- 20
- 198 271
TheDataPost
United States
Приєднався 26 чер 2019
Feature Scaling
Explanation of feature scaling clearly explained.
Image Links:
towardsdatascience.com/gradient-descent-algorithm-and-its-variants-10f652806a3
mccormickml.com/2013/08/15/the-gaussian-kernel/
Image Links:
towardsdatascience.com/gradient-descent-algorithm-and-its-variants-10f652806a3
mccormickml.com/2013/08/15/the-gaussian-kernel/
Переглядів: 9 557
Відео
Linear Regression Part II
Переглядів 8404 роки тому
A continued explanation of linear regression. Links: www.quora.com/How-is-it-determined-if-a-slope-is-positive-negative-or-undefined
Overfitting
Переглядів 5884 роки тому
An explanation of the data science concept overfitting. Links: www.geeksforgeeks.org/underfitting-and-overfitting-in-machine-learning/ www.kaggle.com/learn-forum/61822
Splitting Data
Переглядів 1,1 тис.4 роки тому
An explanation of what splitting data is and why it is necessary. Links: www.commonlounge.com/discussion/5f6c903d4821416b9b2ad2e4b2950250/history www.kaggle.com/learn-forum/61822
Classification vs. Regression
Переглядів 11 тис.4 роки тому
Simple explanation of classification and regression.
Supervised vs. Unsupervised Learning
Переглядів 4,6 тис.4 роки тому
A simple explanation of the differences between supervised and unsupervised learning.
Continuous vs. Discrete Values
Переглядів 9754 роки тому
Explanation of the differences between continuous and discrete values.
What is Machine Learning?
Переглядів 3 тис.4 роки тому
A quick and simple explanation of what machine learning is. Links: giphy.com/gifs/imadeit-qKltgF7Aw515K www.geeksforgeeks.org/clustering-in-machine-learning/
Random Forests Explanation and Visualization
Переглядів 12 тис.4 роки тому
explanation of random forests clearly explained
Bias Variance Tradeoff
Переглядів 3,2 тис.4 роки тому
A core machine learning concept known as bias variance tradeoff clearly explained. Links: scott.fortmann-roe.com/docs/BiasVariance.html www.geeksforgeeks.org/underfitting-and-overfitting-in-machine-learning/
DBSCAN Advantages and Disadvantages
Переглядів 2,8 тис.4 роки тому
analysis of the strengths and weaknesses of the dbscan algorithm
K-Means Implementation and Parameter Tuning
Переглядів 8 тис.4 роки тому
K-Means Implementation and Parameter Tuning
K-Means Clustering Explanation and Visualization
Переглядів 74 тис.4 роки тому
K-Means Clustering Explanation and Visualization
DBSCAN Implementation and Parameter Tuning
Переглядів 9 тис.4 роки тому
DBSCAN Implementation and Parameter Tuning
DBSCAN Explanation and Visualization
Переглядів 41 тис.4 роки тому
DBSCAN Explanation and Visualization
K-Means Advantages and Disadvantages
Переглядів 4 тис.4 роки тому
K-Means Advantages and Disadvantages
That was a really nice explanation, though I wonder if The Algorithm might deboost this video based on what you said around 0:31...
Concise and Clear!
phenomal explanation. after watching around a dozen of videos and not being sure what the difference is, you made it so simple in just 2 minutes. excellent job
This is the easiest explanation to understand.
great explanation..thanks
exeptional explanation!
Simplest and to the point explanation Thank You
Amazing video needed. this for my data mining course
Wow, best explanation Ive seen
Awesome video man!
Holy moly! i'm so glad i found this channel! i'm bulk watching every video
Im glad I found this. Easy to understand. Thank you
@TheDataPost Which tool/software do you use for the visualization?
great vid
the best and easy explanation ever, good job
thanks
Perfectly explained, thanks!
Very good video
great vid. Thank you
Thanks
you could use more of the actual terminology, like fit and predict phases, but overall congrats very weel and concise video
This video referred to one aspect many of the videos about the same subject do not: You get one model per fold (one set of "fitted" parameters, one "RMSE" if that is what you are using to evaluate that model, one set of predicted features, etc), not one final model so, as the author said, you use it to evaluate how a certain type of model can perform by averaging the total of models (averaging the statistic you are using to evaluate how good is the model) you get when doing one model training per fold, NOT to find the final model parameters. It is almost never mentioned this tiny detail. And I see many people, like myself, wondering what the end result of this method is and its usage.
Thanks for the video! In the 2:30 part of the video, I would like to know what software did you use to create this animation effect?
Very much appreciated. Explained quickly and clearly
Quick and effective. Great video
Thanks 👍
Initial centroids are based on points already in the dataset, not selecting them randomly like he did in the beginning.
Excellent tutorial, appreciate your efforts
Best explanation!
amazing
very cool
Vey clear, thank you
That's a clear explanation, thanks alot
I love yoy, thanks
Now i understand. Thanks
@0:27 The strip function seems to not work for some reason. It says " tuple' object has no attribute 'strip' "
Thank you thank you.. I was puzzled with how do we decide which model to adopt until I saw this video.
Thanks for this! How to use the number of clusters if you don't know beforehand?
A gaussian mixed model can be used to estimate the number of clusters
Or you can use agglomerative clustering where the number of clusters will be equal to the number of observations
You can use methods such as "The Elbow Method" to estimate the correct number of clusters for each dataset. What it does is it gets the WSS for each cluster and it selects the number of cluster where the WSS presents diminishing returns. But can you always find more info online. Good luck!
This video is proof there are only 2 genders out there! Take that woke people
straight to the point, thanks.
Best explanation I have seen soooo farr 👏
very nice! thank you!
Very intuitively explained! kudos!
short and clear.Thank you
And this was how AI took the world.
This is a very basic algorithm. I don't this is the world ending AI we need to be concerned about. Now, reinforcement learning networks are potentially dangerous.
does it mean it has to visulise the points, and then may select initial centroids?
great
Nice
amazing simulation in the end
Great explanation. You made it simple and concise.