Readme for our lab's github

[hosseinfani]

Hi @dhwanipatel14 , @Rounique ,

This is going to be the readme (landing page) for our lab's github.

Can you work together and design a cut-clear bio for our lab in this readme.

Thanks.

[dhwanipatel14]

Yes, Dr. Fani we will work on the bio .

Also I want to ask that do we need to add in ReadME , from where the user can get the dataset, and run it?

Thanks

[hosseinfani]

@dhwanipatel14
what dataset? what run?
I am not sure I understand your comment.
This is a readme for the whole lab, its main activities, ...
Please talk to @Rounique . She helps you better.

[Rounique]

I'll take care of that.
@dhwanipatel14 We can talk about it soon.

[hosseinfani]

@Rounique @dhwanipatel14
I've added a paragraph when I see no update for this task.
It should not take this long for you to prepare a readme for our lab!

[dhwanipatel14]

Hello @hosseinfani
I have added some information on projects we conduct research on, will add more and for all areas.
Also, added some resources. Can you please review changes

Thanks

[hosseinfani]

@dhwanipatel14
thanks. where is it?

[dhwanipatel14]

I updated the ReadME and it ask me to create PR to update changes. I cant directly edit it. Wait I think there was some issue when I updated I will add that content again in sometime.

[hosseinfani]

please post it here. I review it here.

[dhwanipatel14]

Yes will do.

[dhwanipatel14]

Research Areas
Team Formation:
Team Formation in Social Network refers to forming the team of individuals, based on their skills or expertise to accomplish the specified task. This is a challenging task to group people as there are many factors that need to be considered based on the problem and individuals ‘abilities, knowledge, biological factors. In order to find effective groups to perform several tasks and solve problems researchers have found various algorithms to solve the problem and are still working to find effective solutions on it.
Community Prediction:
This is an open-source extensible end-to-end python-based framework to predict the future user communities in a text streaming social network (e.g., Twitter) based on the users’ topics of interest. User community prediction aims at identifying communities in the future based on the users' temporal topics of interest. We model inter-user topical affinities at each time interval via streams of temporal graphs. Our framework benefits from temporal graph embedding methods to learn temporal vector representations for users as users' topics of interests and hence their inter-user topical affinities are changing in time.
Machine Learning:
Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it to learn for themselves. It can be further classified as Supervised Learning and Unsupervised Learning.

Resources:
https://arxiv.org/pdf/2106.06090 (Graph Neural Networks for Natural Language Processing: A Survey)
http://norvig.com/chomsky.html (On Chomsky and the Two Cultures of Statistical Learning)
https://arxiv.org/abs/1902.06006 (Contextual Word Reprenstation)
https://colah.github.io/posts/2015-09-Visual-Information/ (Visual Information Theory)
https://arxiv.org/pdf/1912.00848.pdf (Neural Predictor for Neural Architecture Search)

Pytorch Resources
https://www.youtube.com/playlist?list=PLhhyoLH6IjfxeoooqP9rhU3HJIAVAJ3Vz
https://docs.rapids.ai/api/cudf/stable/
Deep Learning Resources:
https://www.youtube.com/playlist?list=PLpFsSf5Dm-pd5d3rjNtIXUHT-v7bdaEIe

Fun Facts
Our team has people coming from diverse regions of the world. They eat delicious food of different cuisines such as Indian, Japanese, Chinese, Korean and of course drink coffee everyday.