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.
635
questions with no upvoted or accepted answers
1
vote
0answers
68 views
Learning from events. Supervised, Unsupervised or MDP?
I have a large set of simulation logs for a market simulation of which I want to learn from. The market includes:
customers
products (subscriptions)
The customers choose products and then stick with ...
1
vote
0answers
26 views
Commercial API Q: is there an api for converting vision tags into a caption?
There are many machine learning api for scanning images but they just return a bunch of tags.
https://azure.microsoft.com/en-gb/services/cognitive-services/computer-vision/
...
1
vote
0answers
153 views
Learning algorithm that filters keyboard clicking in audio feeds
When recording audio for screencasts or similar, very often the keyboard is clearly visible and can start to annoy listeners after a while.
NN are quiet good at recognizing patterns. Image ...
1
vote
0answers
48 views
How to calculate Adaptive gradient?
In the FaceNet paper there mentions an gradient algorithm called 'AdaGrad'(Adaptive Gradient) referenced to this paper which has apparently been used to calculate the gradient of the Triplet Loss ...
1
vote
0answers
266 views
Analogies and similarity
The more I think about machine learning the more I realize the importance of finding similarities by using analogies as a way of learning.
If I want to categorize words into hierarchical tree this ...
1
vote
0answers
93 views
Prove that there might be an Agent function which cannot be implemented by any Agent program
So i really don't get this question because i always thought the agent program is the same as agent's function, but i read somewhere that this is statement might be true
so is this statement actually ...
1
vote
0answers
269 views
Application of Ai to task scheduling problems on heterogenous platforms
Let's say we have a cluster of 20-2000 heterogenous compute nodes.
Consider for example the parallel solution of the helmholtz equation:
Now we want to distribute the solution process and, to make ...
1
vote
0answers
23 views
Can number of Leads be predicted based on previous months
I have a sample set of data about Leads that gets generated every day. Leads are nothing but a user expressing request to be our partner or not. Sample data set is as shown below
...
1
vote
0answers
56 views
Decision tree doesn't quite work, is there a better alternative?
I have a problem that I have been trying to use decision trees to solve. There is a data set of pricing information for products sold by a company. The goal is to infer the pricing algorithm for each ...
1
vote
0answers
63 views
Orientation of data set before training simple ANN's
Well, I am new to implementing ANN's and there is something that i want to know. It maybe a bit silly though.
I just wanted to know that if we have a simple data set say dependent only on a single ...
1
vote
0answers
56 views
Build Android News Recommendation app
Please I am interested in building a news recommendation app that will be powered by artificial intelligence. I have being making a whole lot of research on this and will be glad if somebody can tell ...
1
vote
0answers
233 views
Converting pictures into numerical values
I am working to make my first trained model for image recognition, using the programming language R.
First I am attempting to make a function that takes a PNG-image as input, resizes it to 128x128 ...
1
vote
0answers
146 views
Tuning the parameters of Particle swarm optimization (PSO)
To tune the parameters of Particle swarm optimization (PSO), there are two methods offline and online. In offline manner, the meta-optimization is used to tune the parameters of PSO by using another ...
1
vote
0answers
88 views
Agent exploration which leads to a negative state where actions are limited
I'm working on a project where I train a Q-learning agent to learn an optimal control policy for a water heater. I've set up a simulation which allows the agent to explore for one year. I then examine ...
1
vote
0answers
98 views
Infer dependent variables to produce output aligned to trained data
Hypothetical example, say I wanted: P(gender,ethnicity|age,hair); so that the input would aligned to a trained dataset of: ...
1
vote
1answer
70 views
Can the addition of unnoticeable noise to images be used to create subliminals?
I was reading this report: https://www.theverge.com/2017/4/12/15271874/ai-adversarial-images-fooling-attacks-artificial-intelligence
Researchers used noise to trick machine learning algorithms to ...
0
votes
0answers
8 views
Nonrealtime tracking for object detection (with or without deep features)
I've been doing a search for tracking systems based on bounding box for several days (like Sort, DeepSort, Motpy, ...). But neither is nonrealtime.
My problem is based on the tracking of multiple ...
0
votes
0answers
15 views
Architecture for Logistic Regression with Arbitrary Number of Options
Suppose I want to design a neural network to choose one of several mutually exclusive options. This may normally be done via logistic regression, where the input of the network would be a [batch x ...
0
votes
0answers
12 views
Low Signal-To-Noise Ratio Data Processing and Model Choices
Attached is a plot showing that y regresses on individual features: Scatter Plot
And as shown, each feature has minuscule predictive power on y. I have 130 features like this, all of them are more or ...
0
votes
1answer
53 views
+100
How to predict the best from a set of messages - best practice
Suppose I have a set of messages A,B,C,D and I want to produce the best message for a website user at a given time.
For training I plan to show random users a random single message [A/B/C/D] and fill ...
0
votes
1answer
17 views
Is it possible to modify or replace the basic network of YOLO?
I have an idea to adapt YOLO algorithm to my application, the original YOLO algorithm is for image classifications, which have 24 convolutional layers with output class of 1000, is it possible to ...
0
votes
0answers
19 views
ML method for detecting which individuals are best predicted by the features
Broad question to help in finding an appropriate method. So I have a given feature set of (DNA/genetic) predictors and a group of individuals which are either cases or controls for diseaseX. While I ...
0
votes
0answers
7 views
How to classify “composite” gestures from “primitive” gestures (with IMU data)
I'm exploring this idea:
I record IMU data for "primitive" gestures (up-down, left-right, diagonal, circle...)
I train a classifier to classify them (on my dataset, RandomForest achieves &...
0
votes
0answers
12 views
Recommended vehicle trajectory prediction algorithms (based only on lat/lon data)?
Could you recommend me the most suitable algorithms for vehicle trajectory prediction? Although I'm studying kalman filter approaches and they are the most used, are there other common (NN, SVM, RF, ...
0
votes
0answers
36 views
Is training on single game each time appropriate for an agent to learn to play checkers
I was facing a problem I mentioned in a previous question but after a while, I realize that maybe the problem in the dataset not in the learning rate.
I build the dataset from white positions only i.e ...
0
votes
0answers
11 views
What are the general inequalities needed for the logic gate perceptrons?
I'm trying to understand how the logic gates (e.g. AND, OR, NOT, NAND) can be built into single-layer perceptrons.
I understand specific examples of weights and thresholds for the gates, but I'm stuck ...
0
votes
1answer
61 views
A way to leverage machine learning to reduce DFS/BFS search time on a tree graph?
I'm not very knowledgeable in this field but I'm wondering if any research or information already exists for the following situation:
I have some data that may or may not look similar to each other. ...
0
votes
0answers
11 views
How to update the error on hidden nodes using back-propogation, given the error on the output nodes and weights
I'm trying to solve question 30 of this paper.
The short version of the question is if someone could show me how to do this, I would appreciate it (the answer should be A; -0.0660).
The long version ...
0
votes
0answers
15 views
Is there any solution to the problem of detecting whether a user is having trouble finding something while surfing a webpage?
While a user is navigating through a website, we need to detect whether the user is having trouble finding something in realtime. The output is used to trigger an event that should pop up a FAQ page ...
0
votes
0answers
16 views
How to build a commercial Image-Image search engine using LSH / Near Duplicate or some other algo on more than 20M images
TL;DR: HOW DO I APPLY LSH WITH A DEEP LEARNING MODEL TO BUILD A IMAGE-IMAGE SEARCH ENGINE ON >20M IMAGES?
I want to build a system where I am helping my ...
0
votes
0answers
44 views
Which approach should I follow to classify tweets into topics?
I am approaching machine learning for the first time because of my studies.
I have been given a bunch of tweets and the goal is to classify them per topic. The topics are not predefined, but need to ...
0
votes
0answers
15 views
How do I find text ellipses using machine learning?
I need to detect text ellipses in scanned text documents. These ellipses are defined by lines next to text.
Here is a sample:
(This text is a training for pupils. They have to fill in the appropriate ...
0
votes
1answer
37 views
How to do early classification of time series event with small dataset?
I would like to build a real-time binary classifier that can predict an event of interest that is occurring as soon as it starts. These are electromyographic signals, and the event classification ...
0
votes
1answer
42 views
What is “Pattern Theory”?
I came across Grenander's work "Probabilities on Algebraic Structures" recently and found that much of Grenander's work focused on what he called "Pattern Theory." He's written ...
0
votes
0answers
20 views
Network structure of generative model for classification
I'm trying to model a generative model for classification problem, especially aiming to solve an imbalanced data problem.
However, I couldn't get intuitive understanding for generative classifier in ...
0
votes
1answer
50 views
Why does k-means have more bias than spectral clustering and GMM?
I ran into a 2019-Entrance Exam question as follows:
The answer mentioned is (4), but some search on google showed me maybe (1) and (2) is equal to (4). Why would k-means be the algorithm with the ...
0
votes
0answers
13 views
Are there any good self annotating methods in machine learning
Currently I want to train a deep learning model on finger detection (drawing bounding boxes around fingers), so I haven't found an annotated dataset, so I decided to make it myself. but the number of ...
0
votes
0answers
20 views
How to deal with predictions for data outside the range of the training dataset in neural networks?
I’ve set up a neural network model to experiment with predicting foreign exchange rates based on various economic data. The model learned fine and the test data is OK ($R^2 = 0.88$).
But I can't ...
0
votes
0answers
17 views
Estimating depth/perspective of image
I'd like to find a method in which the depth or perspective of an image is estimated. I imagine this could perhaps be done based on how quickly classified objects, such as cars or humans, grow or ...
0
votes
1answer
106 views
How to fill NaNs in Cross-Validation?
I have been searching this but did not find the answer, so sorry if this is a duplicated question.
I was working with cross-validation, where some doubts came to my mind, and I am not sure about which ...
0
votes
0answers
23 views
Find the distance between two objects from a 45 degree tilted camera images taken from a drone with a specific elevation from the ground
I have a project where i'm supposed to find the distance and the height of a specific object in an image taken by a drone using one camera. I have looked into perspective transformation/correction but ...
0
votes
0answers
35 views
Which models can I use for supervised learning with images?
I have to do a project that detects fabric surface errors and I will use machine learning methods to deal with it. I have a dataset that includes around six thousand fabric surface images with the ...
0
votes
0answers
17 views
Utilizing continuous variables in concept learning algorithms
Suppose I'm using the Spambase dataset, with 57 real continuous variables and one binary label, and I'd like to implement the Find-S or LGG or similar algorithms.
How do I represent the dataset for ...
0
votes
1answer
22 views
Which machine learning technique can I use to match one set of data points to another?
I have two measuring devices. Both measure the same thing. One is accurate, the other is not, but does correlate with a non-fixed offset, some outliers, and some noise.
I won't always be using the ...
0
votes
0answers
25 views
Find repeating patterns in sequence data
I have database of sequential events for multiple animals.
The events are represented by integers so it looks something like:
...
0
votes
0answers
15 views
How would named recognition and entity linking interface with subsequent machine learning model?
I have a database containing summary of the movie, the price of the movie, location, language. I would like to make a prediction on 'like' based on previous like of a user.
I am wonder how the output ...
0
votes
0answers
38 views
Is the “mlpconv” layer in the “Network in Network” paper computing $1 \times 1$ convolutions or not?
I am reading the Network in Network paper. This is the equation they introduce for their mlpconv layer (equation 2 in the paper, page 3):
$$
\begin{aligned}
f_{i, j,...
0
votes
0answers
29 views
Transforming neural network target values before training
Consider the scenario in which I am measuring certain $f(a,x)$, which i want to be the target value for some related input $g(a,x)$. In other words, I am trying to map
$$g(a,x)\Rightarrow f(a,x)$$
I ...
0
votes
0answers
19 views
Extracting specific information from an Invoice images
Tried to extract only specific information from the images but Couldn't, We have to automate this process using this as the format of the Images keeps on changing.
LinkSample data
What I have Tried:
<...
0
votes
0answers
33 views
Bigger models get higher losses
I'm training a model with the transformer encoder architecture on a given fixed set of data.
The task I'm solving has a trivial approximation which consists in copying part of the input to the output, ...
