Talking to oneself is a trait that feels inherently human. Our inner monologues help us organize our thoughts, make decisions, and understand our emotions. However, it’s not just humans who can reap the benefits of such self-talk. In a groundbreaking study published in Neural Computation, scientists from the Okinawa Institute of Science and Technology (OIST) have demonstrated the potential of inner speech to improve AI learning. The research shows how AI models can generalize across different tasks more effectively when supported by both inner speech and short-term memory.
“This study highlights the importance of self-interactions in how we learn. By structuring training data in a way that teaches our system to talk to itself, we show that learning is shaped not only by the architecture of our AI systems but by the interaction dynamics embedded within our training procedures,” says first author Dr. Jeffrey Queißer, Staff Scientist within OIST’s Cognitive Neurorobotics Research Unit.
Brain-Inspired Modeling for AI Learning
The team has long been interested in content-agnostic information processing—the ability to perform tasks beyond the exact situations we’ve previously encountered by learning general methods and operations. “Rapid task switching and solving unfamiliar problems is something we humans do easily every day. But for AI, it’s much more challenging,” notes Dr. Queißer. “That’s why we take an interdisciplinary approach, blending developmental neuroscience and psychology with machine learning and robotics, among other fields, to find new ways to think about learning and inform the future of AI.”
The researchers initially focused on the AI models’ memory architecture, examining the importance of working memory for task generalization. From remembering instructions to quick mental math, working memory is the short-term ability of a system to retain and use information. By simulating tasks of varying difficulty, they examined the effectiveness of different memory structures, demonstrating that systems which included multiple working memory slots—temporary containers for pieces of information—could generalize better on the tricky tasks of reversing the order of and regenerating patterns.
Enhancing AI with Self-Mumbling
Upon adding self-mumbling targets—telling the system to talk to itself a certain number of times—the researchers gained better performance, particularly when multitasking or completing tasks with many steps. “Our combined system is particularly exciting because it can work with sparse data instead of the extensive datasets usually required to train such models for generalization. It provides a complementary, lightweight alternative,” emphasizes Dr. Queißer.
This development follows a growing trend in AI research that seeks to mimic human cognitive processes. By incorporating elements of self-dialogue and memory, AI systems are not only becoming more efficient but also more adaptable to real-world applications.
Learning to Learn Better
Looking forward, the researchers plan to make things ‘messier.’ Dr. Queißer says, “In the real world, we’re making decisions and solving problems in complex, noisy, dynamic environments. To better mirror human developmental learning, we need to account for these external factors.”
This ties in with the team’s overarching goal to understand the neural basis of human learning. “By exploring phenomena like inner speech, and understanding the mechanisms of such processes, we gain fundamental new insights into human biology and behavior,” concludes Dr. Queißer. “We can also apply this knowledge, for example, in developing household or agricultural robots which can function in our complex, dynamic worlds.”
The move represents a significant step forward in AI development, potentially paving the way for more intuitive and responsive systems that can operate under a variety of conditions. As AI continues to evolve, the integration of human-like cognitive strategies could prove crucial in bridging the gap between machine efficiency and human adaptability.
Meanwhile, the implications of this research could extend beyond AI, offering new perspectives on how humans learn and adapt. By understanding and replicating these processes, scientists hope to unlock new avenues in both artificial intelligence and cognitive science.