Dinesh Ladi

Data Scientist, Walmart Global Tech India

Dinesh has a Bachelors’s and Masters’s degrees in Energy Engineering from the Indian Institute of Technology, Bombay. He has an overall work experience of 4.5 years of experience in data analyses, machine learning, and NLP. Built end-to-end data pipelines and data tools for various enterprises. He is currently working as a Data Scientist at Walmart Global Tech India.

Past sessions

Summit 2021 Conversational AI with Transformer Models

May 27, 2021 11:35 AM PT

With the advancements in Artificial Intelligence (AI) and cognitive technologies,  automation has been a key prospect for many enterprises in various domains. Conversational AI is one such area where many organizations are heavily investing in.

 

In this session, we discuss the building blocks of conversational agents, Natural Language Understanding Engine with transformer models which have proven to offer state of the art results in standard NLP tasks.

 

We will first talk about the advantages of Transformer models over RNN/LSTM models and later talk about knowledge distillation and model compression techniques to make these parameter heavy models work in production environments with limited resources.

 

Key takeaways:

  • Understanding the building blocks & flow of Conversational Agents. 
  • Advantages of Transformer based models over RNN/LSTMS
  • Knowledge distillation techniques
  • Different model compressions techniques including Quantization
  • Sample code in PyTorch & TF2
In this session watch:
Rajesh Shreedhar Bhat, Senior Data Scientist, Walmart Global Tech India
Dinesh Ladi, Data Scientist, Walmart Global Tech India

[daisna21-sessions-od]