IIT Hyderabad researchers develop method to access the inner workings of AI
Previously researchers have developed Artificial intelligence and with that many inventions have been taken place in every field like Medical, education, finance, IT etc…. now it’s touching it’s next level by knowing the inner workings of artificial intelligence models. Moreover when a research is made, there will not be an end like that it continuous innovating new things.
IIT Hyderabad researchers have developed a method by which the inner workings of Artificial Intelligence (AI) models can be understood. With the help of this we can understand better about artificial neural networks or ANN which are AI models and programs that mimic the working of the human brain like that machines can learn to make decisions in a more human-like manner.
Vineeth N Balasubramanian a researcher in IIT Hyderabad, proposed a new method to compute the average causal effect of an input neuron on an output neuron. It is significant to understand which input parameter is ‘causally’ responsible for a given output.
For instance in the field of medicine, how does one know which patient attribute was causally responsible for the heart attack? “Our (IIT Hyderabad research) method provides a tool to analyse such causal effects, Balasubramanian explained.
Artificial neural networks also known as Deep Learning (DL), help machines train themselves to process and learn from data that has been supplied to them as input, and almost match human performance in many tasks. However, one does not know how these machines arrive at decisions, making them less useful when the reason for decisions is necessary, according to a release shared by the institute.
Along with Balasubramanian, his student researchers- Aditya Chattopadhyay, Piyushi Manupriya, and Anirban Sarkar are also part of this research team. Their effort has recently been published in the proceedings of 36th International Conference on Machine Learning, one of the highest-rated conferences in AI and ML, the institute stated.