Questions tagged [machine-learning]

relates to algorithms that are "trained" by some data set.

Filter by
Sorted by
Tagged with
-2
votes
0answers
23 views

Selection of independent variables in K means clustering among a vast dataset

As I understand it, the process of K means clustering takes a set of sample points with k arbitrary centroids and uses Euclidean distance to classify the points closest to centroids to k groups. What ...
1
vote
1answer
195 views

How to maintain well structured code and latency optimized code together?

I'm working on a c++ data analysis project. My workflow goes like this Analyze the data and build models Optimize the code for latency, to deploy for production goto 1 Step 1 has lots of machine ...
0
votes
1answer
142 views

Machine Learning pipeline design patterns

In machine learning we have modules that perform operations on data in a sequencial manner. Modules are generally the following: Data Collection Module: Takes raw data from a resource (filesystem,...
0
votes
0answers
176 views

What would be a good approach to applying computer vision to automatically edit out the downtime in tennis video?

I have an iOS/macOS tennis app that now lets the user import video, and I would like to add the ability to automatically edit out the significant amount of downtime where players are not in a rally or ...
-2
votes
1answer
120 views

Is it bad design to pass around a dictionary of arguments to all your functions?

In my machine learning pipeline, I have all the arguments collected into a dictionary. args = {'save_model': True, 'learning_rate': 0.01, 'batch_size': 4, 'model': 'my_model', 'momentum': 0.9, '...
1
vote
1answer
55 views

Best file formats for ML training

Hi I'm bulding an ML pipeline with PyTorch to support various tasks and am looking for some advice on efficient ways to store processed data. The main frame work was 3 layers [data prep] -> [data ...
0
votes
3answers
207 views

Is it really good practice in Python code for machine learning to use so many parameters?

Currently I am a student learning Machine Learning, and so my observation is from an academic context. It may be different in a business environment. One thing I find very odd when I see Python code ...
-1
votes
1answer
103 views

K-nearest neighbors for friend recommendation system

I want to write algorithm that will find recommended friends for given user. I was wondering if K-nearest neighbors algorithm will work fine for that task? Firstly, I'm not sure if I understood this ...
0
votes
0answers
43 views

What algorithm should I use to optimize a bike sharing redistribution system?

I want to optimize a bike-sharing redistribution system( find the best way for an agent to take bikes from a station that has more bikes than needed and relocate them to a station that needs more ...
-4
votes
1answer
35 views

How to make comprehension questions from text?

Lets say I wanted to autogenerate questions for a wikipedia page as a sort of comprehension exercise, how would i best go about that. Using machine learning would be necessary but any other things i ...
-4
votes
1answer
34 views

backpropagation DQN double q learning

After many research, I still can't find a neat answer about this question: Let's assume 'lo' is our loss for a state-action pair calculated with the Bellman eq. I don't understand wich one here is ...
-2
votes
1answer
1k views

Best way to store data for machine learning (Database or Files)

I am currently in the process of developing a machine learning application, where my users can upload their own data to train models. Furthermore, the users must be able to extend their uploaded data ...
0
votes
2answers
79 views

Do we draw the dataset as a secondary actor in a use case diagram?

I am working on a project to detect cancer and I am using deep learning (Convolutional neural network). In the user interface, the user has only to input an image number then click test when the user ...
-4
votes
1answer
47 views

Development paradigms of ML libraries

I know that Tensorflow use symbolic model-building APIs where the developers can use them to build static computational graphs. Whereas Pytorch offer imperative programming paradigm where it performs ...
-4
votes
1answer
44 views

How to create a quiz app without multiple choice?

So I'm trying to make a quiz app where the answers should be typed rather than multiple choice. However, even though there is always one right answer, in english, we have many ways of writing the same ...
0
votes
0answers
29 views

How to approach the lack of labels variability in a dataset for a RNN model?

I'm working on a quality air index model prediction from certain city. I have a dataset composed of hourly pollutants readings (5) from up to 24 basestations. Not all basestations can read all 5 ...
-2
votes
1answer
23 views

What do these terms refer to in the context of RL/TD learning?

I've been working on an implementation of TD-backgammon. The paper/project I'm basing my implementation on is here: https://www.cs.cornell.edu/boom/2001sp/Tsinteris/gammon.htm Everything makes sense ...
-4
votes
1answer
55 views

Capture the face when we blink eye

I need some guidance that how to capture the face when we blink the eyes. I have seen the core Image framework, but it detects only after capturing the image. But I need it to be live capture.
-1
votes
1answer
176 views

Is Python's Django WebFramework good to design Expert System as a Web App?

I hope everyone is good. Well, I am at the end of my degree BS (Software Engineering), and in the third Phase of my Final Year Project named as 'Test Phase'. My Project is to build an Expert System ...
3
votes
1answer
83 views

Machine Learning in Real Time

I've been going over some tutorials on machine learning using Python and libraries including SciKit Learn and Tensor Flow. (Basic tutorials like creating an algorithm to predict a price given input ...
0
votes
1answer
87 views

How can I alter a system design to improve computational efficiency with AWS?

I have a use case which will take in data from the front end and transform it with various parameters. Then a random effects model is run on each transformation and multiple models are built For ...
-1
votes
2answers
58 views

Sensitive data and cloud storage

I've been reading about machine learning models deployment and pipelines and so far most of the sources suggest that the data should be ingested from some sort of cloud based storage or source, be it ...
2
votes
0answers
46 views

How to test generated text

I am creating a text generation algorithm for my master's research. I have a dialogue between two people and I would like to simulate one part of the conversation with naturally generated text (not ...
-1
votes
1answer
91 views

Algorithm that maps consecutive whole numbers to sets of numbers

Where would I begin if I wanted to develop an algorithm that maps consecutive whole numbers to a long list of unique sets of whole numbers. For example: 0 = {0, 0, 0} 1 = {0, 0, 1} 2 = {0, 0, 2} ...
-2
votes
1answer
621 views

How to do regression testing on a machine learning based application? [duplicate]

This question is different from What are best practices for testing programs with stochastic behavior? be cause it's particular to Regression testing. We are building a chat bot, and for regression ...
3
votes
2answers
460 views

What is the best way for transferring large datasets between an old java app and a python app on the network?

I am working on a machine learning project at the moment which requires me to transfer the data from an old Java app(which is also the custodian of the data in current paradigm) to a python service ...
1
vote
1answer
55 views

Ideal architecture for ML training -> API service workflow, with multiple models/services? [closed]

I'm planning to construct a workflow/environment for training and serving NLP classifiers, that follows something like: The model training system takes in annotated documents from a subset of a ...
2
votes
1answer
38 views

Setup pipeline to analyze data stored in web app DB

Background: So there is a (Ruby) web app with a production Postgres DB (hosted in the cloud) I would like to run some machine learning algorithms in a Python setting on the production data and (...
-2
votes
1answer
121 views

Sphere parameter optimization: how would I approach it? [closed]

I am looking to construct a program that takes, as input, 576 [x, y, z] points as well as 576 corresponding distance values. I want to find the [x, y, z, radius] parameters of a sphere such that the ...
1
vote
1answer
163 views

How does machine learning learn? [closed]

I'm new to Machine learning or Ai but I have been a developer for almost 10 years. I have a news aggregator application that grabs and save articles from news websites, And I have developed an ...
1
vote
2answers
99 views

Balancing function call overhead and testability in a code that is a part of the deep learning model training loop

I am currently implementing the transformer architecture for sequence to sequence problems. Key part of the model is the attention mechanism, which is basically a matrix multiplication, followed by a ...
1
vote
0answers
114 views

Solution architecture for storing machine learning data

I'm building a mobile application using Expo & React Native. As the user interacts with the mobile app I need to store their interactions in Google BigQuery, so they can later be used to train ...
1
vote
1answer
54 views

Compare two arrays by the number of occurances

I have the following dictionary: { "Drama": 8, "Adventure": 8, "Action": 4, "Comedy": 3, "Thriller": 1 } This dictionary is like a representation of a user's preferences in movies. (in the past he ...
1
vote
1answer
77 views

Predicting Diagnosis Codes

I am very new to Machine Learning. I've read about it and I successfully did a tutorial where we looked at the dimensions of Iris petals and predicted what other Iris petal sizes may be. This all made ...
2
votes
2answers
327 views

Distributed training of many small ML models

I have a data science application that involves training tens of thousands of small individual Gaussian models. By "small", I mean that any individual model can easily be trained on one of our worker ...
2
votes
3answers
73 views

Redesigning Procedural Decision Engine To Leverage Machine Learning (and Which)

I'm not sure if this is the right forum, but I'm really looking for an advice on this. We've a procedural decision engine, which is fairly rudimentary, to decide application routing. It's basically ...
0
votes
1answer
677 views

Battery level prediction model

I have the idea of develop a model that predicts the battery charge level of my system for now until the following 5 days. The battery is charged using a solar panel. I am writing my code in Python 2....
0
votes
1answer
539 views

Clustering Algorithm with max number of clusters

I'm looking for a clustering algorithm (ideally density based) that allows me to specify the maximum number of clusters (but not the exact number). All points must be assigned to a cluster, so I can't ...
-2
votes
1answer
77 views

How to physically test a machine learning model?

I am new to machine learning. I have implemented a machine learning model which detects sound (for example: horn, siren, hammer etc) and predicts the type of sound. I have to physically test the model ...
1
vote
0answers
28 views

Bernoulli naive bayes document model for multi-label classification

I want to ask about Bernoulli Naive Bayes document model. Can we use Bernoulli Naive Bayes document model for multi-label classification of documents?
3
votes
2answers
530 views

Is manually tagging content an ideal start for eventual machine learning?

I'm putting together a mobile app that would allow users to search, rate, and upload photos of dishes at restaurants. I have no machine learning experience (just FE/BE/Mobile) so for the time being I ...
-1
votes
1answer
4k views

Training data in unsupervised learning?

Unsupervised learning (USL) is about learning/constructing the algorithm to find the hidden data pattern based on training data without hard coded business rules like arithmetic sum, etc. Example of ...
0
votes
1answer
271 views

How do I check programmatically if two photos show the same drawing? [closed]

Imagine a simple drawing of let's say a duck. And you have an photo of it in your database. Now a user takes a second photo of the same drawing of the duck. What approaches exist to check if both ...
3
votes
1answer
2k views

Distinction between AI, ML, Neural Networks, Deep learning and Data mining

I have recently started exploring the field of machine learning (ML). I think I understand the difference between ML and AI at high level, but I wanted to understand more accurately the differences ...
3
votes
0answers
87 views

Software design strategy for a machine learning tool that outputs a subset of the text input (Information Extraction)?

Let's say I have thousands of pdfs that are each about 30k words written in conversational English. In each of the pdfs there is a name / names of a person/people who snowboard. There are also many ...
-2
votes
1answer
74 views

Licensing of classifier tool trained on open data [closed]

The broad question is: how are the licensing terms for a classifier that is trained with open annotated data (or manually annotated) data? I am trying to train a dependency parser for German text ...
1
vote
0answers
109 views

Can machine learning be used for non-numerical prediction?

I've started reading a machine learning book since a few days ago, and I've learned about how it can be used for classification/regression/etc. However, I am unsure if it will be able to handle the ...
1
vote
2answers
216 views

How to loosely couple chained algorithms

I have a search algorithm that is used in conjunction with a machine learning algorithm. I separated the two because I wanted to be able to swap out search algorithms on the fly. However, the coupling ...
20
votes
7answers
4k views

Machine learning applied to code development

My background is in mechanical engineering, so please forgive my ignorance to this area. I really enjoy programming and software development. Also, I recently took a free online Machine Learning (ML) ...
-6
votes
4answers
281 views

AI Language that doesn't release source code or can't be decompiled

I looked at using python for the AI in a security application for hobby-business but apparently you either release it as source code or it can be easily decompiled. Of the new machine learning ...