Machine Learning | Hyperparameter

In machine learning, a hyperparameter is a parameter whose value is set before the learning process begins. By contrast, the values of other parameters are derived via training. #MachineLearning #Hyperparameter
𝑫𝒆𝒆𝒑 𝑳𝒆𝒂𝒓𝒏𝒊𝒏𝒈 👉 • Deep Learning
𝑴𝒂𝒄𝒉𝒊𝒏𝒆 𝑳𝒆𝒂𝒓𝒏𝒊𝒏𝒈 👉 • Machine Learning
𝑨𝒓𝒕𝒊𝒇𝒊𝒄𝒊𝒂𝒍 𝑰𝒏𝒕𝒆𝒍𝒍𝒊𝒈𝒆𝒏𝒄𝒆 👉 • Artificial Intelligenc...
𝑪𝒍𝒐𝒖𝒅 𝑪𝒐𝒎𝒑𝒖𝒕𝒊𝒏𝒈 👉 • Cloud Computing Tutorials
𝑾𝒊𝒓𝒆𝒍𝒆𝒔𝒔 𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒚 👉 • Wireless Technology Tu...
𝑫𝒂𝒕𝒂 𝑴𝒊𝒏𝒊𝒏𝒈 👉 • Data Mining & Business...
𝑺𝒊𝒎𝒖𝒍𝒂𝒕𝒊𝒐𝒏 𝑴𝒐𝒅𝒆𝒍𝒊𝒏𝒈 👉 • Simulation Modeling Tu...
𝑩𝒊𝒈 𝑫𝒂𝒕𝒂 👉 • Big Data Anaytics
𝑩𝒍𝒐𝒄𝒌𝒄𝒉𝒂𝒊𝒏 𝑻𝒆𝒄𝒉𝒏𝒐𝒍𝒐𝒈𝒚 👉 • Blockchain Technology
𝑰𝑶𝑻 👉 • Internet Of Things
𝓕𝓸𝓵𝓵𝓸𝔀 𝓶𝓮 𝓸𝓷 𝓘𝓷𝓼𝓽𝓪𝓰𝓻𝓪𝓶 👉 / ngnieredteacher
𝓥𝓲𝓼𝓲𝓽 𝓶𝔂 𝓟𝓻𝓸𝓯𝓲𝓵𝓮 👉 / reng99
𝓢𝓾𝓹𝓹𝓸𝓻𝓽 𝓶𝔂 𝔀𝓸𝓻𝓴 𝓸𝓷 𝓟𝓪𝓽𝓻𝓮𝓸𝓷 👉 / ranjiraj
𝓖𝓲𝓽𝓗𝓾𝓫👉 github.com/ran...

[@RanjiRaj18]

For notes👉 github.com/ranjiGT/ML-latex-amendments

[@AnshulBhardwaj]

Hyperparameter is - A configuration that is external to the data and whose value can not be estimated from the data.
Thank you for this definition

[@murarikumar346]

Model Parameter: Instrinsic configuration to the model and whose value is defined by the data. For example (1.) in case of linear regression modeling, slope(m) and constant(c) are parameter of the model. (2.) In case of ANN, weight(w) is parameter of ANN-Model.
Hyperparameter: It is a configuration that is external to the data and whose value cannot be estimated from the data. It is set externally. It is set by data analyst. Hyperparameter is used to derive model prameter. Hyperparameter value is derived from the heuristics i.e., it is a self discoverable value instead of it is being automatically set.

[@sym3012]

For people new to ML, this is a perfect video to understand what a hyperparameter is. I was looking for an example related to k-fold cross validation though. Would have liked that as an example in the video.

[@RanjiRaj18]

I have a video on that, may be you could check the ML playlist.

[@souvikdas7200]

Not only you just explain the concept along with that statistical aspects has been covered too. Keep doing that.... lots of best wishes.

[@shailyjain2711]

Your explanation is best for statistical person, really helpful, .... thanks

[@pujarivarnika7855]

After completing writing and teaching part, just a move from the board to see the entire board in for 2 seconds before closing. So that take screenshot of it for reference

[@RanjiRaj18]

sure will do in future videos.

[@victoradepoju8158]

Realy helpful and understandable

[@Ravindrakumar-vr3hr]

Well explained

[@shivamlasiyal1795]

Damn so easily and well explained thanks sir

[@Irwansight]

great explanation Sir. Thanks

[@samansamanbooyan]

well explained! thank you!

[@kkartz123]

very decent explaination.

[@marouasedoud7033]

thank you ❤

[@RanjiRaj18]

You're welcome 😊

[@Abhishek_Dahariya]

excellent explaination 👍

[@_iamankitt_]

Thanks bro

[@karthikgolagani6844]

this is too deep for me, i just want the definition for hyper parameter in ML

[@FeddFGC]

Every parameter that's not taught by your learning algorithm. So parameters that you manually put in I guess. I'm not sure either, I just gave you this answer from my course lmao

[@rocksand5350]

a parameter that the model assigns for itself is model parameter (based on the data it feeds upon), a parameter that is set extrinsically (by a practitioner ex: data scientist) to derive model parameters is hyper parameter

[@AnuragSingh-vv3qv]

Nice

[@mmm-me4kk]

if we change by KNN for example the value of K (so K = 3 instead of K = 4), are we then tuning the hyperparameter?

[@abhishekjn3390]

ty sir

[@rubayetalam8759]

what's value of x? at 2:27

[@omdeshpande1162]

You look similar to south indian actor Rajeev Kanakala, just search his name

[@abdullahhussein6568]

Could you please help me with ML? May I have your contact information?

[@shivamyadav-ct6og]

Learning rate in Perceptrons model is a hyperparameter like in Gradient Descent and Adaline to ...???

[@RanjiRaj18]

Yes same though