Fujitsu and the Center for Brains, Minds and Machines (CBMM) have achieved an important milestone in a joint initiative to deliver improvements in accuracy of artificial intelligence (AI) models.
The results of the research collaboration between Fujitsu and CBMM are published in a paper discussing computational principles that draw inspiration from neuroscience to enable AI models to recognize unseen (out-of-distribution, OOD) data that deviates from the original training data.
Seishi Okamoto, Fellow at Fujitsu Limited commented, “Since 2019, Fujitsu has engaged in joint research with MIT’s CBMM to deepen our understanding of how the human brain synthesizes information to generate intelligent behavior, pursuing how to realize such intelligence as AI and leveraging this knowledge that contributes to solving problems facing a variety of industries and society at large. This achievement marks a major milestone for the future development of AI technology that could deliver a new tool for training models that can respond flexibly to different situations and recognize even unknown data that differs considerably from the original training data with high accuracy, and we look forward to the exciting real-world possibilities this opens up.”
Tomaso Poggio, the Eugene McDermott Professor at the Department of Brain and Cognitive Sciences at MIT and Director of the Center for Brains, Minds and Machines, remarked, “There is a significant gap between DNNs and humans when evaluated in out-of-distribution conditions, which severely compromises AI applications, especially in terms of their safety and fairness. Research inspired by neuroscience may lead to novel technologies capable of overcoming dataset bias. The results obtained so far in this research program are a good step in this direction.”
Highlights of the paper will be presented at the NeurIPS 2021 (Conference on Neural Information Processing Systems), showing improvements in the accuracy of AI models.
Researchers at Fujitsu and CBMM have made collaborative progress in understanding AI principles enabling recognition of OOD data with high accuracy by dividing the DNN into modules – for example shape and color, amongst other attributes – taking a unique approach inspired by the cognitive characteristics of humans and the structure of the brain.
An AI model using this process was rated as the most accurate in an evaluation measuring image recognition accuracy against the “CLEVR-CoGenT” benchmark, as shown in the paper presented by the group at NeurIPS.