I'm preparing for an exam and looking for some exercises with solutions about pattern recognition and machine learning specially in the field of : SVM, Bayes, Decision Tree, Overfitting and underfitting, VC dimension, PCA, KNN, Kmeans, Combination, Renforcement learning,MAP and ML.
Review questions of Machine Learning course by Prof. Andrew, Stanford univ is available after logging in the following link
https://www.coursera.org/course/ml
Thanks for the link Chanukya !!
(Of cause the course was just to confirm what I already knew :-) )
Hi, try also looking through Numerical Recipes in C++. Although the algorithms are in C++, the background theory and examples are given in general. http://www2.units.it/ipl/students_area/imm2/files/Numerical_Recipes.pdf
Hi
we have some labs from the course "Fundamentals in statistical pattern recognition" that was given at EPFL last Spring semester. Labs are in Python but only includes PCA, k-Means, GMMs and MLPs.
http://www.idiap.ch/~marcel/professional/EPFL_2013.html
http://people.epfl.ch/cgi-bin/people?id=143942&op=teaching_phd&lang=en&cvlang=en
If you develop new labs I hope you will share them as well.
Thank you all for your comments.
It's a theoretical exam and I need some paper based and conceptual exercises.
Dear Dadi, I think the dataset you present is't straight forward my exam is conceptual and we are not allowed to use calculator in our exam. There will be some numerical question but they wont be complicated.
Coursera exercise:
You are running a company, and you want to develop learning algorithms to address each of the two problems.
problem 1:
You have a large inventory of identical items, You want to predict how many of these items will sell over the next 3 months.
Problem 2:
You would like software to examine individual customer account and for each account decide if it has been hacked/compromised.
should you treat these as classification or as regression problems?
choices
1. treat problem 1 as regression problem, problem 2 as a classification problem.
2. treat both as classification problems.
3. treat both as regression problems.
4. treat problem 1 as a classification problem and problem 2 as a regression problem,
I am sure the answer will be quite simple for you
Second exercise for you:
Choose which of the examples below consider as unsupervised learning algorithms:
1. Given a dataset of patients diagnosed as either having diabetes or not, learn to classify new patients as having diabetes or not.
2. Given a dataset of customers data, automatically discover customer segments, and group customers into different market segment.
3. Given email labeled as spam or non-spam, learn a spam filter.
4. Given a set of books in a library, group them into a shelf about the same field.
Dear Sami,
Many thanks for your exercises.
First exercise: I think problem two is an anomaly detection and I'd say it's a classification problem.
But I'm not sure about the problem one.
Second exercise: 2 and 4 are both unsupervised.
- Badges
- Science topic