Recommendation systems | Sequence Models

GDG Bangalore
Sun, Jun 14, 2020, 6:00 PM (IST)

35 RSVP'ed

About this event

This is a collaborative event between GDG Bangalore , WiMLDS Mysore and Applied Singularity

Pic Credit : Mohammed Shafi

Talk 1 :

Youtube Live URL : https://www.youtube.com/watch?v=vDBs1QSJJwA

Title: Recommendation systems: Need, Approaches, Modeling and Evaluation

Abstract: Recommender systems are present in a huge variety of applications, such as movies, music, news, books, research papers, search queries, social tags, and products in general, but they are also present in more sophisticated products where personalization is critical, like recommender systems for restaurants, financial services, life assurance, online dating, and Twitter followers. Recommender systems are really interesting when dealing with finding solutions for large amounts of good data, reduction of cognitive load on the user, and allowing new items to be revealed to users. We will see what are recommender systems, how they work, and how they can be implemented. We will also see the different paradigms of recommender systems based on the information they use, as well as the output they produce. We will explore the different characteristics and potentials of different prediction techniques in order to serve as a compass for research and practice in the field of recommendation systems.

Speaker : Dr.Kanimozhi U
Designation: Senior Data Scientist @ Crayon Data
https://www.linkedin.com/in/kanimozhi-u-ph-d-8b116058/

Talk 2 :

Topic : Sequence Models and their Applications

Youtube Live URL : https://www.youtube.com/watch?v=HD0pHs-urtg

Data that forms the basis of many of our daily activities like speech, text, videos has sequential/temporal dependencies. Traditional deep learning models, being inadequate to model this connectivity needed to be made recurrent before they brought technologies such as voice assistants (Alexa, Siri) or video based speech translation (Google Translate) to a practically usable form by reducing the Word Error Rate (WER) significantly. RNNs solve this problem by adding internal memory. The capacities of traditional neural networks are bolstered with this addition and the results outperform the conventional ML techniques wherever the temporal dynamics are more important. In this session, we will develop an intuition for sequence models through the mathematical discussion of RNNs with some real world applications that are being developed at Symbiosis Centre for Applied AI.

Speaker Bio :

LinkedIN : https://www.linkedin.com/in/raheewalambe/

Dr. Rahee Walambe

Rahee is an experienced Robotics and AI researcher. She has combined core research with cutting edge technology to create unique products. Passionate about applications of Deep Learning, she has worked in diverse domains including, Healthcare, Assistive Tech, Sequence modeling, Multi-sensor data fusion. Her work towards developing solutions that can create societal impact has been recognized at many levels. Currently, she is an Associate Research Faculty at Symbiosis Centre for Applied Artificial Intelligence (SCAAI) and Associate Professor at Symbiosis Institute of Technology (SIT), Pune. Her love for teaching drives her sessions at various academic and corporate workshops. She is a recipient of prestigious SPARC research grants of MHRD with Arizona State University, USA and University of Queensland, AUS, WOS - A fellowship of DST, Govt of India. She is also the recipient of the Professor Fellowship Award of DUO ASME for year 2020 with Brunel University, UK.


Organizers