Please open the PDF and Code links mentioned above to find detailed project architecture schematics and further details!
Abstract:
In the past few years, advances in artificial intelligence have captured the public imagination and led to widespread acceptance of AI-infused assistants. We have come across a multitude of systems ranging from Google Assistant, Amazon Alexa, Siri and so on. The goal is to advance the ability of systems to interact with us in a more natural way and this is critical for the AI-human relationship to reach its fullest potential. AI-infused personal assistants let us ask a wide array of questions and receive answers. Since, these systems are highly context insensitive, user frustration levels with AI conversational agents are beginning to rise. To add this contextual intelligence to the system, we explore & design different intelligent assistant architectures ranging from supervised to reinforcement (Deep Q) learning.
Instructions
- Clone the project repository.
- Explore schematics, benefits, trade-offs and sensitivity points of different supervised and deep reinforcement learning based intelligent assistant architectures.