Ranjeev Mittu shares promises, limitations of machine learning

AI researcher offers insight on promise, pitfalls of machine learning

By Victor Chen,

These days, the latest developments in artificial intelligence (AI) research always get plenty of attention, but an AI researcher at the U.S. Naval Research Laboratory believes one AI technique might be getting a little too much.

Ranjeev Mittu heads NRL’s Information Management and Decision Architectures Branch and has been working in the AI field for more than two decades.

“I think people have focused on an area of machine learning—deep learning (aka deep networks)—and less so on the variety of other artificial intelligence techniques,” Mittu said. “The biggest limitation of deep networks is that a complete understanding of how these networks arrive at a solution is still far from reality.”

“There are numerous AI techniques of which machine learning is a subset,” he said. “While deep learning has been highly successful, it is also currently limited because there is little visibility into its decision rationale. Until we truly reach a point where this technique becomes fully “explainable,” it cannot inform humans or other automation as to how it arrived at a solution, or why it failed. We have to realize that deep networks are just one tool in the AI tool box.”

“The difficulty comes when you start to train machine learning algorithms on data that is of poor quality,” Mittu said. “Machine learning becomes unreliable at some point, and operators will not trust the outcomes of the algorithms.”

“There are many ways to improve predictive capabilities, but probably the best–of-breed will take a holistic approach and employ multiple AI techniques and strategically integrate the human decision-maker,” he said.

“We need to determine the right techniques, their limitations, and the data that is needed in order to get reliable answers in order for the users to trust the resulting system,” he said. “The field of AI has a long way to go in taking a holistic approach by strategically integrating the decision-maker in order to improve the performance of the human and machine system.”

Image credit:  MarineTraffic, Image credit: U.S. Transportation Command/Defense Logistics Agency