阅读说明：本技术 用于手势分类和施加的力估计的无监督机器学习的方法和装置 (Method and apparatus for unsupervised machine learning for gesture classification and applied force estimation ) 是由 亚历山大·巴拉尚 于 2019-02-28 设计创作，主要内容包括：用于训练分类模型并使用经训练的分类模型来识别用户执行的手势的方法和装置。一种装置包括处理器,该处理器被编程为：当用户执行手势的第一单个动作时,经由多个神经肌肉传感器从用户接收第一多个神经肌肉信号；基于第一多个神经肌肉信号训练分类模型,训练包括：从第一多个神经肌肉信号导出值,这些值指示手势的区别特征,该区别特征包括随着在手势的执行期间施加的力而线性变化的至少一个特征；以及基于该值在分类模型中生成手势的第一分类表示；以及基于经训练的分类模型和第二多个神经肌肉信号,确定用户执行了手势的第二单个动作。(Methods and apparatus for training a classification model and using the trained classification model to recognize gestures performed by a user. An apparatus comprising a processor programmed to: receiving, from the user via the plurality of neuromuscular sensors, a first plurality of neuromuscular signals when the user performs a first single action of the gesture; training a classification model based on a first plurality of neuromuscular signals, the training comprising: deriving values from the first plurality of neuromuscular signals, the values being indicative of a distinguishing characteristic of the gesture, the distinguishing characteristic including at least one characteristic that varies linearly with a force applied during performance of the gesture; and generating a first classification representation of the gesture in a classification model based on the value; and determining that the user performed a second single action of the gesture based on the trained classification model and the second plurality of neuromuscular signals.)