Exploring machine learning methodologies for brain decoding

We are developing machine learning methodologies, particularly focused on reading out information from the brain. As one of the key attempts, our recent study demonstrates that images imagined in the mind can be visualized (reconstructed) from fMRI brain signals, although the accuracy is still under development (see this page for details). We are developing and improving these machine learning methodologies for neuroscience research and neural engineering.

• Mental image reconstruction using generative AI — Decoding brain signals into images: New technology developed by QST

• AI-generated imaging using brain activity hits record 75% accuracy: Japan research

• Japan Succeeds in Image Reconstruction from Brain Signal Data

• Japan scientists create world's 1st mental images with AI tech

Accelaration of machine learninig algorithms using quantum and quantum-inspired techniques

Quantum computing, quantum-inspired algorithms, and Ising machines have attracted attention due to their potential to speed up computations. We are engaged in developing fast and scalable machine learning algorithms by leveraging those computational techniques.

• Quantum-inspired canonical correlation analysis for exponentially large dimensional data

• Quantum circuit-like learning: A fast and scalable classical machine-learning algorithm with similar performance to quantum circuit learning

• Fast, accurate, and interpretable decoding of electrocorticographic signals using dynamic mode decomposition