DataHour: Need for Self Supervised Learning - Practice at SAP

DataHour: Need for Self Supervised Learning - Practice at SAP

11 Nov 202213:11pm - 11 Nov 202214:11pm

DataHour: Need for Self Supervised Learning - Practice at SAP

About the Event

Self-supervised learning (SSL) is an unsupervised approach for representation learning without relying on human-provided labels. It creates auxiliary tasks on unlabeled input data and learns representations by solving these tasks. SSL has demonstrated great success on images (e.g., MoCo, PIRL, SimCLR) and texts (e.g., BERT) and has shown promising results in other data modalities, including graphs, time-series, audio, etc. On a wide variety of tasks, SSL without using human-provided labels achieves performance that is close to fully supervised approaches.

In this DataHour Dr, Sai will provide you a basic understanding of the need for SSL and then practically demonstrate the successful implementations of SSL to tasks in the industry setting of SAP.


Prerequisites:
 
Interest of Learning Data Science and Basic understanding of Neural Networks, Machine Learning

  1. Best articles get published on Analytics Vidhya’s Blog Space
  2. Best articles get published on Analytics Vidhya’s Blog Space
  3. Best articles get published on Analytics Vidhya’s Blog Space
  4. Best articles get published on Analytics Vidhya’s Blog Space
  5. Best articles get published on Analytics Vidhya’s Blog Space

Who is this DataHour for?

  1. Best articles get published on Analytics Vidhya’s Blog Space
  2. Best articles get published on Analytics Vidhya’s Blog Space
  3. Best articles get published on Analytics Vidhya’s Blog Space

About the Speaker

Dr. Sai Hareesh

Dr. Sai Hareesh

Research Expert at SAP Labs India

Dr. Sai Hareesh is currently working as a Research Expert at SAP Labs India. He has completed his Ph.D in Computer Vision from Sri Sathya Sai Institute of Higher Learning. He has 12 + years of working experience in both Academia and Industry Working on a variety of AI (ML + DL + MR) algorithms for HR, Defense, Healthcare, Telecom, Industrial IOT, Digital Marketing, Retail, Business and Renewables domain data. He has Hands-on experience in Computer Vision (video, image), NLP(text), IoT (time-series, numerical data ), Speech (Audio) complemented with Data Visualization and Creative Ideation.Till date he has registered 35 publications and 43 patents / Disclosures and been honored  by 35 Awards. He is also an efficient public speaker and has presented more than 27 Technical Talks.

Participate in discussion

Registration Details

7513

Registered

Become a Speaker

Share your vision, inspire change, and leave a mark on the industry. We're calling for innovators and thought leaders to speak at our event

  • Professional Exposure
  • Networking Opportunities
  • Thought Leadership
  • Knowledge Exchange
  • Leading-Edge Insights
  • Community Contribution