Shuki Goto

SoftBank Group (Japan)

Papers

1

Total Citations

2

H-Index

1

About

Shuki Goto is a researcher at the intersection of robotics, neuroscience, and artificial intelligence, with a primary focus on visuomotor coordination and attention mechanisms in autonomous systems. His work investigates how recurrent neural networks can learn to dynamically shift visual attention based on task demands, enabling robots to flexibly adapt to changing environments and objectives. In his most cited paper, "Visualization of Focal Cues for Visuomotor Coordination by Gradient-based Methods," Goto demonstrates how attention is acquired and represented inside neural networks trained through supervised learning, providing critical insights into the internal representations that guide robotic behavior. Though early in his career, his research contributes to the broader goal of building more adaptive, intelligent machines that can learn from experience. By visualizing the "focal cues" that drive decision-making, Goto helps bridge the gap between neural network interpretability and practical robotics, laying groundwork for future advances in autonomous navigation and human-robot interaction.

Research Focus

Key Achievements

1
H-Index
1
Papers
2
Total Citations
2
Avg Citations/Paper
🏆 Most Cited Paper
Visualization of Focal Cues for Visuomotor Coordination by Gradient-based Methods: A Recurrent Neural Network Shifts The Attention Depending on Task Requirements
2 citations · 2020
📈 Most Prolific Year: 2020 (1 Papers)
🤝 Key Collaborators: 4
🏛 Institutions: SoftBank Group (Japan)

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago