A number of studies in tetraplegic humans and healthy nonhuman primates (NHPs) have shown that neuronal activity from reachrelated cortical areas can be used to predict reach intentions using brain-machine interfaces (BMIs) and therefore assist tetraplegic patients by controlling external devices (e.g., robotic limbs and computer cursors). However, to our knowledge, there have been no studies that have applied BMIs to eye movement areas to decode intended eye movements. In this study, we recorded the activity from populations of neurons from the lateral intraparietal area (LIP), a cortical node in the NHP saccade system. Eye movement plans were predicted in real time using Bayesian inference from small ensembles of LIP neurons without the animal making an eye movement. Learning, defined as an increase in the prediction accuracy, occurred at the level of neuronal ensembles, particularly for difficult predictions. Population learning had two components: an update of the parameters of the BMI based on its history and a change in the responses of individual neurons. These results provide strong evidence that the responses of neuronal ensembles can be shaped with respect to a cost function, here the prediction accuracy of the BMI. Furthermore, eye movement plans could be decoded without the animals emitting any actual eye movements and could be used to control the position of a cursor on a computer screen. These findings show that BMIs for eye movements are promising aids for assisting paralyzed patients.learning | lateral intraparietal area | brain-machine interface | eye movements | saccades B rain-machine interfaces (BMIs) have been successfully used to predict reaches and arm movements (1-7). However, little effort has been concentrated on building a BMI based on eye movements. This gap is surprising because the motor and neuronal mechanisms of eye movements are very well understood and arguably simpler than those of arm movements. Specifically, eye movements are rapid and ballistic. The lateral intraparietal cortex (LIP) is ideally suited to be the site for a BMI based on eye movements (8). LIP neurons are known to encode eye movement plans, among other signals such as eye position (9-16). We recently showed that eye movement plans can be accurately predicted from the responses of populations of LIP neurons using Bayesian inference (16). The aim of the present study was twofold. First, a BMI was used with small neuronal ensembles of LIP neurons to predict, in real time, eye movement plans without the animals actually making eye movements. Second, the BMI application induced learning-related changes in the saccade system. Learning can produce changes in reach areas, but how learning-related changes occur at the level of LIP neuronal ensembles is still unclear (17,18).Here, we show that the intended eye movement activity can be used to accurately position a cursor on a computer screen. These results suggest that an eye movement BMI can be used as a prosthetic to assist locked-in patients who cannot produce eye mov...