Mixture of Trajectory Models for Neural Decoding of Goal-Directed Movements

Abstract

Probabilistic decoding techniques have been used successfully to infer time-evolving physical state, such as arm trajectory or the path of a foraging rat, from neural data. A vital element of such decoders is the trajectory model, expressing knowledge about the statistical regularities of the movements. Unfortunately, trajectory models that both 1) accurately describe the movement statistics and 2) admit decoders with relatively low computational demands can be hard to construct. Simple models are computationally inexpensive, but often inaccurate. More complex models may gain accuracy, but at the expense of higher computational cost, hindering their use for real-time decoding. Here, we present a new general approach to defining trajectory models that simultaneously meets both requirements. The core idea is to combine simple trajectory models, each accurate within a limited regime of movement, in a probabilistic mixture of trajectory models (MTM). We demonstrate the utility of the approach by using an MTM decoder to infer goal-directed reaching movements to multiple discrete goals from multi-electrode neural data recorded in monkey motor and premotor cortex. Compared with decoders using simpler trajectory models, the MTM decoder reduced the decoding error by 38 (48) percent in two monkeys using 98 (99) units, without a necessary increase in running time. When available, prior information about the identity of the upcoming reach goal can be incorporated in a principled way, further reducing the decoding error by 20 (11) percent. Taken together, these advances should allow prosthetic cursors or limbs to be moved more accurately toward intended reach goals.

Motor cortical prediction of EMG: evidence that a kinetic brain-machine interface may be robust across altered movement dynamics

“…Morrow et al 2007;Scott and Kalaska 1997;Sergio et al 2005). Numerous BMI studies have reported kinematic decoder performance similar to ours but restricted to a single set of dynamical conditions (Brockwell et al 2004;Carmena et al 2003;Gupta and Ashe 2009;Kim et al 2006;Koike et al 2006;Serruya et al 2002;Stark and Abeles 2007;Taylor et al 2002;Wu et al 2006;Yu et al 2007). However, few BMI studies have directly addressed the role of M1 in the control of dynamical systems.…”

Neural prosthetic systems: Current problems and future directions

“…There has been extensive work in modeling spike trains [5], [38]- [42] and estimating firing rates [43]- [47]. While some decode algorithms average over neural activity in small temporal windows [17], some algorithms use firing rates or use spiking models directly [18]. Spiking models are another source of approximation in BMIs.…”

“…This occurred despite the fact that the training dataset included 3 other examples of reaches to the same angle and 6 other reaches to the same distance. It is notable that many other prosthetic experiments to date have used highly constrained movement tasks which may overestimate the ability of linear models to generalize [17], [48]. While these tests indeed demonstrate useful signal extraction from cortex, they do not test a broad range of behavior.…”

Techniques for extracting single-trial activity patterns from large-scale neural recordings

“…The decoded trajectory is thus a concise 'explanation' or summary of the high-dimensional neural data. Decoding techniques include linear filters [63,64], the population vector [62,65,66], and recursive Bayesian decoding using state-space models [67][68][69]. Most of these approaches attempt to infer something that can be directly observed/inferred on most trials (e.g., actual or expected arm trajectory), yet in some ways this is an advantage, as it allows evaluation of the performance of different decoding techniques.…”