Zafar Ali

14 Questions 51 Answers 0 Followers

Questions related from Zafar Ali

Tanh or ReLu, which activation function perform better in firing a neuron?

I would like to ask a question from Neural nets community, that there exist many activation functions such as Sigmoid, Tanh, ReLu etc., to fire a neuron. To insure non-linearity and better update...

03 October 2018 426 8 View

Can someone differentiate between Cosine, Adjusted cosine, and Pearson correlation similarity measuring techniques?

Different similarity measuring techniques have been used in finding similarity between user profiles. However, what is the difference between these techniques, in which circumstances we should use...

04 March 2017 8,252 4 View

Any special evaluation metrics for context aware recommender systems?

Hi everyone, If we want to evaluate the results generated by a context-aware recommender systems, which among the existing metrics would be suitable for this situation. Also, i would like to know...

03 June 2016 7,052 4 View

Evaluating recommender systems?

Hi everyone, If a researcher want to evaluate the results and performance of a recommender system, what possible approaches he/she can use?. Can someone categorize these methods and explain its...

11 May 2016 8,287 5 View

What are the different potential applications of context-aware recommender systems?

Recommendation systems are one of the information personalisation approach which is used to suggest relevant items and information according to user preferences and objective behaviors. As far as...

03 May 2016 5,904 6 View

Any idea about using Multi-Class SVM (Support Vector Machine) to classify large size PDF documents?

I want to classify PDF documents belong to various topics and field of study. As SVM (support vector machine) is a suitable approach to classify such kind of textual documents, can anybody provide...

13 April 2016 2,189 11 View

What is the differentiation between user profile and item profile in any recommender system?

In designing a recommender system, we need to represent both users and items by using their profiles. But, sometimes these roles are represented by the same set of features. Can anyone tell me and...

10 April 2016 7,148 13 View

What parameters we should consider in design of a context aware recommender system?

If we want to develop a context-aware recommender system in domains (such as movies, other products) which parameters will play the key role?. As far as my knowledge is concerned, i have noticed...

29 March 2016 4,798 7 View

Is there any new area of research in which recommender systems are required but not yet designed?

Recommender systems have been developed in various domains however, there can be some areas in which these systems needs to be designed. Can you please give valuable ideas and suggestions...

15 March 2016 181 13 View

How collaborative filtering recommender systems generate predictions for those new items user has not yet rated?

Can anybody explain how collaborative filtering recommender systems make predictions for new items uisng Weighted sum method. Most of the research articles has provided formula but not explained...

20 February 2016 4,042 1 View

How can we calculate adjusted cosine similarity for two items represented by their ratings in a collaborative filtering recommender system?

I want to compute adjusted cosine similarity value in an item-based collaborative filtering system for two items represented by a and b respectively. these items are represented by two vectors...

18 February 2016 3,080 4 View

Which one is the best similarity calculation formula to use for finding similar users in Collaborative filtering recommendations?

I am working on a recommender system where i need to calculate similarity in ratings for user friends. which one out of cosine similarity and pearson correlation is better approach?

04 February 2016 4,566 1 View

How to use Naive Bayes Classifier for numerical data?

Is it possible to use naive byes algorithm for features represented by Term frequencies. i am classifying books on the bases of features these books have, for that, i am representing these...

09 January 2016 4,549 3 View

Can we use mixed features both of nominal and numerical type in the naive Bayes classification algorithm?

Is it possible to use both kinds (nominal, numerical) of features in designing training set for Naive byes machine learning algorithm. Can we mention feature frequencies for designing feature...

06 January 2016 3,151 2 View