IIT Hyderabad makes new inroads into artificial intelligence technology

Hyderabad: Researchers at the Indian Institute of Technology (IIT) Hyderabad have developed a method to tackle the lack of transparency in the deep learning (DL) models used in phones, tablets and television sets. The method, which accesses the “insides of artificial intelligence (AI) programs”, will prevent end-users from losing trust over the system.

Speaking about the research, Dr Vineeth Balasubramanian, associate professor, department of computer science and engineering, said, “The simplest application that we know of deep learning is in machine translation, speech recognition or face detection. New algorithms are being used in a variety of disciplines, including engineering, finance, artificial perception and control and simulation. Much as the achievements have wowed everyone, there are still challenges to be met.”

Dr Balasubramanian felt there is a need for methods that can access the underbelly of AI programs and unravel their structure and functions.

The IIT Hyderabad team approached this problem with artificial neural network (ANN) architectures using causal inference with what is known in the field as a ‘structural causal model.’