Leveraging over intact priors for boosting control and dexterity of prosthetic hands by amputees

This becomes even more problematic with highly articulated modern prostheses. The natural use of these devices is challenging in everyday life primarily due to the software [2, 3, 4]. The open question is how to reduce this training time while making control as natural as possible. Machine learning has opened a new path to tackle this problem by allowing the prosthesis to adapt to the myoelectric signals of a specific user. Although these methods have been applied with success (e.g., [5] and references therein), they still require a significant amount of data from individual subjects to learn models with satisfactory performance. Consider a situation in which different subjects repeat the same hand postures and suppose that a new target user attempts to learn the same movements. In this case it should be beneficial to reuse the information from the latter subjects and thereby reduce the training data required from a new subject. However, even if a movement appears the same for all subjects, the distribution of their myoelectric signals is very different.