We use sparse modeling technology that can extract features with a small amount of training data or without any training data. You can use AI in areas where large amounts of training data are not available and where collecting training data is too expensive.
Unlike deep learning, in which the decision-making process of AI is a black box, ours is visualized in a form that can be interpreted by humans. Our AI provides high interpretability in medical and mission-critical areas where it is essential to understand AI’s decision-making process.
Training and Inference at the Edge
Our technology can prevent the performance degradation of AI due to environmental changes by additional learning on the edge side. Supports both learning and inference completely offline without the need for a server or internet connection.