Yasutaka Furusho

According to our database, Yasutaka Furusho authored at least 6 papers between 2015 and 2021.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2021

Kernel ridge reconstruction for anomaly detection: general and low computational reconstruction.

Yasutaka Furusho, Shuhei Nitta, Yukinobu Sakata

Proceedings of the 20th IEEE International Conference on Machine Learning and Applications, 2021

2019

Skipping Two Layers in ResNet Makes the Generalization Gap Smaller than Skipping One or No Layer.

Yasutaka Furusho, Tongliang Liu, Kazushi Ikeda

Proceedings of the Recent Advances in Big Data and Deep Learning, 2019

Effects of Skip-Connection in ResNet and Batch-Normalization on Fisher Information Matrix.

Yasutaka Furusho, Kazushi Ikeda

Proceedings of the Recent Advances in Big Data and Deep Learning, 2019

ResNet and Batch-normalization Improve Data Separability.

Yasutaka Furusho, Kazushi Ikeda

Proceedings of The 11th Asian Conference on Machine Learning, 2019

2017

Roles of pre-training in deep neural networks from information theoretical perspective.

Yasutaka Furusho, Takatomi Kubo, Kazushi Ikeda

Neurocomputing, 2017

2015

Information Theoretical Analysis of Deep Learning Representations.

Yasutaka Furusho, Takatomi Kubo, Kazushi Ikeda

Proceedings of the Neural Information Processing - 22nd International Conference, 2015