Because the boundaries of artificial intelligence (AI) continually expand, researchers grapple with one among the largest challenges in the sector: memory loss. Generally known as “catastrophic forgetting” in AI terms, this phenomenon severely impedes the progress of machine learning, mimicking the elusive nature of human memories. A team of electrical engineers from The Ohio State University are investigating how continual learning, the flexibility of a pc to always acquire knowledge from a series of tasks, affects the general performance of AI agents.

Bridging the Gap Between Human and Machine Learning

Ness Shroff, an Ohio Eminent Scholar and Professor of Computer Science and Engineering at The Ohio State University, emphasizes the criticality of overcoming this hurdle. “As automated driving applications or other robotic systems are taught recent things, it is important that they do not forget the teachings they’ve already learned for our safety and theirs,” Shroff said. He continues, “Our research delves into the complexities of continuous learning in these artificial neural networks, and what we found are insights that begin to bridge the gap between how a machine learns and the way a human learns.”

Research reveals that, just like humans, artificial neural networks excel in retaining information when faced with diverse tasks successively quite than tasks with overlapping features. This insight is pivotal in understanding how continual learning could be optimized in machines to closely resemble the cognitive capabilities of humans.

The Role of Task Diversity and Sequence in Machine Learning

The researchers are set to present their findings on the fortieth annual International Conference on Machine Learning in Honolulu, Hawaii, a flagship event within the machine learning field. The research brings to light the aspects that contribute to the length of time a man-made network retains specific knowledge.

Shroff explains, “To optimize an algorithm’s memory, dissimilar tasks ought to be taught early on within the continual learning process. This method expands the network’s capability for brand spanking new information and improves its ability to subsequently learn more similar tasks down the road.” Hence, task similarity, positive and negative correlations, and the sequence of learning significantly influence memory retention in machines.

The aim of such dynamic, lifelong learning systems is to escalate the speed at which machine learning algorithms could be scaled up and adapt them to handle evolving environments and unexpected situations. The final word goal is to enable these systems to mirror the educational capabilities of humans.

The research conducted by Shroff and his team, including Ohio State postdoctoral researchers Sen Lin and Peizhong Ju and Professors Yingbin Liang, lays the groundwork for intelligent machines that would adapt and learn akin to humans. “Our work heralds a brand new era of intelligent machines that may learn and adapt like their human counterparts,” Shroff says, emphasizing the numerous impact of this study on our understanding of AI.