José Antonio Pérez Carrasco
Papers
1
Total Citations
3
H-Index
1
About
José Antonio Pérez Carrasco is a researcher whose work sits at the intersection of unsupervised learning and robotic vision, with a particular focus on making deep neural networks more efficient. His most cited contribution, "Clustering Learning for Robotic Vision" (2013, 3 citations), introduces a novel unsupervised learning technique for multi-layer feedforward deep neural networks. The key innovation lies in its ability to compute network filters in just a few minutes using a drastically reduced set of parameters, challenging the conventional reliance on large, computationally expensive datasets. This work promotes a more accessible and faster approach to training vision systems, which is especially valuable in resource-constrained robotics applications. While his citation count is modest, the conceptual impact of his method is significant for researchers seeking to streamline deep learning pipelines. Pérez Carrasco’s research underscores a commitment to practical, efficient solutions in artificial intelligence, making his contributions a noteworthy reference for students and engineers exploring lightweight neural architectures for real-world vision tasks.
Research Focus
Key Achievements
Top Papers
- 1Clustering Learning for Robotic Vision3 citations · 2013