In this talk, we discuss some of the recent developments in the applications of AI/ML on Software Engineering tasks. Specifically, we focus on the applications of AI/ML on GUI development.

One of the main activities in the creation of the Graphical User Interface involves converting the wireframes, screenshots, and natural text descriptions created by users into computer code. Recent advances in image processing, natural language understanding, and the advent of generative models have provided us with the possibilities for generating code directly from images and/or text descriptions. Thus, many of the repetitive tasks in Software Development phases are now prime for automation. In this session, we will deep dive into some of the recent advances in the applications of deep learning techniques for text-to-image creation, image-to-code generation.

Outline:

1. Role of AI in Application Development and Maintenance


2. Deep Learning in Software Engineering


3. The current scenario – GUI development


4. Deep dive –Mphasis deep learning frameworks for software engineering tasks
   
   
   • Image to Code
   
   
   • Template/Wireframe to Code
     
     
     • Computer Vision techniques
     
     
     • Image Processing techniques
     
     
   • Text to Code
     
     
     • NLP techniques
     
     
5. Application of GAN for Interface Design


6. Challenges and Future work


7. Conclusion

Who is this presentation for?

Executives, data scientists, managers, and machine learning experts

SPEAKERS

Dr. Archisman Majumdar

Dr. Archisman Majumdar is an Assistant Vice President and lead for applied AI at Mphasis Next Labs, where he conceptualizes, develops, and leads multiple products in the analytics R&D space. Archisman is responsible for the research, innovation, and go to market for the products and solutions. His areas of expertise are business analytics, machine learning, product management, and information systems research. He holds a PhD in quantitative methods and information systems from the Indian Institute of Management Bangalore (IIMB).

Rajendrakumar Mishra

Rajendrakumar Mishra is Manager at Mphasis NextLabs, where he leads a team of young and vibrant individuals involved in building the Next in AI and Cognitive space. His recent work at NextLabs involves research and development of several projects transforming the way software development process was approached traditionally using Generative Adversarial Network, Deep Learning, Computer Vision and NLP.

He has previously worked in Smart Assistant and Chatbot domain, and Automated Digital Content Generation. His area of expertise includes Machine Learning, Deep Learning, Natural Language Processing and Image Processing. He holds an M.Tech. in IT from International Institute of Information Technology, Bangalore. He is a vivid blogger and poet.