Brain organoids decode Braille at about 83% accuracy when combined
What happened
A University of Bristol team wired brain organoids to tactile sensors so they produced distinguishable neural signals for Braille letters, then classified them with a support vector machine. A single organoid decoded at about 61% accuracy; three combined reached about 83%. The organoids are under 1 mm across and hold about 10,000 neurons. Under artificial noise, signals processed by the organoids were harder to disrupt than direct decoding. The study has not shown the organoids can learn; next steps are texture and edge tasks and closed-loop feedback.
Written by AI from the coverage · updated 45 minutes ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageMini brain organoids 'reading' Braille key step towards biohybrid computing
布里斯托大学团队将脑类器官接入触觉传感器，使其对盲文字母产生可区分的神经信号，单个类器官解码准确率约 61%，三个类器官组合提升至约 83%。这些类器官直径不足 1 毫米、含约 1 万个神经元，信号由支持向量机分类；在人工噪声下，经类器官处理的信号比直接解码更难被干扰。研究未证明类器官具备学习能力，下一步将拓展到纹理、边缘等触觉任务与闭环反馈。
Heat over time
Not enough continuous observations to draw a trend yet.