[Azythum]

And so post about machine learning can be posted here ?

[Hackers]

And so post about machine learning can be posted here ?

Yes you can talk about it, no its not technically a software itself. There is software FOR machine learning, but ML itself is a concept / type of tech.

[Perlo]

There isn't a specific place for Machine Learning on this forum. I would say you can categorise it in either "Coders Lounge" or "Science, Religion, Philosophy, and Politics".

Machine learning are mainly mathematical and statistical formula's which analyse trends and patterns in (large) datasets. ML algorithms can be written out as formula's and solved on a piece of paper using linear algebra or calculus. However, applying it to real world problem solving usually requires programming knowledge (mainly Python or R).

Very cool and interesting concepts if you ask me. If you'd like to know more about it feel free to ask, I have quite some knowledge on these topics.

[Hackers]

There isn't a specific place for Machine Learning on this forum. I would say you can categorise it in either "Coders Lounge" or "Science, Religion, Philosophy, and Politics".

Machine learning are mainly mathematical and statistical formula's which analyse trends and patterns in (large) datasets. ML algorithms can be written out as formula's and solved on a piece of paper using linear algebra or calculus. However, applying it to real world problem solving usually requires programming knowledge (mainly Python or R).

Very cool and interesting concepts if you ask me. If you'd like to know more about it feel free to ask, I have quite some knowledge on these topics.

Only really messed with Python for it, but how do you like R? Haven't given it a go yet

OP, have you used any Tensorflow? You can build some pretty cool software with it

[Perlo]

Only really messed with Python for it, but how do you like R? Haven't given it a go yet

OP, have you used any Tensorflow? You can build some pretty cool software with it

R is a popular language for statistical analysis. Widely used in academia. It also has similar packages as Python for machine learning models. However, it lacks the ability to be used for wider applications rather than static data analysis / research. It’s perfectly fine to use for research, however if you want to use ML models in production (ML-ops) you should use Python. R lacks functionality for for example webservers. Its much easier to setup a restful API using Python and serve your models using API calls.

I’ve used Tensorflow before during some courses of my master. Image recognition, object detection, information retrieval (auto-encoders), and finetuning NLP models were mainly the use cases for me. Additionally we also used PyTorch as alternative for Tensorflow.

[Azythum]

Thanks for answering guys.

There isn't a specific place for Machine Learning on this forum. I would say you can categorise it in either "Coders Lounge" or "Science, Religion, Philosophy, and Politics".

Machine learning are mainly mathematical and statistical formula's which analyse trends and patterns in (large) datasets. ML algorithms can be written out as formula's and solved on a piece of paper using linear algebra or calculus. However, applying it to real world problem solving usually requires programming knowledge (mainly Python or R).

Very cool and interesting concepts if you ask me. If you'd like to know more about it feel free to ask, I have quite some knowledge on these topics.

Ok thanks I will ask you if I have a question.

Only really messed with Python for it, but how do you like R? Haven't given it a go yet

OP, have you used any Tensorflow? You can build some pretty cool software with it

No I haven't used Tensorflow yet.
I'm really a beginner in that.

[Perlo]

Thanks for answering guys.



Ok thanks I will ask you if I have a question.




No I haven't used Tensorflow yet.
I'm really a beginner in that.

No problem!

If you are just beginning with machine learning I would suggest to not start with Tensorflow. This is mainly used to build neural networks which is usually explained at the end of a machine learning course or even skipped and only discussed in an Artificial Intelligence course.

A good start would be to begin with regression, classification and clustering. Look into linear/logistic regression, decision tree’s, random forests and clustering algorithms (K-means, K-nn). These will help you get a better understanding of machine learning algorithms. If you’ve gotten a grasp of these concepts you can start exploring neural networks.

[Dirty]

There isn't a specific place for Machine Learning on this forum. I would say you can categorise it in either "Coders Lounge" or "Science, Religion, Philosophy, and Politics".

Machine learning are mainly mathematical and statistical formula's which analyse trends and patterns in (large) datasets. ML algorithms can be written out as formula's and solved on a piece of paper using linear algebra or calculus. However, applying it to real world problem solving usually requires programming knowledge (mainly Python or R).

Very cool and interesting concepts if you ask me. If you'd like to know more about it feel free to ask, I have quite some knowledge on these topics.

mathematical formulas can definetly be software though, thats essentially functional programming. I have recently implemented an internal tool where the whole spec was written as maths, and now that tool generates our kubernetes manifests.

[IMM0RTAL1TY]

ML is a subset of artificial intelligence combined with networking science, neurolinguistic programming, and more that is the backbone of AI. Machine learning is an actual application of AI systems and their usage by the individual.

A good start would be to begin with regression, classification and clustering. Look into linear/logistic regression, decision tree’s, random forests and clustering algorithms (K-means, K-nn). These will help you get a better understanding of machine learning algorithms. If you’ve gotten a grasp of these concepts you can start exploring neural networks.

I suck at math but am a god at stats (yes I am a liar's mathematician) and can confirm that this is where you want to start. Particularly look into the rudimentary functioning of clustering algorithms. Also, decision tree's (as simple as they are); are literally the basis for this field so a solid understanding of them won't hurt.