understood that they're mostly generated through the usage of GANs and autoencoders. The autoencoders part is understandable, but what ...
2
votes
0answers
33 views

how to handle highly imbalanced multilabel classification?

I am working on a multilabel classification in which I am having 206 labels. When I saw the percentage of the number of 1's in each label they are way less than 0.1% for each label. The maximum ...
2
votes
0answers
40 views

What is the difference between text-based image retrieval and natural language object retrieval?

I'm working on creating a model that locates the object in the scene (2D image or 3D scene) using a natural language query. I came across this paper on natural language object retrieval, which ...
2
votes
0answers
28 views

Why don't ensembling, bagging and boosting help to improve accuracy of Naive bayes classifier?

You might think to apply some classifier combination techniques like ensembling, bagging and boosting but these methods would not help. Actually, “ensembling, boosting, bagging” won’t help since their ...
2
votes
0answers
30 views

How does Hartigan & Wong algorithm compare to Lloyd's and Macqueen's algorithm in K-means clustering?

As far I know, this is how the latter two algorithms work... Lloyd's algorithm Choose the number of clusters. Choose a distance metric (typically squared euclidean). Randomly assign each observation ...
2
votes
0answers
50 views

Estimating an $n$-Gram model using on bigrams

One of the main arguments against $n$-gram models is that, as $n$ increases, there is no way to compute $P(w_n|w_1,\cdots,w_{n-1})$ from training data (since the chance of visiting $w_n,...,w_1$ is ...

1
2
3 4 5
15