Presented By O’Reilly and Intel AI
Put AI to work
8-9 Oct 2018: Training
9-11 Oct 2018: Tutorials & Conference
London, UK

Design to architecture and code using deep learning: Implications for GUI development

Archisman Majumdar (Mphasis)
16:00–16:40 Thursday, 11 October 2018
AI in the Enterprise, Impact of AI on Business and Society
Location: Hilton Meeting Room 3-6
Secondary topics:  Interfaces and UX

Who is this presentation for?

  • Executives, data scientists, managers, and machine learning experts

Prerequisite knowledge

  • Basic knowledge of AI and neural networks

What you'll learn

  • Understand the implications of deep learning techniques on frontend GUI development
  • Explore emerging AI and deep learning techniques for automatically generating web pages on the required infrastructure


The process of software application development consists of requirement gathering and converting these requirements to a specific set of instructions to be performed on a specific set of hardware. With the evolution of machine learning, the cloud, and containerization, multiple activities in the process are now prime for disruption. One such area is the graphical user interface, particularly its deployment and management across a cluster of host servers.

The graphical user interface creation process in software development involves converting the wireframes and screenshots created by designers into computer code. Currently, every step of this development process is manual, and thus costly and time consuming. It involves bringing together various stakeholders, exploring various alternate options, and creating images, mock screens, and prototypes, which are eventually turned into interactive screens.

On the other hand, the deployment architecture—the hardware and software required for different types of web pages—is fairly standard. Thus, the web servers required and their hardware configurations can often be determined from the text descriptions provided by the user. With the evolution of cloud formation templates, containerized applications, and programs that can automate the deploying, maintaining, and scaling applications, the requirement for human intervention is drastically reduced. Many of these tasks are repetitive and hence prime for automation and disruption.

Archisman Majumdar and Jai Ganesh describe the effects of AI techniques on frontend GUI development—specifically, the use of automatically generated code and architecture from text descriptions. Archisman and Jai outline the process of automated creation of the user interface using deep learning and the provisioning, management, and scaling of the hardware required for the application, based on text descriptions provided by the user. They also share deep learning techniques for text-to-image creation and template-to-code generation, along with cloud technologies in automated deployment, management, and scaling of such applications.

Archisman Majumdar


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).

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)