Very good explanation. You deserve more subscription sir. RU-vid shorts might bring some users. Unfortunately, the algorithm works that way. All the best.
Sir for applying ANOVA for feature selection we need to apply normality test to demonstrate whether our data follows a normal distribution? Or we can apply for any type of data set without checking the normal distribution.... could you please clarify it?
Wow, this video on Linear Discriminant Analysis (LDA) by Instructor Saptarsi Goswami is incredibly informative and well-explained. I truly appreciate how he breaks down the concepts and compares LDA to PCA, highlighting the advantages of LDA. The explanations of the Fisher discriminant ratio, inter-class scatter, within-class scatter, and eigenvalue decomposition have given me a solid understanding of LDA. Thank you, Instructor Saptarsi, for sharing your expertise and helping me improve my knowledge in this area!
In the SWAP stage, do we drop the medoid node that is replaced by non-medoid node so it is not SWAP checked against other medoid nodes? in other words, dose the medoid node becomes non-medoid if it is replaced by a non-medoid and SWAP checked against the other initial medoids or removed from the list of medoids and non-medoids?
thank you so much for the video but i have a question in adasyn we choose must far instance to have higher chance of being sampled to avoid over fitting ? if yes but what if was a noisy one ?
Very informative and clear. Thank you for your effort! The following are the steps for the self-learning algorithm. 1. Train a supervised classifier on the labelled data. 2. Use the resulting classifier to make predictions on the unlabelled data. 3. Add the most confident of these predictions to the labelled data set. 4. Re-train the classifier on both the original labelled data and the newly obtained pseudo-labelled data. 5. Repeat steps 2-4 until no unlabelled data remain. There are two hyperparameters to set, the maximum number of iterations and the number of unlabelled examples to add at each iteration. One issue of self-learning is if we add many examples with incorrect predictions to the labelled data set, the final classifier may be worse than the classifier only trained on the original labelled data. I hope this answer may help someone interested in semi-supervised learning.
Thanks a lot sir. I have a doubt. I used LDA on Water Potability dataset from Kaggle. I did all the cleaning of data and proceeded with the methods you taught. Since my data was of binary classification, I had only 1 component. So, which graph should I plot for such cases to show classification and how? Also, the accuracy for my dataset was quite low around 61%. Any suggestions on this low accuracy on why it is so?
Thanks Sir, for the video which was very easy to understand. However I was thinking if the labelled dataset contains sample of 2 classes only(does not contain a sample of a possible 3rd class) and the unlabeled sample contains that specific sample of 3rd class (without the class), then I think the classifier trained on the labeled data cannot properly predict and its confidence for both classes would be low. Can anything or strategy be adopted in this case?
Please go through the parameters class imblearn.over_sampling.SMOTE(*, sampling_strategy='auto', random_state=None, k_neighbors=5, n_jobs=None). the sampling strategy parameter will give you the handle.