Comparison of average error between unlearned positions and unlearned compositions
Comparison of average error between cases of unlearned object positions (blue) and unlearned compositions of words (orange) among groups with different numbers of compositions in training – Group A is trained on 40 compositions of 5 colors and 8 verb clauses, like ‘grasp yellow’, ‘move red to left’, and ‘put blue on green’. As the number of compositions in training decreases, error increases, especially when encountering unlearned compositions. This suggests that a greater variety in training is crucial for learning to generalize to different combinations of words, including unlearned combinations.
Copyright OIST (Okinawa Institute of Science and Technology Graduate University, 沖縄科学技術大学院大学). Creative Commons Attribution 4.0 International License (CC BY 4.0).